Search results for: speech dataset

Authors: Celso L. Fernando, Toshio Yoshii, Takahiro Tsubota

Abstract:

Understanding the causes of a road accident and predicting their occurrence is key to preventing deaths and serious injuries from road accident events. Traditional statistical methods such as the Poisson and the Logistics regressions have been used to find the association of the traffic environmental factors with the accident occurred; recently, an artificial neural network, ANN, a computational technique that learns from historical data to make a more accurate prediction, has emerged. Although the ability to make accurate predictions, the ANN has difficulty dealing with highly unbalanced attribute patterns distribution in the training dataset; in such circumstances, the ANN treats the minority group as noise. However, in the real world data, the minority group is often the group of interest; e.g., in the road traffic accident data, the events of the accident are the group of interest. This study proposes a combination of the k-means with the ANN to improve the predictive ability of the neural network model by alleviating the effect of the unbalanced distribution of the attribute patterns in the training dataset. The results show that the proposed method improves the ability of the neural network to make a prediction on a highly unbalanced distributed attribute patterns dataset; however, on an even distributed attribute patterns dataset, the proposed method performs almost like a standard neural network.

Keywords: accident risks estimation, artificial neural network, deep learning, k-mean, road safety

Procedia PDF Downloads 162

Authors: Zainab Mutlaq Ibrahim, Mohamed Bader-El-Den, Mihaela Cocea

Abstract:

Students' textual feedback can hold unique patterns and useful information about learning process, it can hold information about advantages and disadvantages of teaching methods, assessment components, facilities, and other aspects of teaching. The results of analysing such a feedback can form a key point for institutions’ decision makers to advance and update their systems accordingly. This paper proposes a data mining framework for analysing end of unit general textual feedback using part of speech feature (PoS) with four machine learning algorithms: support vector machines, decision tree, random forest, and naive bays. The proposed framework has two tasks: first, to use the above algorithms to build an optimal model that automatically classifies the whole data set into two subsets, one subset is tailored to assessment practices (assessment related), and the other one is the non-assessment related data. Second task to use the same algorithms to build an optimal model for whole data set, and the new data subsets to automatically detect their sentiment. The significance of this paper is to compare the performance of the above four algorithms using part of speech feature to the performance of the same algorithms using n-grams feature. The paper follows Knowledge Discovery and Data Mining (KDDM) framework to construct the classification and sentiment analysis models, which is understanding the assessment domain, cleaning and pre-processing the data set, selecting and running the data mining algorithm, interpreting mined patterns, and consolidating the discovered knowledge. The results of this paper experiments show that both models which used both features performed very well regarding first task. But regarding the second task, models that used part of speech feature has underperformed in comparison with models that used unigrams and bigrams.

Keywords: assessment, part of speech, sentiment analysis, student feedback

Procedia PDF Downloads 142

Authors: Essam Al Daoud

Abstract:

Gradient boosting methods have been proven to be a very important strategy. Many successful machine learning solutions were developed using the XGBoost and its derivatives. The aim of this study is to investigate and compare the efficiency of three gradient methods. Home credit dataset is used in this work which contains 219 features and 356251 records. However, new features are generated and several techniques are used to rank and select the best features. The implementation indicates that the LightGBM is faster and more accurate than CatBoost and XGBoost using variant number of features and records.

Keywords: gradient boosting, XGBoost, LightGBM, CatBoost, home credit

Procedia PDF Downloads 170

Authors: Zahra Fotovatnia, Jeffery A. Jones, Alexandra Gottardo

Abstract:

Speech communication often occurs in environments where noise conceals part of a message. Listeners should compensate for the lack of auditory information by picking up distinct acoustic cues and using semantic and sentential context to recreate the speaker’s intended message. This situation seems to be more challenging in a nonnative than native language. On the other hand, early bilinguals are expected to show an advantage over the late bilingual and monolingual speakers of a language due to their better executive functioning components. In this study, English monolingual speakers were compared with early and late nonnative speakers of English to understand speech in noise processing (SIN) and the underlying neurobiological features of this phenomenon. Auditory mismatch negativities (MMNs) were recorded using a double-oddball paradigm in response to a minimal pair that differed in their middle vowel (beat/bit) at Wilfrid Laurier University in Ontario, Canada. The results did not show any significant structural and electroneural differences across groups. However, vocabulary knowledge correlated positively with performance on tests that measured SIN processing in participants who learned English after age 6. Moreover, their performance on the test negatively correlated with the integral area amplitudes in the left superior temporal gyrus (STG). In addition, the STG was engaged before the inferior frontal gyrus (IFG) in noise-free and low-noise test conditions in all groups. We infer that the pre-attentive processing of words engages temporal lobes earlier than the fronto-central areas and that vocabulary knowledge helps the nonnative perception of degraded speech.

Keywords: degraded speech perception, event-related brain potentials, mismatch negativities, brain regions

Procedia PDF Downloads 107

Authors: Renukswamy Chikkamath, Vishvapalsinhji Ramsinh Parmar, Christoph Hewel, Markus Endres

Abstract:

Given a patent document, identifying distinct semantic annotations is an interesting research aspect. Text annotation helps the patent practitioners such as examiners and patent attorneys to quickly identify the key arguments of any invention, successively providing a timely marking of a patent text. In the process of manual patent analysis, to attain better readability, recognising the semantic information by marking paragraphs is in practice. This semantic annotation process is laborious and time-consuming. To alleviate such a problem, we proposed a dataset to train machine learning algorithms to automate the highlighting process. The contributions of this work are: i) we developed a multi-class dataset of size 150k samples by traversing USPTO patents over a decade, ii) articulated statistics and distributions of data using imperative exploratory data analysis, iii) baseline Machine Learning models are developed to utilize the dataset to address patent paragraph highlighting task, and iv) future path to extend this work using Deep Learning and domain-specific pre-trained language models to develop a tool to highlight is provided. This work assists patent practitioners in highlighting semantic information automatically and aids in creating a sustainable and efficient patent analysis using the aptitude of machine learning.

Keywords: machine learning, patents, patent sentiment analysis, patent information retrieval

Procedia PDF Downloads 88

Authors: Heeba A. Gurku

Abstract:

Introduction: Cone Beam CT(CBCT) images play an integral part in proper patient positioning in cancer patients undergoing radiation therapy treatment. But these images are low in quality. The purpose of this study is to generate high-quality synthetic CT images from CBCT using generative models. Material and Methods: This study utilized two datasets from The Cancer Imaging Archive (TCIA) 1) Lung cancer dataset of 20 patients (with full view CBCT images) and 2) Pancreatic cancer dataset of 40 patients (only 27 patients having limited view images were included in the study). Cycle Generative Adversarial Networks (GAN) and its variant Attention Guided Generative Adversarial Networks (AGGAN) models were used to generate the synthetic CTs. Models were evaluated by visual evaluation and on four metrics, Structural Similarity Index Measure (SSIM), Peak Signal Noise Ratio (PSNR) Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), to compare the synthetic CT and original CT images. Results: For pancreatic dataset with limited view CBCT images, our study showed that in Cycle GAN model, MAE, RMSE, PSNR improved from 12.57to 8.49, 20.94 to 15.29 and 21.85 to 24.63, respectively but structural similarity only marginally increased from 0.78 to 0.79. Similar, results were achieved with AGGAN with no improvement over Cycle GAN. However, for lung dataset with full view CBCT images Cycle GAN was able to reduce MAE significantly from 89.44 to 15.11 and AGGAN was able to reduce it to 19.77. Similarly, RMSE was also decreased from 92.68 to 23.50 in Cycle GAN and to 29.02 in AGGAN. SSIM and PSNR also improved significantly from 0.17 to 0.59 and from 8.81 to 21.06 in Cycle GAN respectively while in AGGAN SSIM increased to 0.52 and PSNR increased to 19.31. In both datasets, GAN models were able to reduce artifacts, reduce noise, have better resolution, and better contrast enhancement. Conclusion and Recommendation: Both Cycle GAN and AGGAN were significantly able to reduce MAE, RMSE and PSNR in both datasets. However, full view lung dataset showed more improvement in SSIM and image quality than limited view pancreatic dataset.

Keywords: CT images, CBCT images, cycle GAN, AGGAN

Procedia PDF Downloads 83

Authors: Joy Aworo-Okoroh

Abstract:

Literary texts are mirrors of a real-life situation. Thus, authors choose the linguistic items that would best encode their intended meanings and messages. However, words mean more than they seem. The meaning of words is not static rather, it is dynamic as they constantly enter into relationships within a context. Literary texts can only be meaningful if all pragmatic cues are identified and interpreted. Drawing upon Teun Van Djik's theory of local pragmatic coherence, it is established that words enter into relations in a text and these relations account for sequential speech acts in the texts. Comprehension of the text is dependent on the interpretation of these relations.To show the relevance of pragmatic coherence in literary text analysis, ten conversations were selected in Americanah in order to give a clear idea of the pragmatic relations used. The conversations were analysed, identifying the speech act and epistemic relations inherent in them. A subtle analysis of the structure of the conversations was also carried out. It was discovered that justification is the most commonly used relation and the meaning of the text is dependent on the interpretation of these instances' pragmatic coherence. The study concludes that to effectively teach literature in English, pragmatic coherence should be incorporated as words mean more than they say.

Keywords: pragmatic coherence, epistemic coherence, speech act, Americanah

Procedia PDF Downloads 135

Authors: Tiago do Carmo Nogueira, Cássio Dener Noronha Vinhal, Gélson da Cruz Júnior, Matheus Rudolfo Diedrich Ullmann

Abstract:

Generating automatic image descriptions through natural language is a challenging task. Image captioning is a task that consistently describes an image by combining computer vision and natural language processing techniques. To accomplish this task, cutting-edge models use encoder-decoder structures. Thus, Convolutional Neural Networks (CNN) are used to extract the characteristics of the images, and Recurrent Neural Networks (RNN) generate the descriptive sentences of the images. However, cutting-edge approaches still suffer from problems of generating incorrect captions and accumulating errors in the decoders. To solve this problem, we propose a model based on the encoder-decoder structure, introducing a module that generates the weights according to the importance of the word to form the sentence, using the part-of-speech (PoS). Thus, the results demonstrate that our model surpasses state-of-the-art models.

Keywords: gated recurrent units, caption generation, convolutional neural network, part-of-speech

Procedia PDF Downloads 101

Authors: Alimohamad Asghari, Ahmad Daneshi, Mohammad Farhadi, Arash Bayat, Mohammad Ajalloueyan, Marjan Mirsalehi, Mohsen Rajati, Seyed Basir Hashemi, Nader Saki, Ali Omidvari

Abstract:

Evidence suggests that Cochlear Implantation (CI) is a beneficial approach for auditory and speech skills improvement in children with severe to profound hearing loss. However, it remains controversial if implantation in children <12 months is safe and effective compared to older children. The present study aimed to determine whether children's ages affect surgical complications and auditory and speech development. The current multicenter study enrolled 86 children who underwent CI surgery at <12 months of age (group A) and 362 children who underwent implantation between 12 and 24 months of age (group B). The Categories of Auditory Performance (CAP) and Speech Intelligibility Rating (SIR) scores were determined pre-impanation, and "one-year" and "two-year" post-implantation. Four complications (overall rate: 4.65%; three minor) occurred in group A and 12 complications (overall rate: 4.41%; nine minor) occurred in group B. We found no statistically significant difference in the complication rates between the groups (p>0.05). The mean SIR and CAP scores improved over time following CI activation in both groups. However, we did not find significant differences in CAP and SIR scores between the groups across different time points. Cochlear implantation is a safe and efficient procedure in children younger than 12 months, providing substantial auditory and speech benefits comparable to children undergoing implantation at 12 to 24 months of age. Furthermore, surgical complications in younger children are similar to those of children undergoing the CI at an older age.

Keywords: cochlear implant, Infant, complications, outcome

Procedia PDF Downloads 107

Authors: Sadeq Al Yaari, Fayza Al Hammadi, Ayman Al Yaari, Adham Al Yaari, Montaha Al Yaari, Aayah Al Yaari, Sajedah Al Yaari, Salah Al Yami

Abstract:

Background: When we further take Arabic grammatical issues into account in accordance with applied linguistic investigations on Arabic as Second Language (ASL) learners, a fundamental issue arises at this point as to the production of speech in Arabic: Oral grammatical errors committed by ASL learners. Aims: Using manual rating as well as computational analytic methodology to test a corpus of recorded speech by Second Language (ASL) learners of Arabic, this study aims to find the areas of difficulties in learning Arabic grammar. More specifically, it examines how and why ASL learners make grammatical errors in their oral speech. Methods: Tape recordings of four (4) Arabic as Second Language (ASL) learners who ranged in age from 23 to 30 were naturally collected. All participants have completed an intensive Arabic program (two years) and 20 minute-speech was recorded for each participant. Having the collected corpus, the next procedure was to rate them against Arabic standard grammar. The rating includes four processes: Description, analysis and assessment. Conclusions: Outcomes made from the issues addressed in this paper can be summarized in the fact that ASL learners face many grammatical difficulties when studying Arabic word order, tenses and aspects, function words, subject-verb agreement, verb form, active-passive voice, global and local errors, processes-based errors including addition, omission, substitution or a combination of any of them.

Keywords: grammar, error, oral, Arabic, second language, learner, applied linguistics.

Procedia PDF Downloads 44

Authors: Deeman Yousif Mahmood, Mohammed Abdullah Hussein

Abstract:

The goal of a network-based intrusion detection system is to classify activities of network traffics into two major categories: normal and attack (intrusive) activities. Nowadays, data mining and machine learning plays an important role in many sciences; including intrusion detection system (IDS) using both supervised and unsupervised techniques. However, one of the essential steps of data mining is feature selection that helps in improving the efficiency, performance and prediction rate of proposed approach. This paper applies unsupervised K-means clustering algorithm with information gain (IG) for feature selection and reduction to build a network intrusion detection system. For our experimental analysis, we have used the new NSL-KDD dataset, which is a modified dataset for KDDCup 1999 intrusion detection benchmark dataset. With a split of 60.0% for the training set and the remainder for the testing set, a 2 class classifications have been implemented (Normal, Attack). Weka framework which is a java based open source software consists of a collection of machine learning algorithms for data mining tasks has been used in the testing process. The experimental results show that the proposed approach is very accurate with low false positive rate and high true positive rate and it takes less learning time in comparison with using the full features of the dataset with the same algorithm.

Keywords: information gain (IG), intrusion detection system (IDS), k-means clustering, Weka

Procedia PDF Downloads 294

Authors: Albatool Al Abdulwahid, Bayan Shakally, Mariam Mohamed, Wed Almokri

Abstract:

Artificial intelligence has infiltrated every part of our life and every field we can think of. With technical developments, artificial intelligence applications are becoming more prevalent. We chose ELSA speak because it is a magnificent example of Artificial intelligent applications, ELSA speak is a smartphone application that is free to download on both IOS and Android smartphones. ELSA speak utilizes artificial intelligence to help non-native English speakers pronounce words and phrases similar to a native speaker, as well as enhance their English skills. It employs speech-recognition technology that aids the application to excel the pronunciation of its users. This remarkable feature distinguishes ELSA from other voice recognition algorithms and increase the efficiency of the application. This study focused on evaluating ELSA speak application, by testing the degree of effectiveness based on survey questions. The results of the questionnaire were variable. The generality of the participants strongly agreed that ELSA has helped them enhance their pronunciation skills. However, a few participants were unconfident about the application’s ability to assist them in their learning journey.

Keywords: ELSA speak application, artificial intelligence, speech-recognition technology, language learning, english pronunciation

Procedia PDF Downloads 103

Authors: T. Thein, S. Kalyar Myo

Abstract:

Human uses visual information for understanding the speech contents in noisy conditions or in situations where the audio signal is not available. The primary advantage of visual information is that it is not affected by the acoustic noise and cross talk among speakers. Using visual information from the lip movements can improve the accuracy and robustness of automatic speech recognition. However, a major challenge with most automatic lip reading system is to find a robust and efficient method for extracting the linguistically relevant speech information from a lip image sequence. This is a difficult task due to variation caused by different speakers, illumination, camera setting and the inherent low luminance and chrominance contrast between lip and non-lip region. Several researchers have been developing methods to overcome these problems; the one is lip reading. Moreover, it is well known that visual information about speech through lip reading is very useful for human speech recognition system. Lip reading is the technique of a comprehensive understanding of underlying speech by processing on the movement of lips. Therefore, lip reading system is one of the different supportive technologies for hearing impaired or elderly people, and it is an active research area. The need for lip reading system is ever increasing for every language. This research aims to develop a visual teaching method system for the hearing impaired persons in Myanmar, how to pronounce words precisely by identifying the features of lip movement. The proposed research will work a lip reading system for Myanmar Consonants, one syllable consonants (င (Nga)၊ ည (Nya)၊ မ (Ma)၊ လ (La)၊ ၀ (Wa)၊ သ (Tha)၊ ဟ (Ha)၊ အ (Ah) ) and two syllable consonants ( က(Ka Gyi)၊ ခ (Kha Gway)၊ ဂ (Ga Nge)၊ ဃ (Ga Gyi)၊ စ (Sa Lone)၊ ဆ (Sa Lain)၊ ဇ (Za Gwe) ၊ ဒ (Da Dway)၊ ဏ (Na Gyi)၊ န (Na Nge)၊ ပ (Pa Saug)၊ ဘ (Ba Gone)၊ ရ (Ya Gaug)၊ ဠ (La Gyi) ). In the proposed system, there are three subsystems, the first one is the lip localization system, which localizes the lips in the digital inputs. The next one is the feature extraction system, which extracts features of lip movement suitable for visual speech recognition. And the final one is the classification system. In the proposed research, Two Dimensional Discrete Cosine Transform (2D-DCT) and Linear Discriminant Analysis (LDA) with Active Contour Model (ACM) will be used for lip movement features extraction. Support Vector Machine (SVM) classifier is used for finding class parameter and class number in training set and testing set. Then, experiments will be carried out for the recognition accuracy of Myanmar consonants using the only visual information on lip movements which are useful for visual speech of Myanmar languages. The result will show the effectiveness of the lip movement recognition for Myanmar Consonants. This system will help the hearing impaired persons to use as the language learning application. This system can also be useful for normal hearing persons in noisy environments or conditions where they can find out what was said by other people without hearing voice.

Keywords: feature extraction, lip reading, lip localization, Active Contour Model (ACM), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Two Dimensional Discrete Cosine Transform (2D-DCT)

Procedia PDF Downloads 282

Authors: Bharatendra Rai

Abstract:

Predictive data analysis and modeling involving machine learning techniques become challenging in presence of too many explanatory variables or features. Presence of too many features in machine learning is known to not only cause algorithms to slow down, but they can also lead to decrease in model prediction accuracy. This study involves housing dataset with 79 quantitative and qualitative features that describe various aspects people consider while buying a new house. Boruta algorithm that supports feature selection using a wrapper approach build around random forest is used in this study. This feature selection process leads to 49 confirmed features which are then used for developing predictive random forest models. The study also explores five different data partitioning ratios and their impact on model accuracy are captured using coefficient of determination (r-square) and root mean square error (rsme).

Keywords: housing data, feature selection, random forest, Boruta algorithm, root mean square error

Procedia PDF Downloads 321

Authors: Chithra A. V., Somoshree Datta, Sandeep Nithyanandan

Abstract:

Sign Language Recognition (SLR) is the process of interpreting and translating sign language into spoken or written language using technological systems. It involves recognizing hand gestures, facial expressions, and body movements that makeup sign language communication. The primary goal of SLR is to facilitate communication between hearing- and speech-impaired communities and those who do not understand sign language. Due to the increased awareness and greater recognition of the rights and needs of the hearing- and speech-impaired community, sign language recognition has gained significant importance over the past 10 years. Technological advancements in the fields of Artificial Intelligence and Machine Learning have made it more practical and feasible to create accurate SLR systems. This paper presents a distinct approach to SLR by framing it as a video classification problem using Deep Learning (DL), whereby a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) has been used. This research targets the integration of sign language recognition into healthcare settings, aiming to improve communication between medical professionals and patients with hearing impairments. The spatial features from each video frame are extracted using a CNN, which captures essential elements such as hand shapes, movements, and facial expressions. These features are then fed into an RNN network that learns the temporal dependencies and patterns inherent in sign language sequences. The INCLUDE dataset has been enhanced with more videos from the healthcare domain and the model is evaluated on the same. Our model achieves 91% accuracy, representing state-of-the-art performance in this domain. The results highlight the effectiveness of treating SLR as a video classification task with the CNN-RNN architecture. This approach not only improves recognition accuracy but also offers a scalable solution for real-time SLR applications, significantly advancing the field of accessible communication technologies.

Keywords: sign language recognition, deep learning, convolution neural network, recurrent neural network

Procedia PDF Downloads 24

Authors: Rasha Salameh

Abstract:

In light of the tense relationship between Saudi Arabia and Iran, this research paper sheds some light on Al-Arabiya’s reporting of Coronavirus in the Gulf. Particularly because most of the cases, in the beginning, were coming from Iran, some programs of this Saudi channel embraced a conspiracy theory. Hate speech has been used in talking about the topic and discussing it. The results of these discussions will be detailed in this paper in percentages with regard to the research sample, which includes five programs on Al-Arabiya channel: ‘DNA’, ‘Marraya’ (Mirrors), ‘Panorama’, ‘Tafaolcom’ (Your Interaction) and the ‘Diplomatic Street’, in the period between January 19, that is, the date of the first case in Iran, and April 10, 2020. The research shows the use of a conspiracy theory in the programs, in addition to some professional violations. The surveyed sample also shows that the matter receded due to the Arab Gulf states' preoccupation with the successively increasing cases that have appeared there since the start of the pandemic. The results indicate that hate speech was present in the sample at a rate of 98.1% and that most of the programs that dealt with the Iranian issue under the Corona pandemic on Al Arabiya used the conspiracy theory at a rate of 75.5%.

Keywords: Al-Arabiya, Iran, Corona, hate speech, conspiracy theory, politicization of the pandemic

Procedia PDF Downloads 134

Authors: Shantanu Arya, Sachin Sakhuja, Gunjan Mehta, Sanjay Munjal

Abstract:

Stuttering may be defined as a speech disorder affecting the fluency domain of speech and characterized by covert features like word substitution, omittance and circumlocution and overt features like prolongation of sound, syllables and blocks etc. Many etiologies have been postulated to explain stuttering based on various experiments and research. Moreover, Breathlessness has also been reported by many individuals with stuttering for which breathing exercises are generally advised. However, no studies reporting objective evaluation of the pulmonary capacity and further objective assessment of the efficacy of breathing exercises have been conducted. Pulmonary Function Test which evaluates parameters like Forced Vital Capacity, Peak Expiratory Flow Rate, Forced expiratory flow Rate can be used to study the pulmonary behavior of individuals with stuttering. The study aimed: a) To identify speech motor & physiologic behaviours associated with stuttering by administering PFT. b) To recognize possible reasons for an association between speech motor behaviour & stuttering severity. In this regard, PFT tests were administered on individuals who reported signs and symptoms of stuttering and showed abnormal scores on Stuttering Severity Index. Parameters like Forced Vital Capacity, Forced Expiratory Volume, Peak Expiratory Flow Rate (L/min), Forced Expiratory Flow Rate (L/min) were evaluated and correlated with scores of Stuttering Severity Index. Results showed significant decrease in the parameters (lower than normal scores) in individuals with established stuttering. Strong correlation was also found between degree of stuttering and the degree of decrease in the pulmonary volumes. Thus, it is evident that fluent speech requires strong support of lung pressure and requisite volumes. Further research in demonstrating the efficacy of abdominal breathing exercises in this regard is needed.

Keywords: forced expiratory flow rate, forced expiratory volume, forced vital capacity, peak expiratory flow rate, stuttering

Procedia PDF Downloads 274

Authors: Vishal Raj, Noorhan Abbas

Abstract:

Ambiguity in NLP (Natural language processing) refers to the ability of a word, phrase, sentence, or text to have multiple meanings. This results in various kinds of ambiguities such as lexical, syntactic, semantic, anaphoric and referential am-biguities. This study is focused mainly on solving the issue of Lexical ambiguity. Word Sense Disambiguation (WSD) is an NLP technique that aims to resolve lexical ambiguity by determining the correct meaning of a word within a given context. Most WSD solutions rely on words for training and testing, but we have used lemma and Part of Speech (POS) tokens of words for training and testing. Lemma adds generality and POS adds properties of word into token. We have designed a novel method to create an affinity matrix to calculate the affinity be-tween any pair of lemma_POS (a token where lemma and POS of word are joined by underscore) of given training set. Additionally, we have devised an al-gorithm to create the sense clusters of tokens using affinity matrix under hierar-chy of POS of lemma. Furthermore, three different mechanisms to predict the sense of target word using the affinity/similarity value are devised. Each contex-tual token contributes to the sense of target word with some value and whichever sense gets higher value becomes the sense of target word. So, contextual tokens play a key role in creating sense clusters and predicting the sense of target word, hence, the model is named Contextual SenSe Model (CSM). CSM exhibits a noteworthy simplicity and explication lucidity in contrast to contemporary deep learning models characterized by intricacy, time-intensive processes, and chal-lenging explication. CSM is trained on SemCor training data and evaluated on SemEval test dataset. The results indicate that despite the naivety of the method, it achieves promising results when compared to the Most Frequent Sense (MFS) model.

Keywords: word sense disambiguation (wsd), contextual sense model (csm), most frequent sense (mfs), part of speech (pos), natural language processing (nlp), oov (out of vocabulary), lemma_pos (a token where lemma and pos of word are joined by underscore), information retrieval (ir), machine translation (mt)

Procedia PDF Downloads 105

Authors: Seham El Kareh, Miramar Etman

Abstract:

Recently, detecting liars and extracting features which distinguish them from truth-tellers have been the focus of a wide range of disciplines. To the author’s best knowledge, most of the work has been done on facial expressions and body gestures but only few works have been done on the language used by both liars and truth-tellers. This paper sheds light on four axes. The first axis copes with building an audio corpus for deceptive and truthful speech for Egyptian Arabic speakers. The second axis focuses on examining the human perception of lies and proving our need for computational linguistic-based methods to extract features which characterize truthful and deceptive speech. The third axis is concerned with building a linguistic analysis program that could extract from the corpus the inter- and intra-linguistic cues for deceptive and truthful speech. The program built here is based on selected categories from the Linguistic Inquiry and Word Count program. Our results demonstrated that Egyptian Arabic speakers on one hand preferred to use first-person pronouns and present tense compared to the past tense when lying and their lies lacked of second-person pronouns, and on the other hand, when telling the truth, they preferred to use the verbs related to motion and the nouns related to time. The results also showed that there is a need for bigger data to prove the significance of words related to emotions and numbers.

Keywords: Egyptian Arabic corpus, computational analysis, deceptive features, forensic linguistics, human perception, truthful features

Procedia PDF Downloads 204

Authors: Sakda Loetpiparwanich, Preecha Vichitthamaros

Abstract:

Nowadays, poor data quality is considered one of the majority costs for a data project. The data project with data quality awareness almost as much time to data quality processes while data project without data quality awareness negatively impacts financial resources, efficiency, productivity, and credibility. One of the processes that take a long time is defining the expectations and measurements of data quality because the expectation is different up to the purpose of each data project. Especially, big data project that maybe involves with many datasets and stakeholders, that take a long time to discuss and define quality expectations and measurements. Therefore, this study aimed at developing meaningful indicators to describe overall data quality for each dataset to quick comparison and priority. The objectives of this study were to: (1) Develop a practical data quality indicators and measurements, (2) Develop data quality dimensions based on statistical characteristics and (3) Develop Composite Indicator that can describe overall data quality for each dataset. The sample consisted of more than 500 datasets from public sources obtained by random sampling. After datasets were collected, there are five steps to develop the Dataset Quality Index (SDQI). First, we define standard data quality expectations. Second, we find any indicators that can measure directly to data within datasets. Thirdly, each indicator aggregates to dimension using factor analysis. Next, the indicators and dimensions were weighted by an effort for data preparing process and usability. Finally, the dimensions aggregate to Composite Indicator. The results of these analyses showed that: (1) The developed useful indicators and measurements contained ten indicators. (2) the developed data quality dimension based on statistical characteristics, we found that ten indicators can be reduced to 4 dimensions. (3) The developed Composite Indicator, we found that the SDQI can describe overall datasets quality of each dataset and can separate into 3 Level as Good Quality, Acceptable Quality, and Poor Quality. The conclusion, the SDQI provide an overall description of data quality within datasets and meaningful composition. We can use SQDI to assess for all data in the data project, effort estimation, and priority. The SDQI also work well with Agile Method by using SDQI to assessment in the first sprint. After passing the initial evaluation, we can add more specific data quality indicators into the next sprint.

Keywords: data quality, dataset quality, data quality management, composite indicator, factor analysis, principal component analysis

Procedia PDF Downloads 138

Authors: Sadeq Al Yaari, Muhammad Alkhunayn, Montaha Al Yaari, Ayman Al Yaari, Aayah Al Yaari, Adham Al Yaari, Sajedah Al Yaari, Fatehi Eissa

Abstract:

Introduction: It is well established that lengthening (longer duration) is considered one of the correlates of lexical and phrasal prominence. However, it is unexplored whether the scope of vowel lengthening in the Arabic dialect of Yemen (ADY) is differently affected by educated and/or uneducated speakers from different dialectal backgrounds. Specifically, the research aims to examine whether or not linguistic background acquired through different educational channels makes a difference in the speech of the speaker and how that is reflected in related psychoneurolinguistic impairments. Methods: For the above mentioned purpose, we conducted an articulatory experiment wherein a set of words from ADY were examined in the dialectal speech of thousand and seven hundred Yemeni educated and uneducated speakers aged 19-61 years growing up in five regions of the country: Northern, southern, eastern, western and central and were, accordingly, assigned into five dialectal groups. A seven-minute video clip was shown to the participants, who have been asked to spontaneously describe the scene they had just watched before the researchers linguistically and statistically analyzed recordings to weigh vowel lengthening in the speech of the participants. Results: The results show that vowels (monophthongs and diphthongs) are lengthened by all participants. Unexpectedly, educated and uneducated speakers from northern and central dialects lengthen vowels. Compared with uneducated speakers from the same dialect, educated speakers lengthen fewer vowels in their dialectal speech. Conclusions: These findings support the notion that extensive exposure to dialects on account of standard language can cause changes to the patterns of dialects themselves, and this can be seen in the speech of educated and uneducated speakers of these dialects. Further research is needed to clarify the phonemic distinctive features and frequency of lengthening in other open class systems (i.e., nouns, adjectives, and adverbs). Phonetic and phonological report measures are needed as well as validation of existing measures for assessing phonemic vowel length in the Arabic population in general and Arabic individuals with voice, speech, and language impairments in particular.

Keywords: vowel lengthening, Arabic dialect of Yemen, phonetics, phonology, impairment, distinctive features

Procedia PDF Downloads 40

Authors: Zuzanna Miodonska, Michal Krecichwost, Pawel Badura

Abstract:

Sigmatism (lisping) is a speech disorder in which sibilant consonants are mispronounced. The diagnosis of this phenomenon is usually based on the auditory assessment. However, the progress in speech analysis techniques creates a possibility of developing computer-aided sigmatism diagnosis tools. The aim of the study is to statistically verify whether specific acoustic features of sibilant sounds may be related to pronunciation correctness. Such knowledge can be of great importance while implementing classifiers and designing novel tools for automatic sibilants pronunciation evaluation. The study covers analysis of various speech signal measures, including features proposed in the literature for the description of normative sibilants realization. Amplitudes and frequencies of three fricative formants (FF) are extracted based on local spectral maxima of the friction noise. Skewness, kurtosis, four normalized spectral moments (SM) and 13 mel-frequency cepstral coefficients (MFCC) with their 1st and 2nd derivatives (13 Delta and 13 Delta-Delta MFCC) are included in the analysis as well. The resulting feature vector contains 51 measures. The experiments are performed on the speech corpus containing words with selected sibilant sounds (/ʃ, ʒ/) pronounced by 60 preschool children with proper pronunciation or with natural pathologies. In total, 224 /ʃ/ segments and 191 /ʒ/ segments are employed in the study. The Mann-Whitney U test is employed for the analysis of stigmatism and normative pronunciation. Statistically, significant differences are obtained in most of the proposed features in children divided into these two groups at p < 0.05. All spectral moments and fricative formants appear to be distinctive between pathology and proper pronunciation. These metrics describe the friction noise characteristic for sibilants, which makes them particularly promising for the use in sibilants evaluation tools. Correspondences found between phoneme feature values and an expert evaluation of the pronunciation correctness encourage to involve speech analysis tools in diagnosis and therapy of sigmatism. Proposed feature extraction methods could be used in a computer-assisted stigmatism diagnosis or therapy systems.

Keywords: computer-aided pronunciation evaluation, sigmatism diagnosis, speech signal analysis, statistical verification

Procedia PDF Downloads 299

Authors: Ghazal Faraj, Andras Micsik

Abstract:

The CIDOC Conceptual Reference Model (CRM) is an extensible ontology that provides integrated access to heterogeneous and digital datasets. The CIDOC-CRM offers a “semantic glue” intended to promote accessibility to several diverse and dispersed sources of cultural heritage data. That is achieved by providing a formal structure for the implicit and explicit concepts and their relationships in the cultural heritage field. The COURAGE (“Cultural Opposition – Understanding the CultuRal HeritAGE of Dissent in the Former Socialist Countries”) project aimed to explore methods about socialist-era cultural resistance during 1950-1990 and planned to serve as a basis for further narratives and digital humanities (DH) research. This project highlights the diversity of flourished alternative cultural scenes in Eastern Europe before 1989. Moreover, the dataset of COURAGE is an online RDF-based registry that consists of historical people, organizations, collections, and featured items. For increasing the inter-links between different datasets and retrieving more relevant data from various data silos, a shared federated ontology for reconciled data is needed. As a first step towards these goals, a full understanding of the CIDOC CRM ontology (target ontology), as well as the COURAGE dataset, was required to start the work. Subsequently, the queries toward the ontology were determined, and a table of equivalent properties from COURAGE and CIDOC CRM was created. The structural diagrams that clarify the mapping process and construct queries are on progress to map person, organization, and collection entities to the ontology. Through mapping the COURAGE dataset to CIDOC-CRM ontology, the dataset will have a common ontological foundation with several other datasets. Therefore, the expected results are: 1) retrieving more detailed data about existing entities, 2) retrieving new entities’ data, 3) aligning COURAGE dataset to a standard vocabulary, 4) running distributed SPARQL queries over several CIDOC-CRM datasets and testing the potentials of distributed query answering using SPARQL. The next plan is to map CIDOC-CRM to other upper-level ontologies or large datasets (e.g., DBpedia, Wikidata), and address similar questions on a wide variety of knowledge bases.

Keywords: CIDOC CRM, cultural heritage data, COURAGE dataset, ontology alignment

Procedia PDF Downloads 144

Authors: Azita Ramezani, Ghazal Mashhadiagha, Bahareh Sanabakhsh

Abstract:

This study researches the combination of Random. Forest classifiers with large language models (LLMs) and natural language processing (NLP) to improve diagnostic accuracy in chest X-ray analysis using the Indiana University dataset. Utilizing advanced NLP techniques, the research preprocesses textual data from radiological reports to extract key features, which are then merged with image-derived data. This improved dataset is analyzed with Random Forest classifiers to predict specific clinical results, focusing on the identification of health issues and the estimation of case urgency. The findings reveal that the combination of NLP, LLMs, and machine learning not only increases diagnostic precision but also reliability, especially in quickly identifying critical conditions. Achieving an accuracy of 99.35%, the model shows significant advancements over conventional diagnostic techniques. The results emphasize the large potential of machine learning in medical imaging, suggesting that these technologies could greatly enhance clinician judgment and patient outcomes by offering quicker and more precise diagnostic approximations.

Keywords: natural language processing (NLP), large language models (LLMs), random forest classifier, chest x-ray analysis, medical imaging, diagnostic accuracy, indiana university dataset, machine learning in healthcare, predictive modeling, clinical decision support systems

Procedia PDF Downloads 42

Authors: Archit Yajnik

Abstract:

Part of Speech Tagging has always been a challenging task in the era of Natural Language Processing. This article presents POS tagging for Nepali text using Hidden Markov Model and Viterbi algorithm. From the Nepali text, annotated corpus training and testing data set are randomly separated. Both methods are employed on the data sets. Viterbi algorithm is found to be computationally faster and accurate as compared to HMM. The accuracy of 95.43% is achieved using Viterbi algorithm. Error analysis where the mismatches took place is elaborately discussed.

Keywords: hidden markov model, natural language processing, POS tagging, viterbi algorithm

Procedia PDF Downloads 325

Authors: Kaleem Kashif, Tayyaba Anam, Yizhi Wu

Abstract:

This paper introduces a methodology for advancing Italian speech vowels landmark detection within the distinctive feature-based speech recognition domain. Leveraging the legacy tool 'xkl' by integrating combined convolutional neural networks (CNNs) and recurrent neural networks (RNNs), the study presents a comprehensive enhancement to the 'xkl' legacy software. This integration incorporates re-assigned spectrogram methodologies, enabling meticulous acoustic analysis. Simultaneously, our proposed model, integrating combined CNNs and RNNs, demonstrates unprecedented precision and robustness in landmark detection. The augmentation of re-assigned spectrogram fusion within the 'xkl' software signifies a meticulous advancement, particularly enhancing precision related to vowel formant estimation. This augmentation catalyzes unparalleled accuracy in landmark detection, resulting in a substantial performance leap compared to conventional methods. The proposed model emerges as a state-of-the-art solution in the distinctive feature-based speech recognition systems domain. In the realm of deep learning, a synergistic integration of combined CNNs and RNNs is introduced, endowed with specialized temporal embeddings, harnessing self-attention mechanisms, and positional embeddings. The proposed model allows it to excel in capturing intricate dependencies within Italian speech vowels, rendering it highly adaptable and sophisticated in the distinctive feature domain. Furthermore, our advanced temporal modeling approach employs Bayesian temporal encoding, refining the measurement of inter-landmark intervals. Comparative analysis against state-of-the-art models reveals a substantial improvement in accuracy, highlighting the robustness and efficacy of the proposed methodology. Upon rigorous testing on a database (LaMIT) speech recorded in a silent room by four Italian native speakers, the landmark detector demonstrates exceptional performance, achieving a 95% true detection rate and a 10% false detection rate. A majority of missed landmarks were observed in proximity to reduced vowels. These promising results underscore the robust identifiability of landmarks within the speech waveform, establishing the feasibility of employing a landmark detector as a front end in a speech recognition system. The synergistic integration of re-assigned spectrogram fusion, CNNs, RNNs, and Bayesian temporal encoding not only signifies a significant advancement in Italian speech vowels landmark detection but also positions the proposed model as a leader in the field. The model offers distinct advantages, including unparalleled accuracy, adaptability, and sophistication, marking a milestone in the intersection of deep learning and distinctive feature-based speech recognition. This work contributes to the broader scientific community by presenting a methodologically rigorous framework for enhancing landmark detection accuracy in Italian speech vowels. The integration of cutting-edge techniques establishes a foundation for future advancements in speech signal processing, emphasizing the potential of the proposed model in practical applications across various domains requiring robust speech recognition systems.

Keywords: landmark detection, acoustic analysis, convolutional neural network, recurrent neural network

Procedia PDF Downloads 62

Authors: P. Renjitha, P. Hari Prakash

Abstract:

Auditory neuropathy spectrum disorder (ANSD) is an auditory disorder with normal cochlear outer hair cell function and disrupted auditory nerve function. It results in unique clinical characteristic with absent auditory brainstem response (ABR), absent acoustic reflex and the presence of otoacoustic emissions (OAE) and cochlear microphonics. The lesion site could be at cochlear inner hair cells, the synapse between the inner hair cells and type I auditory nerve fibers, and/or the auditory nerve itself. But the literatures on synchrony at higher auditory system are sporadic and are less understood. It might be interesting to see if there is a recovery of neural synchrony at higher auditory centers. Also, does the level at which the auditory system recovers with adequate synchrony to the extent of observable evoke response potentials (ERPs) can predict speech perception? In the current study, eight ANSD participants and healthy controls underwent detailed audiological assessment including ABR, auditory middle latency response (AMLR), and auditory late latency response (ALLR). AMLR was recorded for clicks and ALLR was evoked using 500Hz and 2 kHz tone bursts. Analysis revealed that the participant could be categorized into three groups. Group I (2/8) where ALLR was present only for 2kHz tone burst. Group II (4/8), where AMLR was absent and ALLR was seen for both the stimuli. Group III (2/8) consisted individuals with identifiable AMLR and ALLR for all the stimuli. The highest speech identification sore observed in ANSD group was 30% and hence considered having poor speech perception. Overall test result indicates that the site of neural synchrony recovery could be varying across individuals with ANSD. Some individuals show recovery of neural synchrony at the thalamocortical level while others show the same only at the cortical level. Within ALLR itself there could be variation across stimuli again could be related to neural synchrony. Nevertheless, none of these patterns could possible explain the speech perception ability of the individuals. Hence, it could be concluded that neural synchrony as measured by evoked potentials could not be a good clinical predictor speech perception.

Keywords: auditory late latency response, auditory middle latency response, auditory neuropathy spectrum disorder, correlation with speech identification score

Procedia PDF Downloads 147

Authors: Virender Singh, Mathew Rees, Simon Hampton, Sivaram Annadurai

Abstract:

Plant identification is a challenging task that aims to identify the family, genus, and species according to plant morphological features. Automated deep learning-based computer vision algorithms are widely used for identifying plants and can help users narrow down the possibilities. However, numerous morphological similarities between and within species render correct classification difficult. In this paper, we tested custom convolution neural network (CNN) and vision transformer (ViT) based models using the PyTorch framework to classify plants. We used a large dataset of 88,000 provided by the Royal Horticultural Society (RHS) and a smaller dataset of 16,000 images from the PlantClef 2015 dataset for classifying plants at genus and species levels, respectively. Our results show that for classifying plants at the genus level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420 and other state-of-the-art CNN-based models suggested in previous studies on a similar dataset. ViT model achieved top accuracy of 83.3% for classifying plants at the genus level. For classifying plants at the species level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420, with a top accuracy of 92.5%. We show that the correct set of augmentation techniques plays an important role in classification success. In conclusion, these results could help end users, professionals and the general public alike in identifying plants quicker and with improved accuracy.

Keywords: plant identification, CNN, image processing, vision transformer, classification

Procedia PDF Downloads 102

Authors: Keyur Joshi, Philip Dietrich, Tjark Windisch, Markus König

Abstract:

In the field of surveillance-based fire detection, the volume of incoming data is increasing rapidly. However, the labeling of a large industrial dataset is costly due to the high annotation costs associated with current state-of-the-art methods, which often require bounding boxes or segmentation masks for model training. This paper introduces VideoAssist, a video annotation solution that utilizes a video-based foundation model to annotate entire videos with minimal effort, requiring the labeling of bounding boxes for only a few keyframes. To the best of our knowledge, VideoAssist is the first method to significantly reduce the effort required for labeling fire detection videos. The approach offers bounding box and segmentation annotations for the video dataset with minimal manual effort. Results demonstrate that the performance of labels annotated by VideoAssist is comparable to those annotated by humans, indicating the potential applicability of this approach in fire detection scenarios.

Keywords: fire detection, label annotation, foundation models, object detection, segmentation

Procedia PDF Downloads 5

Authors: Arpit Rai

Abstract:

In this work, we propose PatchMix, a semi-supervised method for pre-training visual representations. PatchMix mixes patches of two images and then solves an auxiliary task of predicting the label of each patch in the mixed image. Our experiments on the CIFAR-10, 100 and the SVHN dataset show that the representations learned by this method encodes useful information for transfer to new tasks and outperform the baseline Residual Network encoders by on CIFAR 10 by 12% on ResNet 101 and 2% on ResNet-56, by 4% on CIFAR-100 on ResNet101 and by 6% on SVHN dataset on the ResNet-101 baseline model.

Keywords: self-supervised learning, representation learning, computer vision, generalization

Procedia PDF Downloads 89