Search results for: speech dataset

Authors: Khenfer Koummich Fatma, Hendel Fatiha, Mesbahi Larbi

Abstract:

This paper presents an approach based on Hidden Markov Models (HMM: Hidden Markov Model) using HTK tools. The goal is to create a human-machine interface with a voice recognition system that allows the operator to teleoperate a mentor robot to execute specific tasks as rotate, raise, close, etc. This system should take into account different levels of environmental noise. This approach has been applied to isolated words representing the robot commands pronounced in two languages: French and Arabic. The obtained recognition rate is the same in both speeches, Arabic and French in the neutral words. However, there is a slight difference in favor of the Arabic speech when Gaussian white noise is added with a Signal to Noise Ratio (SNR) equals 30 dB, in this case; the Arabic speech recognition rate is 69%, and the French speech recognition rate is 80%. This can be explained by the ability of phonetic context of each speech when the noise is added.

Keywords: Arabic speech recognition, Hidden Markov Model (HMM), HTK, noise, TIMIT, voice command

Procedia PDF Downloads 347

Authors: Shaima Almalhan, Lubna Shukri, Miriam Talal, Safaa Teskieh

Abstract:

Since artificial intelligence is a rapidly evolving topic that has had a significant impact on technical growth and innovation, this paper examines people's awareness, use, and engagement with the Google Translate application. To see how familiar aware users are with the app and its features, quantitative and qualitative research was conducted. The findings revealed that consumers have a high level of confidence in the application and how far people they benefit from this sort of innovation and how convenient it makes communication.

Keywords: artificial intelligence, google translate, speech recognition, language translation, camera translation, speech to text, text to speech

Procedia PDF Downloads 126

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, convolutional neural network, capsule network, capacity optimization, character recognition, data augmentation, semantic segmentation

Procedia PDF Downloads 125

Authors: Felipe Villegas-Velasquez, Harold Pantoja-Villota, Sergio Holguin-Cardona, Alejandro Osorio-Botero, Brayan Candamil-Arango

Abstract:

Colombian electricity comes mainly from hydric resources, affected by environmental variations such as the El Niño phenomenon. That is why incorporating other types of resources is necessary to provide electricity constantly. This research seeks to fill the wind speed and global solar irradiance dataset for two years with the highest amount of information. A further result is the characterization of the data by region that led to infer which errors occurred and offered the incomplete dataset.

Keywords: energy, wind speed, global solar irradiance, Colombia, imputation

Procedia PDF Downloads 118

Authors: Elena E. Lyakso, Olga V. Frolova, Yuri N. Matveev, Aleksey S. Grigorev, Alexander S. Nikolaev, Viktor A. Gorodnyi

Abstract:

The study of the children’s emotional sphere depending on age and psychoneurological state is of great importance for the design of educational programs for children and their social adaptation. Atypical development may be accompanied by violations or specificities of the emotional sphere. To study characteristics of the emotional state reflection in the voice and speech features of children, the perceptual study with the participation of adults and the automatic recognition of speech were conducted. Speech of children with typical development (TD), with Down syndrome (DS), and with autism spectrum disorders (ASD) aged 6-12 years was recorded. To obtain emotional speech in children, model situations were created, including a dialogue between the child and the experimenter containing questions that can cause various emotional states in the child and playing with a standard set of toys. The questions and toys were selected, taking into account the child’s age, developmental characteristics, and speech skills. For the perceptual experiment by adults, test sequences containing speech material of 30 children: TD, DS, and ASD were created. The listeners were 100 adults (age 19.3 ± 2.3 years). The listeners were tasked with determining the children’s emotional state as “comfort – neutral – discomfort” while listening to the test material. Spectrographic analysis of speech signals was conducted. For automatic recognition of the emotional state, 6594 speech files containing speech material of children were prepared. Automatic recognition of three states, “comfort – neutral – discomfort,” was performed using automatically extracted from the set of acoustic features - the Geneva Minimalistic Acoustic Parameter Set (GeMAPS) and the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS). The results showed that the emotional state is worse determined by the speech of TD children (comfort – 58% of correct answers, discomfort – 56%). Listeners better recognized discomfort in children with ASD and DS (78% of answers) than comfort (70% and 67%, respectively, for children with DS and ASD). The neutral state is better recognized by the speech of children with ASD (67%) than by the speech of children with DS (52%) and TD children (54%). According to the automatic recognition data using the acoustic feature set GeMAPSv01b, the accuracy of automatic recognition of emotional states for children with ASD is 0.687; children with DS – 0.725; TD children – 0.641. When using the acoustic feature set eGeMAPSv01b, the accuracy of automatic recognition of emotional states for children with ASD is 0.671; children with DS – 0.717; TD children – 0.631. The use of different models showed similar results, with better recognition of emotional states by the speech of children with DS than by the speech of children with ASD. The state of comfort is automatically determined better by the speech of TD children (precision – 0.546) and children with ASD (0.523), discomfort – children with DS (0.504). The data on the specificities of recognition by adults of the children’s emotional state by their speech may be used in recruitment for working with children with atypical development. Automatic recognition data can be used to create alternative communication systems and automatic human-computer interfaces for social-emotional learning. Acknowledgment: This work was financially supported by the Russian Science Foundation (project 18-18-00063).

Keywords: autism spectrum disorders, automatic recognition of speech, child’s emotional speech, Down syndrome, perceptual experiment

Procedia PDF Downloads 165

Authors: Indira Kothalanka

Abstract:

For individuals born with a cleft palate (CP), there is no separation between the nasal cavity and the oral cavity, due to which they cannot build up enough air pressure in the mouth for speech. Therefore, it is common for them to have speech problems. Common cleft type speech errors include abnormal articulation (compensatory or obligatory) and abnormal resonance (hyper, hypo and mixed nasality). These are generally resolved after palate repair. However, in some individuals, articulation problems do persist even after the palate repair. Such individuals develop variant articulations in an attempt to compensate for the inability to produce the target phonemes. A spectrographic analysis is used to investigate the compensatory articulatory behaviours of pressure consonants in the speech of 10 Telugu speaking individuals aged between 7-17 years with a history of cleft palate. Telugu is a Dravidian language which is spoken in Andhra Pradesh and Telangana states in India. It is a language with the third largest number of native speakers in India and the most spoken Dravidian language. The speech of the informants is analysed using single word list, sentences, passage and conversation. Spectrographic analysis is carried out using PRAAT, speech analysis software. The place and manner of articulation of consonant sounds is studied through spectrograms with the help of various acoustic cues. The types of compensatory articulation identified are glottal stops, palatal stops, uvular, velar stops and nasal fricatives which are non-native in Telugu.

Keywords: cleft palate, compensatory articulation, spectrographic analysis, PRAAT

Procedia PDF Downloads 422

Authors: P. S. Jagadeesh Kumar, S. Meenakshi Sundaram, Wenli Hu, Yang Yung

Abstract:

In 3D video games, the dominance of production is unceasingly growing with a protruding level of affordability in terms of budget. Afterward, the automation of speech-lip synchronization technique is customarily onerous and has advanced a critical research subject in virtual reality based 3D video games. This paper presents one of these automatic tools, precisely riveted on the synchronization of the speech and the lip movement of the game characters. A robust and precise speech recognition segment that systematized with Algebraic Code Excited Linear Prediction method is developed which unconventionally delivers lip sync results. The Algebraic Code Excited Linear Prediction algorithm is constructed on that used in code-excited linear prediction, but Algebraic Code Excited Linear Prediction codebooks have an explicit algebraic structure levied upon them. This affords a quicker substitute to the software enactments of lip sync algorithms and thus advances the superiority of service factors abridged production cost.

Keywords: algebraic code excited linear prediction, speech-lip synchronization, video games, virtual reality

Procedia PDF Downloads 447

Authors: D. Beziakina, E. Bulgakova

Abstract:

This study continues the research on Tuvinian intonation and presents a general cross-dialect analysis of intonation of Tuvinian declarative utterances, specifically the character of the tone movement in order to test the hypothesis about the prevalence of level tone in some Tuvinian dialects. The results of the analysis of basic pitch characteristics of Tuvinian speech (in general and in comparison with two other Turkic languages - Uzbek and Azerbaijani) are also given in this paper. The goal of our work was to obtain the ranges of pitch parameter values typical for Tuvinian speech. Such language-specific values can be used in speaker identification systems in order to get more accurate results of ethnic speech analysis. We also present the results of a cross-dialect analysis of declarative intonation in the poorly studied Tuvinian language.

Keywords: speech analysis, statistical analysis, speaker recognition, identification of person

Procedia PDF Downloads 444

Authors: Maisa Haj-Tas, Jehad Alaraifi

Abstract:

The significance of the study: This retrospective study examined the speech and language profiles of patients who received clinical services at the University of Jordan Hearing and Speech Clinic (UJ-HSC) from 2009 to 2014. The UJ-HSC clinic is located in the capital Amman and was established in the late 1990s. It is the first hearing and speech clinic in Jordan and one of first speech and hearing clinics in the Middle East. This clinic provides services to an annual average of 2000 patients who are diagnosed with different communication disorders. Examining the speech and language profiles of patients in this clinic could provide an insight about the most common disorders seen in patients who attend similar clinics in Jordan. It could also provide information about community awareness of the role of speech therapists in the management of speech and language disorders. Methodology: The researchers examined the clinical records of 1140 patients (797 males and 343 females) who received clinical services at the UJ-HSC between the years 2009 and 2014 for the purpose of data analysis for this study. The main variables examined in the study were disorder type and gender. Participants were divided into four age groups: children, adolescents, adults, and older adults. The examined disorders were classified as either speech disorders, language disorders, or dysphagia (i.e., swallowing problems). The disorders were further classified as childhood language impairments, articulation disorders, stuttering, cluttering, voice disorders, aphasia, and dysphagia. Results: The results indicated that the prevalence for language disorders was the highest (50.7%) followed by speech disorders (48.3%), and dysphagia (0.9%). The majority of patients who were seen at the JU-HSC were diagnosed with childhood language impairments (47.3%) followed consecutively by articulation disorders (21.1%), stuttering (16.3%), voice disorders (12.1%), aphasia (2.2%), dysphagia (0.9%), and cluttering (0.2%). As for gender, the majority of patients seen at the clinic were males in all disorders except for voice disorders and cluttering. Discussion: The results of the present study indicate that the majority of examined patients were diagnosed with childhood language impairments. Based on this result, the researchers suggest that there seems to be a high prevalence of childhood language impairments among children in Jordan compared to other types of speech and language disorders. The researchers also suggest that there is a need for further examination of the actual prevalence data on speech and language disorders in Jordan. The fact that many of the children seen at the UJ-HSC were brought to the clinic either as a result of parental concern or teacher referral indicates that there seems to an increased awareness among parents and teachers about the services speech pathologists can provide about assessment and treatment of childhood speech and language disorders. The small percentage of other disorders (i.e., stuttering, cluttering, dysphasia, aphasia, and voice disorders) seen at the UJ-HSC may indicate a little awareness by the local community about the role of speech pathologists in the assessment and treatment of these disorders.

Keywords: clinic, disorders, language, profile, speech

Procedia PDF Downloads 293

Authors: Yeliz Karaca, Rana Karabudak

Abstract:

Multifractal Denoising techniques are used in the identification of significant attributes by removing the noise of the dataset. Magnetic resonance (MR) image technique is the most sensitive method so as to identify chronic disorders of the nervous system such as Multiple Sclerosis. MRI and Expanded Disability Status Scale (EDSS) data belonging to 120 individuals who have one of the subgroups of MS (Relapsing Remitting MS (RRMS), Secondary Progressive MS (SPMS), Primary Progressive MS (PPMS)) as well as 19 healthy individuals in the control group have been used in this study. The study is comprised of the following stages: (i) L2 Norm Multifractal Denoising technique, one of the multifractal technique, has been used with the application on the MS data (MRI and EDSS). In this way, the new dataset has been obtained. (ii) The new MS dataset obtained from the MS dataset and L2 Multifractal Denoising technique has been applied to the K-Means and Fuzzy C Means clustering algorithms which are among the unsupervised methods. Thus, the clustering performances have been compared. (iii) In the identification of significant attributes in the MS dataset through the Multifractal denoising (L2 Norm) technique using K-Means and FCM algorithms on the MS subgroups and control group of healthy individuals, excellent performance outcome has been yielded. According to the clustering results based on the MS subgroups obtained in the study, successful clustering results have been obtained in the K-Means and FCM algorithms by applying the L2 norm of multifractal denoising technique for the MS dataset. Clustering performance has been more successful with the MS Dataset (L2_Norm MS Data Set) K-Means and FCM in which significant attributes are obtained by applying L2 Norm Denoising technique.

Keywords: clinical decision support, clustering algorithms, multiple sclerosis, multifractal techniques

Procedia PDF Downloads 141

Authors: Jong Han Joo, Jung Hoon Lee, Young Sun Kim, Jae Young Kang, Seung Ho Choi

Abstract:

In this study, we propose a novel technique for acoustic echo suppression (AES) during speech recognition under barge-in conditions. Conventional AES methods based on spectral subtraction apply fixed weights to the estimated echo path transfer function (EPTF) at the current signal segment and to the EPTF estimated until the previous time interval. We propose a new approach that adaptively updates weight parameters in response to abrupt changes in the acoustic environment due to background noises or double-talk. Furthermore, we devised a voice activity detector and an initial time-delay estimator for barge-in speech recognition in communication networks. The initial time delay is estimated using log-spectral distance measure, as well as cross-correlation coefficients. The experimental results show that the developed techniques can be successfully applied in barge-in speech recognition systems.

Keywords: acoustic echo suppression, barge-in, speech recognition, echo path transfer function, initial delay estimator, voice activity detector

Procedia PDF Downloads 347

Authors: Khadija Rafi, Neha Jamil, Laiba Khalid, Meerub Nawaz, Mahwish Farooq

Abstract:

Speech articulation is a complex process to produce intelligible sounds with the help of precise movements of various structures within the vocal tract. All these structures in the vocal tract are named as articulators, which comprise lips, teeth, tongue, and palate. These articulators work together to produce a range of distinct phonemes, which happen to be the basis of language. It starts with the airstream from the lungs passing through the trachea and into oral and nasal cavities. When the air passes through the mouth, the tongue and the muscles around it form such coordination it creates certain sounds. It can be seen when the tongue is placed in different positions- sometimes near the alveolar ridge, soft palate, roof of the mouth or the back of the teeth which end up creating unique qualities of each phoneme. We can articulate vowels with open vocal tracts, but the height and position of the tongue is different every time depending upon each vowel, while consonants can be pronounced when we create obstructions in the airflow. For instance, the alphabet ‘b’ is a plosive and can be produced only by briefly closing the lips. Articulation disorders can not only affect communication but can also be a hurdle in speech production. To improve articulation skills for such individuals, doctors often recommend speech therapy, which involves various kinds of exercises like jaw exercises and tongue twisters. However, this disorder is more common in children who are going through developmental articulation issues right after birth, but in adults, it can be caused by injury, neurological conditions, or other speech-related disorders. In short, speech articulation is an essential aspect of productive communication, which also includes coordination of the specific articulators to produce different intelligible sounds, which are a vital part of spoken language.

Keywords: linguistics, speech articulation, speech therapy, language learning

Procedia PDF Downloads 37

Authors: Laurel Chikwado Madumere, Kevin O. Ugorji

Abstract:

A speech is said to be full of hate when it appropriates disparaging and vituperative locutions and/or appellations, which are riddled with prejudices and misconceptions about an antagonizing party on the grounds of gender, race, political orientation, religious affiliations, tribe, etc. Due largely to the dichotomies and polarities that exist in Nigeria across political ideological spectrum, tribal affiliations, and gender contradistinctions, there are possibilities for the existence of socioeconomic, religious and political conditions that would induce, provoke and catalyze hate speeches in Nigeria’s mainstream media. Therefore the aim of this paper is to investigate, using select daily newspapers in Nigeria, the extent and complexity of those likely hate speeches that emanate from the pluralism in Nigeria and to set in to relief, the discrepancies and contrariety in the interpretation of those hate words. To achieve the above, the paper shall be qualitative in orientation as it shall be using the Speech Act Theory of J. L. Austin and J. R. Searle to interpret and evaluate the hate speeches in the select Nigerian daily newspapers. Also this paper shall help to elucidate the conditions that generate hate, and inform the government and NGOs how best to approach those conditions and put an end to the possible violence and extremism that emanate from extreme cases of hate.

Keywords: extremism, gender, hate speech, pluralism, prejudice, speech act theory

Procedia PDF Downloads 124

Authors: Partha Protim Majumder, Sajeeb Das, Sharun Akter Khushbu

Abstract:

Bengali is widely spoken in the world, but Bengali speech recognition has not received much attention. Here, we are conducting the toughest task because it must be performed in a noisy place in our study. Another challenge we overcome is dealing with speeches and collecting data on third genders, and our approach is to recognize the gender in speeches. All of the Bangla speech samples used in this study were short and were taken from real-life situations. We employed the male, female, and third-gender categories of speech. In this study, we derive the feature from the spoken word. We used MFCC(1-20), ZCR,rolloff,spec_cen, RMSE, and chroma_stft. Here, we used the algorithms Gboost, Random Forest, K-Nearest Neighbors (KNN), Decision Tree, Naive Bayes, and Logistic Regression (LR) to assess the performance of recognition metrics, and we got the highest performance from random forest in recognizing the gender of the speeches.

Keywords: MFCC, ZCR, Bengali, LR, RMSE, roll-off, Gboost

Procedia PDF Downloads 38

Authors: Takayuki Konishi, Kakeru Yazawa, Mariko Kondo

Abstract:

This study examines developmental change in the production of epenthetic vowels by Japanese learners of English in relation to acquisition of L2 English speech rhythm. Seventy-two Japanese learners of English in the J-AESOP corpus were divided into lower- and higher-level learners according to their proficiency score and the frequency of vowel epenthesis. Three learners were excluded because no vowel epenthesis was observed in their utterances. The analysis of their read English speech data showed no statistical difference between lower- and higher-level learners, implying the absence of any developmental change in durations of epenthetic vowels. This result, together with the findings of previous studies, will be discussed in relation to the transfer of L1 phonology and manifestation of L2 English rhythm.

Keywords: vowel epenthesis, Japanese learners of English, L2 speech corpus, speech rhythm

Procedia PDF Downloads 246

Authors: Marie Alaghband, Niloofar Yousefi, Ivan Garibay

Abstract:

Facial expressions are important parts of both gesture and sign language recognition systems. Despite the recent advances in both fields, annotated facial expression datasets in the context of sign language are still scarce resources. In this manuscript, we introduce an annotated sequenced facial expression dataset in the context of sign language, comprising over 3000 facial images extracted from the daily news and weather forecast of the public tv-station PHOENIX. Unlike the majority of currently existing facial expression datasets, FePh provides sequenced semi-blurry facial images with different head poses, orientations, and movements. In addition, in the majority of images, identities are mouthing the words, which makes the data more challenging. To annotate this dataset we consider primary, secondary, and tertiary dyads of seven basic emotions of "sad", "surprise", "fear", "angry", "neutral", "disgust", and "happy". We also considered the "None" class if the image’s facial expression could not be described by any of the aforementioned emotions. Although we provide FePh as a facial expression dataset of signers in sign language, it has a wider application in gesture recognition and Human Computer Interaction (HCI) systems.

Keywords: annotated facial expression dataset, gesture recognition, sequenced facial expression dataset, sign language recognition

Procedia PDF Downloads 133

Authors: Nadya Inda Syartanti

Abstract:

This research aims to identify, classify, and analyze descriptively the aspects of grammatical and lexical cohesion in the speech text of Japan’s Prime Minister Shinzo Abe entitled Nihon wa Modotte kimashita delivered in Washington DC, the United States on February 23, 2013, as a research data source. The method used is qualitative research, which uses descriptions through words that are applied by analyzing aspects of grammatical and lexical cohesion proposed by Halliday and Hasan (1976). The aspects of grammatical cohesion consist of references (personal, demonstrative, interrogative pronouns), substitution, ellipsis, and conjunction. In contrast, lexical cohesion consists of reiteration (repetition, synonym, antonym, hyponym, meronym) and collocation. Data classification is based on the 6 aspects of the cohesion. Through some aspects of cohesion, this research tries to find out the frequency of using grammatical and lexical cohesion in Shinzo Abe's speech text entitled Nihon wa Modotte kimashita. The results of this research are expected to help overcome the difficulty of understanding speech texts in Japanese. Therefore, this research can be a reference for learners, researchers, and anyone who is interested in the field of discourse analysis.

Keywords: cohesion, grammatical cohesion, lexical cohesion, speech text, Shinzo Abe

Procedia PDF Downloads 135

Authors: K. Rhea Devaiah, B. S. Premalatha

Abstract:

Background: Tonsillar Lingual sulcus is the area between the tonsils and the base of the tongue. The surgical resection of the lesions in the head and neck results in changes in speech and swallowing functions. The severity of the speech and swallowing problem depends upon the site and extent of the lesion, types and extent of surgery and also the flexibility of the remaining structures. Need of the study: This paper focuses on the importance of speech and swallowing rehabilitation in an individual with the lesion in the Tonsillar Lingual Sulcus and post-operative functions. Aim: Evaluating the speech and swallow functions post-intensive speech and swallowing rehabilitation. The objectives are to evaluate the speech intelligibility and swallowing functions after intensive therapy and assess the quality of life. Method: The present study describes a report of an individual aged 47years male, with the diagnosis of basaloid squamous cell carcinoma, left tonsillar lingual sulcus (pT2n2M0) and underwent wide local excision with left radical neck dissection with PMMC flap reconstruction. Post-surgery the patient came with a complaint of reduced speech intelligibility, and difficulty in opening the mouth and swallowing. Detailed evaluation of the speech and swallowing functions were carried out such as OPME, articulation test, speech intelligibility, different phases of swallowing and trismus evaluation. Self-reported questionnaires such as SHI-E(Speech handicap Index- Indian English), DHI (Dysphagia handicap Index) and SESEQ -K (Self Evaluation of Swallowing Efficiency in Kannada) were also administered to know what the patient feels about his problem. Based on the evaluation, the patient was diagnosed with pharyngeal phase dysphagia associated with trismus and reduced speech intelligibility. Intensive speech and swallowing therapy was advised weekly twice for the duration of 1 hour. Results: Totally the patient attended 10 intensive speech and swallowing therapy sessions. Results indicated misarticulation of speech sounds such as lingua-palatal sounds. Mouth opening was restricted to one finger width with difficulty chewing, masticating, and swallowing the bolus. Intervention strategies included Oro motor exercise, Indirect swallowing therapy, usage of a trismus device to facilitate mouth opening, and change in the food consistency to help to swallow. A practice session was held with articulation drills to improve the production of speech sounds and also improve speech intelligibility. Significant changes in articulatory production and speech intelligibility and swallowing abilities were observed. The self-rated quality of life measures such as DHI, SHI and SESE Q-K revealed no speech handicap and near-normal swallowing ability indicating the improved QOL after the intensive speech and swallowing therapy. Conclusion: Speech and swallowing therapy post carcinoma in the tonsillar lingual sulcus is crucial as the tongue plays an important role in both speech and swallowing. The role of Speech-language and swallowing therapists in oral cancer should be highlighted in treating these patients and improving the overall quality of life. With intensive speech-language and swallowing therapy post-surgery for oral cancer, there can be a significant change in the speech outcome and swallowing functions depending on the site and extent of lesions which will thereby improve the individual’s QOL.

Keywords: oral cancer, speech and swallowing therapy, speech intelligibility, trismus, quality of life

Procedia PDF Downloads 83

Authors: Kseniia Fedorova

Abstract:

The article is devoted to interlinguistic homonymy and enantiosemy analysis. These phenomena belong to the process of linguistic interference, which leads to violation of the communicative utterances integrity and causes misunderstanding between foreign interlocutors - native speakers of different Slavic languages. More attention is paid to investigation of non-typical speech situations, which occurred spontaneously or created by somebody intentionally being based on described phenomenon mechanism. The classification of typical students' mistakes connected with the paradox of interference is being represented in the article. The survey contributes to speech act theory, contemporary linguodidactics, translation science and comparative lexicology of Slavonic languages.

Keywords: adherent enantiosemy, interference, interslavonic homonymy, speech act

Procedia PDF Downloads 218

Authors: Bubai Maji, Monorama Swain

Abstract:

Speech is considered an essential and most natural medium for the interaction between machines and humans. However, extracting effective features for speech emotion recognition (SER) is remains challenging. The present studies show that the temporal information captured but high-level temporal-feature learning is yet to be investigated. In this paper, we present an efficient novel method using the Self-attention (SA) mechanism in a combination of Convolutional Neural Network (CNN) and Bi-directional Gated Recurrent Unit (Bi-GRU) network to learn high-level temporal-feature. In order to further enhance the representation of the high-level temporal-feature, we integrate a Bi-GRU output with learnable weights features by SA, and improve the performance. We evaluate our proposed method on our created SITB-OSED and IEMOCAP databases. We report that the experimental results of our proposed method achieve state-of-the-art performance on both databases.

Keywords: Bi-GRU, 1D-CNNs, self-attention, speech emotion recognition

Procedia PDF Downloads 93

Authors: Anup Anand Deshmukh, Catherine Soladie, Renaud Seguier

Abstract:

Emotion plays a key role in many applications like healthcare, to gather patients’ emotional behavior. Unlike typical ASR (Automated Speech Recognition) problems which focus on 'what was said', it is equally important to understand 'how it was said.' There are certain emotions which are given more importance due to their effectiveness in understanding human feelings. In this paper, we propose an approach that models human stress from audio signals. The research challenge in speech emotion detection is finding the appropriate set of acoustic features corresponding to an emotion. Another difficulty lies in defining the very meaning of emotion and being able to categorize it in a precise manner. Supervised Machine Learning models, including state of the art Deep Learning classification methods, rely on the availability of clean and labelled data. One of the problems in affective computation is the limited amount of annotated data. The existing labelled emotions datasets are highly subjective to the perception of the annotator. We address the first issue of feature selection by exploiting the use of traditional MFCC (Mel-Frequency Cepstral Coefficients) features in Convolutional Neural Network. Our proposed Emo-CNN (Emotion-CNN) architecture treats speech representations in a manner similar to how CNN’s treat images in a vision problem. Our experiments show that Emo-CNN consistently and significantly outperforms the popular existing methods over multiple datasets. It achieves 90.2% categorical accuracy on the Emo-DB dataset. We claim that Emo-CNN is robust to speaker variations and environmental distortions. The proposed approach achieves 85.5% speaker-dependant categorical accuracy for SAVEE (Surrey Audio-Visual Expressed Emotion) dataset, beating the existing CNN based approach by 10.2%. To tackle the second problem of subjectivity in stress labels, we use Lovheim’s cube, which is a 3-dimensional projection of emotions. Monoamine neurotransmitters are a type of chemical messengers in the brain that transmits signals on perceiving emotions. The cube aims at explaining the relationship between these neurotransmitters and the positions of emotions in 3D space. The learnt emotion representations from the Emo-CNN are mapped to the cube using three component PCA (Principal Component Analysis) which is then used to model human stress. This proposed approach not only circumvents the need for labelled stress data but also complies with the psychological theory of emotions given by Lovheim’s cube. We believe that this work is the first step towards creating a connection between Artificial Intelligence and the chemistry of human emotions.

Keywords: deep learning, brain chemistry, emotion perception, Lovheim's cube

Procedia PDF Downloads 126

Authors: Armita Ghobadi, Samantha Emerson, Seyda Ozcaliskan

Abstract:

Being a bilingual involves mastery of both speech and gesture patterns in a second language (L2). We know from earlier work in first language (L1) production contexts that speech and co-speech gesture form a tightly integrated system: co-speech gesture mirrors the patterns observed in speech, suggesting an online effect of language on nonverbal representation of events in gesture during the act of speaking (i.e., “thinking for speaking”). Relatively less is known about the online effect of language on gesture in bilinguals speaking structurally different languages. The few existing studies—mostly with small sample sizes—suggests inconclusive findings: some show greater achievement of L2 patterns in gesture with more advanced L2 speech production, while others show preferences for L1 gesture patterns even in advanced bilinguals. In this study, we focus on advanced bilingual speakers of two structurally different languages (Spanish L1 with English L2) in comparison to L1 English speakers. We ask whether bilingual speakers will follow target L2 patterns not only in speech but also in gesture, or alternatively, follow L2 patterns in speech but resort to L1 patterns in gesture. We examined this question by studying speech and gestures produced by 23 advanced adult Spanish (L1)-English (L2) bilinguals (Mage=22; SD=7) and 23 monolingual English speakers (Mage=20; SD=2). Participants were shown 16 animated motion event scenes that included distinct manner and path components (e.g., "run over the bridge"). We recorded and transcribed all participant responses for speech and segmented it into sentence units that included at least one motion verb and its associated arguments. We also coded all gestures that accompanied each sentence unit. We focused on motion event descriptions as it shows strong crosslinguistic differences in the packaging of motion elements in speech and co-speech gesture in first language production contexts. English speakers synthesize manner and path into a single clause or gesture (he runs over the bridge; running fingers forward), while Spanish speakers express each component separately (manner-only: el corre=he is running; circle arms next to body conveying running; path-only: el cruza el puente=he crosses the bridge; trace finger forward conveying trajectory). We tallied all responses by group and packaging type, separately for speech and co-speech gesture. Our preliminary results (n=4/group) showed that productions in English L1 and Spanish L1 differed, with greater preference for conflated packaging in L1 English and separated packaging in L1 Spanish—a pattern that was also largely evident in co-speech gesture. Bilinguals’ production in L2 English, however, followed the patterns of the target language in speech—with greater preference for conflated packaging—but not in gesture. Bilinguals used separated and conflated strategies in gesture in roughly similar rates in their L2 English, showing an effect of both L1 and L2 on co-speech gesture. Our results suggest that online production of L2 language has more limited effects on L2 gestures and that mastery of native-like patterns in L2 gesture might take longer than native-like L2 speech patterns.

Keywords: bilingualism, cross-linguistic variation, gesture, second language acquisition, thinking for speaking hypothesis

Procedia PDF Downloads 49

Authors: Hussain Hameed Mayuuf

Abstract:

The study is an attempt to investigate the conceptual metonymies is used in political discourse about COVID-19. Thus, this study tries to analyze and investigate how the conceptual metonymies in Johnson's speech about coronavirus are constructed. This study aims at: Identifying how are metonymies relevant to understand the messages in Boris Johnson speeches and to find out how can conceptual blending theory help people to understand the messages in the political speech about COVID-19. Lastly, it tries to Point out the kinds of integration networks are common in political speech. The study is based on the hypotheses that conceptual blending theory is a powerful tool for investigating the intended messages in Johnson's speech and there are different processes of blending networks and conceptual mapping that enable the listeners to identify the messages in political speech. This study presents a qualitative and quantitative analysis of four speeches about COVID-19; they are said by Boris Johnson. The selected data have been tackled from the cognitive-semantic perspective by adopting Conceptual Blending Theory as a model for the analysis. It concludes that CBT is applicable to the analysis of metonymies in political discourse. Its mechanisms enable listeners to analyze and understand these speeches. Also the listener can identify and understand the hidden messages in Biden and Johnson's discourse about COVID-19 by using different conceptual networks. Finally, it is concluded that the double scope networks are the most common types of blending of metonymies in the political speech.

Keywords: cognitive, semantics, conceptual, metonymical, Covid-19

Procedia PDF Downloads 88

Authors: Xulu Yao, Moi Hoon Yap, Yanlong Zhang

Abstract:

As a branch of artificial neural network, deep learning is widely used in the field of image recognition, but the lack of its dataset leads to imperfect model learning. By analysing the data scale requirements of deep learning and aiming at the application in GUI generation, it is found that the collection of GUI dataset is a time-consuming and labor-consuming project, which is difficult to meet the needs of current deep learning network. To solve this problem, this paper proposes a semi-supervised deep learning model that relies on the original small-scale datasets to produce a large number of reliable data sets. By combining the cyclic neural network with the generated countermeasure network, the cyclic neural network can learn the sequence relationship and characteristics of data, make the generated countermeasure network generate reasonable data, and then expand the Rico dataset. Relying on the network structure, the characteristics of collected data can be well analysed, and a large number of reasonable data can be generated according to these characteristics. After data processing, a reliable dataset for model training can be formed, which alleviates the problem of dataset shortage in deep learning.

Keywords: GUI, deep learning, GAN, data augmentation

Procedia PDF Downloads 154

Authors: G. Tamulevičius, A. Serackis, T. Sledevič, D. Navakauskas

Abstract:

We consider the biggest challenge in speech recognition – noise reduction. Traditionally detected transient noise pulses are removed with the corrupted speech using pulse models. In this paper we propose to cope with the problem directly in Dynamic Time Warping domain. Bidirectional Dynamic Time Warping algorithm for the recognition of isolated words impacted by transient noise pulses is proposed. It uses simple transient noise pulse detector, employs bidirectional computation of dynamic time warping and directly manipulates with warping results. Experimental investigation with several alternative solutions confirms effectiveness of the proposed algorithm in the reduction of impact of noise on recognition process – 3.9% increase of the noisy speech recognition is achieved.

Keywords: transient noise pulses, noise reduction, dynamic time warping, speech recognition

Procedia PDF Downloads 530

Authors: Brahim-Fares Zaidi, Malika Boudraa, Sid-Ahmed Selouani

Abstract:

Our work aims to improve our Automatic Recognition System for Dysarthria Speech (ARSDS) based on the Hidden Models of Markov (HMM) and the Hidden Markov Model Toolkit (HTK) to help people who are sick. With pronunciation problems, we applied two techniques of speech parameterization based on Mel Frequency Cepstral Coefficients (MFCC's) and Perceptual Linear Prediction (PLP's) and concatenated them with JITTER and SHIMMER coefficients in order to increase the recognition rate of a dysarthria speech. For our tests, we used the NEMOURS database that represents speakers with dysarthria and normal speakers.

Keywords: hidden Markov model toolkit (HTK), hidden models of Markov (HMM), Mel-frequency cepstral coefficients (MFCC), perceptual linear prediction (PLP’s)

Procedia PDF Downloads 135

Authors: Bingquan Shen

Abstract:

Convolutional Neural Networks (CNN) have demonstrated their effectiveness in synthesizing 3D views of object instances at various viewpoints. Given the problem where one have limited viewpoints of a particular object for classification, we present a pose normalization architecture to transform the object to existing viewpoints in the training dataset before classification to yield better classification performance. We have demonstrated that this Pose Normalization Network (PNN) can capture the style of the target object and is able to re-render it to a desired viewpoint. Moreover, we have shown that the PNN improves the classification result for the 3D chairs dataset and ShapeNet airplanes dataset when given only images at limited viewpoint, as compared to a CNN baseline.

Keywords: convolutional neural networks, object classification, pose normalization, viewpoint invariant

Procedia PDF Downloads 311

Authors: Wei Chen Chang, Ming Yu Hsiao

Abstract:

The commodity takes one kind of mark, the designer how to construction and interpretation the user how to use the process and effectively convey message in design education has always been an important issue. Cultural-creative design refers to signifying cultural heritage for product design. In terms of Peirce’s Semiotic Triangle: signifying elements-object-interpretant, signifying elements are the outcomes of design, the object is cultural heritage, and the interpretant is the positioning and description of product design. How to elaborate the positioning, design, and development of a product is a narrative issue of the interpretant, and how to shape the signifying elements of a product by modifying and adapting styles is a rhetoric matter. This study investigated the rhetoric of elements signifying products to develop a rhetoric model with cultural style. Figures of speech are a rhetoric method in narrative. By adapting figures of speech to the interpretant, this study developed the rhetoric context of cultural context by narrative means. In this two-phase study, phase I defines figures of speech and phase II analyzes existing cultural-creative products in terms of figures of speech to develop a rhetoric of style model. We expect it can reference for the future development of Cultural-creative design.

Keywords: cultural-creative design, cultural-creative products, figures of speech, Peirce’s semiotic triangle, rhetoric of style model

Procedia PDF Downloads 348

Authors: Ali Dulla

Abstract:

This paper introduces a new dataset (and the methodology used to generate it) based on a wide range of historical Arabic documents containing clean data simple and homogeneous-page layouts. The experiments are implemented on printed and handwritten documents obtained respectively from some important libraries such as Qatar Digital Library, the British Library and the Library of Congress. We have gathered and commented on 150 archival document images from different locations and time periods. It is based on different documents from the 17th-19th century. The dataset comprises differing page layouts and degradations that challenge text line segmentation methods. Ground truth is produced using the Aletheia tool by PRImA and stored in an XML representation, in the PAGE (Page Analysis and Ground truth Elements) format. The dataset presented will be easily available to researchers world-wide for research into the obstacles facing various historical Arabic documents such as geometric correction of historical Arabic documents.

Keywords: dataset production, ground truth production, historical documents, arbitrary warping, geometric correction

Procedia PDF Downloads 148

Authors: Deawan Rakin Ahamed Remal, Sinthia Chowdhury, Sharun Akter Khushbu, Sheak Rashed Haider Noori

Abstract:

Native Speech to text synthesis has its own leverage for the purpose of mankind. The extensive nature of art to speaking different accents is common but the purpose of communication between two different accent types of people is quite difficult. This problem will be motivated by the extraction of the wrong perception of language meaning. Thus, many existing automatic speech recognition has been placed to detect text. Overall study of this paper mentions a review of NSTTR (Native Speech Text to Text Recognition) synthesis compared with Text to Text recognition. Review has exposed many text to text recognition systems that are at a very early stage to comply with the system by native speech recognition. Many discussions started about the progression of chatbots, linguistic theory another is rule based approach. In the Recent years Deep learning is an overwhelming chapter for text to text learning to detect language nature. To the best of our knowledge, In the sub continent a huge number of people speak in Bangla language but they have different accents in different regions therefore study has been elaborate contradictory discussion achievement of existing works and findings of future needs in Bangla language acoustic accent.

Keywords: TTR, NSTTR, text to text recognition, deep learning, natural language processing

Procedia PDF Downloads 105