Search results for: cetaceans and human speech

Authors: Ericson O. Alieto, Aprillete C. Devanadera

Abstract:

The main objective of the study is to determine the dominant speech acts in five commemorative speeches of President Duterte. This study employed Speech Act Theory and Discourse analysis to determine how the speech acts features connote the pragmatic meaning of Duterte’s speeches. Identifying the speech acts is significant in elucidating the underlying message or the pragmatic meaning of the speeches. From the 713 sentences or utterances from the speeches, assertive with 208 occurrences from the corpus or 29% is the dominant speech acts. It was followed by expressive with 177 or 25% occurrences, directive accounts for 152 or 15% occurrences. While commisive accounts for 104 or 15% occurrences and declarative got the lowest percentage of occurrences with 72 or 10% only. These sentences when uttered by Duterte carry a certain power of language to move or influence people. Thus, the present study shows the fundamental message perceived by the listeners. Moreover, the frequent use of assertive and expressive not only explains the pragmatic message of the speeches but also reflects the personality of President Duterte.

Keywords: commemorative speech, discourse analysis, duterte, pragmatics

Procedia PDF Downloads 265

Authors: M. Kiran Reddy, K. Sreenivasa Rao

Abstract:

The conventional Hidden Markov Model (HMM)-based speech synthesis system (HTS) uses only a pulse excitation model, which significantly differs from natural excitation signal. Hence, buzziness can be perceived in the speech generated using HTS. This paper proposes an efficient excitation modeling method that can significantly reduce the buzziness, and improve the quality of HMM-based speech synthesis. The proposed approach models the pitch-synchronous residual frames extracted from the residual excitation signal. Each pitch synchronous residual frame is parameterized using 30 wavelet coefficients. These 30 wavelet coefficients are found to accurately capture the perceptually important information present in the residual waveform. In synthesis phase, the residual frames are reconstructed from the generated wavelet coefficients and are pitch-synchronously overlap-added to generate the excitation signal. The proposed excitation modeling method is integrated into HMM-based speech synthesis system. Evaluation results indicate that the speech synthesized by the proposed excitation model is significantly better than the speech generated using state-of-the-art excitation modeling methods.

Keywords: excitation modeling, hidden Markov models, pitch-synchronous frames, speech synthesis, wavelet coefficients

Procedia PDF Downloads 229

Authors: Tadesse Anberbir, Bankole Felix, Tomio Takara

Abstract:

In the development of a text-to-speech synthesizer, automatic derivation of correct pronunciation from the grapheme form of a text is a central problem. Particularly deriving phonological features which are not shown in orthography is challenging. In the Amharic language, geminates and epenthetic vowels are very crucial for proper pronunciation, but neither is shown in orthography. In this paper, to proposed and integrated a morphological analyzer into an Amharic Text-to-Speech system, mainly to predict geminates and epenthetic vowel positions and prepared a duration modeling method. Amharic Text-to-Speech system (AmhTTS) is a parametric and rule-based system that adopts a cepstral method and uses a source filter model for speech production and a Log Magnitude Approximation (LMA) filter as the vocal tract filter. The naturalness of the system after employing the duration modeling was evaluated by sentence listening test, and we achieved an average Mean Opinion Score (MOS) 3.4 (68%), which is moderate. By modeling the duration of geminates and controlling the locations of epenthetic vowel, we are able to synthesize good quality speech. Our system is mainly suitable to be customized for other Ethiopian languages with limited resources.

Keywords: amharic, gemination, Speech synthesis, morphology, epenthesis

Procedia PDF Downloads 61

Authors: Dzhavidan Zeinalov, Bugra Sen, Firangiz Aslanova

Abstract:

Most text-to-speech models cannot operate well in low-resource languages and require a great amount of high-quality training data to be considered good enough. Yet, with the improvements made in ASR systems, it is now much easier than ever to collect data for the design of custom text-to-speech models. In this work, our work on using the ASR model to collect data to build a viable text-to-speech system for one of the leading financial institutions of Azerbaijan will be outlined. NVIDIA’s implementation of the Tacotron 2 model was utilized along with the HiFiGAN vocoder. As for the training, the model was first trained with high-quality audio data collected from the Internet, then fine-tuned on the bank’s single speaker call center data. The results were then evaluated by 50 different listeners and got a mean opinion score of 4.17, displaying that our method is indeed viable. With this, we have successfully designed the first text-to-speech model in Azerbaijani and publicly shared 12 hours of audiobook data for everyone to use.

Keywords: Azerbaijani language, HiFiGAN, Tacotron 2, text-to-speech, transfer learning, whisper

Procedia PDF Downloads 17

Authors: Edemealem Desalegn Kingawa, Kafte Tasew Timkete, Mekashaw Girmaw Abebe, Terefe Feyisa, Abiyot Bitew Mihretie, Senait Teklemarkos Haile

Abstract:

Currently, hate speech is a growing challenge for society, individuals, policymakers, and researchers, as social media platforms make it easy to anonymously create and grow online friends and followers and provide an online forum for debate about specific issues of community life, culture, politics, and others. Despite this, research on identifying and detecting hate speech is not satisfactory performance, and this is why future research on this issue is constantly called for. This paper provides a systematic review of the literature in this field, with a focus on approaches like word embedding techniques, machine learning, deep learning technologies, hate speech terminology, and other state-of-the-art technologies with challenges. In this paper, we have made a systematic review of the last six years of literature from Research Gate and Google Scholar. Furthermore, limitations, along with algorithm selection and use challenges, data collection, and cleaning challenges, and future research directions, are discussed in detail.

Keywords: Amharic hate speech, deep learning approach, hate speech detection review, Afaan Oromo hate speech detection

Procedia PDF Downloads 149

Authors: Tadesse Anberbir, Felix Bankole, Tomio Takara, Girma Mamo

Abstract:

In the development of a text-to-speech synthesizer, automatic derivation of correct pronunciation from the grapheme form of a text is a central problem. Particularly deriving phonological features which are not shown in orthography is challenging. In the Amharic language, geminates and epenthetic vowels are very crucial for proper pronunciation but neither is shown in orthography. In this paper, we proposed and integrated a morphological analyzer into an Amharic Text-to-Speech system, mainly to predict geminates and epenthetic vowel positions, and prepared a duration modeling method. Amharic Text-to-Speech system (AmhTTS) is a parametric and rule-based system that adopts a cepstral method and uses a source filter model for speech production and a Log Magnitude Approximation (LMA) filter as the vocal tract filter. The naturalness of the system after employing the duration modeling was evaluated by sentence listening test and we achieved an average Mean Opinion Score (MOS) 3.4 (68%) which is moderate. By modeling the duration of geminates and controlling the locations of epenthetic vowel, we are able to synthesize good quality speech. Our system is mainly suitable to be customized for other Ethiopian languages with limited resources.

Keywords: Amharic, gemination, speech synthesis, morphology, epenthesis

Procedia PDF Downloads 57

Authors: Sadiq Aminu, Ahmed Lamido

Abstract:

This research studies Barack Obama’s second inaugural speech using Halliday’s Systemic Functional Grammar (SFG). SFG is a text grammar which describes how language is used, so that the meaning of the text can be better understood. The primary source of data in this research work is Barack Obama’s second inaugural speech which was obtained from the internet. The analysis of the speech was based on the ideational and textual metafunctions of Systemic Functional Grammar. Specifically, the researcher analyses the Process Types and Participants (ideational) and the Theme/Rheme (textual). It was found that material process (process of doing) was the most frequently used ‘Process type’ and ‘We’ which refers to the people of America was the frequently used ‘Theme’. Application of the SFG theory, therefore, gives a better meaning to Barack Obama’s speech.

Keywords: ideational, metafunction, rheme, textual, theme

Procedia PDF Downloads 132

Authors: John Lorenzo Bautista, Yoon-Joong Kim

Abstract:

This paper presents the development of a Filipino speech recognition tool using the HTK System. The system was trained from a subset of the Filipino Speech Corpus developed by the DSP Laboratory of the University of the Philippines-Diliman. The speech corpus was both used in training and testing the system by estimating the parameters for phonetic HMM-based (Hidden-Markov Model) acoustic models. Experiments on different mixture-weights were incorporated in the study. The phoneme-level word-based recognition of a 5-state HMM resulted in an average accuracy rate of 80.13 for a single-Gaussian mixture model, 81.13 after implementing a phoneme-alignment, and 87.19 for the increased Gaussian-mixture weight model. The highest accuracy rate of 88.70% was obtained from a 5-state model with 6 Gaussian mixtures.

Keywords: Filipino language, Hidden Markov Model, HTK system, speech recognition

Procedia PDF Downloads 453

Authors: Chunying Fang, Haifeng Li, Lin Ma, Mancai Zhang

Abstract:

Speech intelligibility assessment is an important measure to evaluate the functional outcomes of surgical and non-surgical treatment, speech therapy and rehabilitation. The assessment of pathological speech plays an important role in assisting the experts. Pathological speech usually is non-stationary and mutational, in this paper, we describe a multi-granularity combined feature schemes, and which is optimized by hierarchical visual method. First of all, the difference granularity level pathological features are extracted which are BAFS (Basic acoustics feature set), local spectral characteristics MSCC (Mel s-transform cepstrum coefficients) and nonlinear dynamic characteristics based on chaotic analysis. Latterly, radar chart and F-score are proposed to optimize the features by the hierarchical visual fusion. The feature set could be optimized from 526 to 96-dimensions.The experimental results denote that new features by support vector machine (SVM) has the best performance, with a recognition rate of 84.4% on NKI-CCRT corpus. The proposed method is thus approved to be effective and reliable for pathological speech intelligibility evaluation.

Keywords: pathological speech, multi-granularity feature, MSCC (Mel s-transform cepstrum coefficients), F-score, radar chart

Procedia PDF Downloads 262

Authors: Rahul Mohite, Lahcen Ouarbya

Abstract:

This paper focuses on the interplay between humans and computer systems and the ability of these systems to understand and respond to human emotions, including non-verbal communication. Current emotion recognition systems are based solely on either facial or verbal expressions. The limitation of these systems is that it requires large training data sets. The paper proposes a system for recognizing human emotions that combines both speech and emotion recognition. The system utilizes advanced techniques such as deep learning and image recognition to identify facial expressions and comprehend emotions. The results show that the proposed system, based on the combination of facial expression and speech, outperforms existing ones, which are based solely either on facial or verbal expressions. The proposed system detects human emotion with an accuracy of 86%, whereas the existing systems have an accuracy of 70% using verbal expression only and 76% using facial expression only. In this paper, the increasing significance and demand for facial recognition technology in emotion recognition are also discussed.

Keywords: facial reputation, expression reputation, deep gaining knowledge of, photo reputation, facial technology, sign processing, photo type

Procedia PDF Downloads 94

Authors: Ya-Hui Wang

Abstract:

Lower speech therapy rate of tracheostomized patient was noted in comparison with previous researches. This study is aim to shed light on the referral status of speech therapy in those patients in Taiwan. This study developed an analysis for the size and key characteristics of the population of tracheostomized in-patient in the Taiwan. Method: We analyzed National Healthcare Insurance data (The Collaboration Center of Health Information Application, CCHIA) from Jan 1 2010 to Dec 31 2010. Result: over ages 3, number of tracheostomized in-patient is directly proportional to age. A high service loading was observed in North region in comparison with other regions. Only 4.87% of the tracheostomized in-patients were referred for speech therapy, and 1.9% for swallow examination, 2.5% for communication evaluation.

Keywords: refer, speech therapy, training, rehabilitation

Procedia PDF Downloads 421

Authors: S. B. Rathna Kumar, Sale Kranthi, Sandya K. Varudhini

Abstract:

The precise perception of spoken language is influenced by several variables, including the listeners’ native language, distance between speaker and listener, reverberation and background noise. When noise is present in an acoustic environment, it masks the speech signal resulting in reduction in the redundancy of the acoustic and linguistic cues of speech. There is strong evidence that bilinguals face difficulty in speech perception for their second language compared with monolingual speakers under adverse listening conditions such as presence of background noise. This difficulty persists even for speakers who are highly proficient in their second language and is greater in those who have learned the second language later in life. The present study aimed to assess the performance of monolingual (Telugu speaking) and bilingual (Tamil as first language and Telugu as second language) speakers on Telugu speech perception task under quiet and noisy environments. The results indicated that both the groups performed similar in both quiet and noisy environments. The findings of the present study are not in accordance with the findings of previous studies which strongly report poorer speech perception in adverse listening conditions such as noise with bilingual speakers for their second language compared with monolinguals.

Keywords: monolingual, bilingual, second language, speech perception, quiet, noise

Procedia PDF Downloads 371

Authors: Fathi Kallel, Ahmed Ben Hamida, Christian Berger-Vachon

Abstract:

In this paper, a Speech Enhancement Algorithm based on Multi-Band Spectral Subtraction (MBSS) principle is evaluated for Bilateral Cochlear Implant (BCI) users. Specifically, dual-channel noise power spectral estimation algorithm using Power Spectral Densities (PSD) and Cross Power Spectral Densities (CPSD) of the observed signals is studied. The enhanced speech signal is obtained using Dual-Channel Multi-Band Spectral Subtraction ‘DC-MBSS’ algorithm. For performance evaluation, objective speech assessment test relying on Perceptual Evaluation of Speech Quality (PESQ) score is performed to fix the optimal number of frequency bands needed in DC-MBSS algorithm. In order to evaluate the speech intelligibility, subjective listening tests are assessed with 3 deafened BCI patients. Experimental results obtained using French Lafon database corrupted by an additive babble noise at different Signal-to-Noise Ratios (SNR) showed that DC-MBSS algorithm improves speech understanding for single and multiple interfering noise sources.

Keywords: speech enhancement, spectral substracion, noise estimation, cochlear impalnt

Procedia PDF Downloads 525

Authors: Brahim Fares Zaidi

Abstract:

Our work aims to improve our Automatic Recognition System for Dysarthria Speech based on the Hidden Models of Markov and the Hidden Markov Model Toolkit to help people who are sick. With pronunciation problems, we applied two techniques of speech parameterization based on Mel Frequency Cepstral Coefficients and Perceptual Linear Prediction 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: ARSDS, HTK, HMM, MFCC, PLP

Procedia PDF Downloads 83

Authors: Tomasz Sapiński, Dorota Kamińska, Adam Pelikant, Egils Avots, Cagri Ozcinar, Gholamreza Anbarjafari

Abstract:

People express emotions through different modalities. Integration of verbal and non-verbal communication channels creates a system in which the message is easier to understand. Expanding the focus to several expression forms can facilitate research on emotion recognition as well as human-machine interaction. In this article, the authors present a Polish emotional database composed of three modalities: facial expressions, body movement and gestures, and speech. The corpora contains recordings registered in studio conditions, acted out by 16 professional actors (8 male and 8 female). The data is labeled with six basic emotions categories, according to Ekman’s emotion categories. To check the quality of performance, all recordings are evaluated by experts and volunteers. The database is available to academic community and might be useful in the study on audio-visual emotion recognition.

Keywords: body movement, emotion recognition, emotional corpus, facial expressions, gestures, multimodal database, speech

Procedia PDF Downloads 333

Authors: Xingxing Peng

Abstract:

With the development of society, there are more and more online communication scenarios such as teleconference and online education. In the process of conference communication, the quality of voice communication is a very important part, and noise may cause the communication effect of participants to be greatly reduced. Therefore, voice noise reduction has an important impact on scenarios such as voice calls. This research focuses on the key technologies of the sound transmission process. The purpose is to maintain the audio quality to the maximum so that the listener can hear clearer and smoother sound. Firstly, to solve the problem that the traditional speech enhancement algorithm is not ideal when dealing with non-stationary noise, an adaptive speech noise reduction algorithm is studied in this paper. Traditional noise estimation methods are mainly used to deal with stationary noise. In this chapter, we study the spectral characteristics of different noise types, especially the characteristics of non-stationary Burst noise, and design a noise estimator module to deal with non-stationary noise. Noise features are extracted from non-speech segments, and the noise estimation module is adjusted in real time according to different noise characteristics. This adaptive algorithm can enhance speech according to different noise characteristics, improve the performance of traditional algorithms to deal with non-stationary noise, so as to achieve better enhancement effect. The experimental results show that the algorithm proposed in this chapter is effective and can better adapt to different types of noise, so as to obtain better speech enhancement effect.

Keywords: speech noise reduction, speech enhancement, self-adaptation, Wiener filter algorithm

Procedia PDF Downloads 38

Authors: Monica Gonzalez Machorro

Abstract:

Dementia is hard to diagnose because of the lack of early physical symptoms. Early dementia recognition is key to improving the living condition of patients. Speech technology is considered a valuable biomarker for this challenge. Recent works have utilized conventional acoustic features and machine learning methods to detect dementia in speech. BERT-like classifiers have reported the most promising performance. One constraint, nonetheless, is that these studies are either based on human transcripts or on transcripts produced by automatic speech recognition (ASR) systems. This research contribution is to explore a method that does not require transcriptions to detect early Alzheimer’s disease (AD) and mild cognitive impairment (MCI). This is achieved by fine-tuning a pre-trained ASR model for the downstream early AD and MCI tasks. To do so, a subset of the thoroughly studied Pitt Corpus is customized. The subset is balanced for class, age, and gender. Data processing also involves cropping the samples into 10-second segments. For comparison purposes, a baseline model is defined by training and testing a Random Forest with 20 extracted acoustic features using the librosa library implemented in Python. These are: zero-crossing rate, MFCCs, spectral bandwidth, spectral centroid, root mean square, and short-time Fourier transform. The baseline model achieved a 58% accuracy. To fine-tune HuBERT as a classifier, an average pooling strategy is employed to merge the 3D representations from audio into 2D representations, and a linear layer is added. The pre-trained model used is ‘hubert-large-ls960-ft’. Empirically, the number of epochs selected is 5, and the batch size defined is 1. Experiments show that our proposed method reaches a 69% balanced accuracy. This suggests that the linguistic and speech information encoded in the self-supervised ASR-based model is able to learn acoustic cues of AD and MCI.

Keywords: automatic speech recognition, early Alzheimer’s recognition, mild cognitive impairment, speech impairment

Procedia PDF Downloads 106

Authors: Monica Sharma, Harjit Pal Singh, Jasbinder Singh, Manju Bala

Abstract:

In Voice over Internet Protocol (VoIP) system, the speech signal is degraded when passed through the network layers. The speech signal is processed through the best effort policy based IP network, which leads to the network degradations including delay, packet loss and jitter. The packet loss is the major issue of the degradation in the VoIP signal quality; even a single lost packet may generate audible distortion in the decoded speech signal. In addition to these network degradations, the quality of the speech signal is also affected by the environmental noises and coder distortions. The signal quality of the VoIP system is improved through the interleaving technique. The performance of the system is evaluated for various types of noises at different network conditions. The performance of the enhanced VoIP signal is evaluated using perceptual evaluation of speech quality (PESQ) measurement for narrow band signal.

Keywords: VoIP, interleaving, packet loss, packet size, background noise

Procedia PDF Downloads 458

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 man-machine interface with a voice recognition system that allows the operator to tele-operate 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 spoken in two languages: French and Arabic. The recognition rate obtained 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) equal to 30 db, the Arabic speech recognition rate is 69% and 80% for French speech recognition rate. This can be explained by the ability of phonetic context of each speech when the noise is added.

Keywords: voice command, HMM, TIMIT, noise, HTK, Arabic, speech recognition

Procedia PDF Downloads 357

Authors: Imen Ben Abda

Abstract:

Languages have been classified into different rhythm classes. 'Stress-timed' languages are exemplified by English, 'syllable-timed' languages by French and 'mora-timed' languages by Japanese. However, to our best knowledge, acoustic studies have not been unanimous in strictly establishing which rhythm category a given language belongs to and failed to show empirical evidence for isochrony. Perception seems to be a good approach to categorize languages into different rhythm classes. This study, within the scope of experimental phonetics, includes an account of different perceptual experiments using cues from natural and inverted speech, as well as pitch extracted from speech data. It is an attempt to categorize speech rhythm over a large set of Arabic (Tunisian, Algerian, Lebanese and Moroccan) and English dialects (Welsh, Irish, Scottish and Texan) as well as other languages such as Chinese, Japanese, French, and German. Listeners managed to classify the different languages and dialects into different rhythm classes using suprasegmental cues mainly rhythm and pitch (F0). They also perceived rhythmic differences even among languages and dialects belonging to the same rhythm class. This may show that there are different subclasses within very broad rhythmic typologies.

Keywords: F0, inverted speech, mora-timing, rhythm variation, stress-timing, syllable-timing

Procedia PDF Downloads 495

Authors: Wan-Lin Tsai

Abstract:

Speech act of requests is an important issue in the field of language learning and teaching because we cannot avoid making requesting in our daily life. This study examined whether or not the subjects who were freshmen and majored in German at Wenzao University of Languages were able to use the linguistic forms which they had learned from their course book Schritte International to make appropriate requests through dialogue completed tasks (DCT). The results revealed that the majority of the subjects were unable to use the forms to make appropriate requests in German due to the lack of explicit instructions. Furthermore, Chinese interference was observed in students' productions. Explicit instructions in speech acts are strongly recommended.

Keywords: Chinese interference, German pragmatics, German teaching, make appropriate requests in German, speech act of requesting

Procedia PDF Downloads 447

Authors: Elad Vashdi

Abstract:

It is common to find speech deficit among children diagnosed with Autism. It can be found in the clinical field and recently in research. One of the DSM-V criteria suggests a speech delay (Delay in, or total lack of, the development of spoken language), but doesn't explain the cause of it. A common perception among professionals and families is that the inability to talk results from the autism. Autism is a name for a syndrome which just describes a phenomenon and is defined behaviorally. Since it is not based yet on a physiological gold standard, one can not conclude the nature of a deficit based on the name of the syndrome. A wide retrospective research (n=270) which included children with motor speech difficulties was conducted in Israel. The study analyzed entry evaluations in a private clinic during the years 2006-2013. The data was extracted from the reports. High percentage of children diagnosed with Autism (60%) was found. This result demonstrates the high relationship between Autism and motor speech problem. It also supports recent findings in research of Childhood apraxia of speech (CAS) occurrence among children with ASD. Only small percentage of the participants in this research (10%) were diagnosed with CAS even though their verbal deficits well fitted the guidelines for CAS diagnosis set by ASHA in 2007. This fact raises questions regarding the diagnostic procedure in Israel. The understanding that CAS might highly exist within Autism and can have a remarkable influence on the course of early development should be a guiding tool within the diagnosis procedure. CAS can explain the nature of the speech problem among some of the autistic children and guide the treatment in a more accurate way. Calculating the prevalence of CAS which includes the comorbidity with ASD reveals new numbers and suggests treating differently the CAS population.

Keywords: childhood apraxia of speech, Autism, treatment, speech

Procedia PDF Downloads 253

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 266

Authors: Shaode Yu, Jiajian Meng, Bing Zhu, Hang Yu, Qiurui Sun

Abstract:

Speech emotion recognition (SER) is for recognizing human subjective emotions through audio data in-depth analysis. From speech audios, how to comprehensively extract emotional information and how to effectively fuse extracted features remain challenging. This paper presents a dual-stream SER framework that embraces both full training and transfer learning of different networks for thorough feature encoding. Besides, a plug-and-play cross-attention fusion (CAF) module is implemented for the valid integration of the dual-stream encoder output. The effectiveness of the proposed CAF module is compared to the other three fusion modules (feature summation, feature concatenation, and feature-wise linear modulation) on two databases (RAVDESS and IEMO-CAP) using different dual-stream encoders (full training network, DPCNN or TextRCNN; transfer learning network, HuBERT or Wav2Vec2). Experimental results suggest that the CAF module can effectively reconcile conflicts between features from different encoders and outperform the other three feature fusion modules on the SER task. In the future, the plug-and-play CAF module can be extended for multi-branch feature fusion, and the dual-stream SER framework can be widened for multi-stream data representation to improve the recognition performance and generalization capacity.

Keywords: speech emotion recognition, cross-attention fusion, dual-stream, pre-trained

Procedia PDF Downloads 49

Authors: B.Shukir, H.Woo, P.Barzo, D.Kis

Abstract:

Preoperative brain mapping in tumors involving the speech areas has an important role to reduce surgical risks. Functional magnetic resonance imaging (fMRI) is the gold standard method to localize cortical speech areas preoperatively, but its availability in clinical routine is difficult. Diffusion MRI based probabilistic tractography is available in head MRI. It’s used to segment cortical subregions by their structural connectivity. In our study, we used probabilistic tractography to localize the frontal and temporal cortical speech areas. 15 patients with left frontal tumor were enrolled to our study. Speech fMRI and diffusion MRI acquired preoperatively. The standard automated anatomical labelling atlas 3 (AAL3) cortical atlas used to define 76 left frontal and 118 left temporal potential speech areas. 4 types of tractography were run according to the structural connection of these regions to the left arcuate fascicle (FA) to localize those cortical areas which have speech functions: 1, frontal through FA; 2, frontal with FA; 3, temporal to FA; 4, temporal with FA connections were determined. Thresholds of 1%, 5%, 10% and 15% applied. At each level, the number of affected frontal and temporal regions by fMRI and tractography were defined, the sensitivity and specificity were calculated. At the level of 1% threshold showed the best results. Sensitivity was 61,631,4% and 67,1523,12%, specificity was 87,210,4% and 75,611,37% for frontal and temporal regions, respectively. From our study, we conclude that probabilistic tractography is a reliable preoperative technique to localize cortical speech areas. However, its results are not feasible that the neurosurgeon rely on during the operation.

Keywords: brain mapping, brain tumor, fMRI, probabilistic tractography

Procedia PDF Downloads 136

Authors: Tholaine Matadi

Abstract:

South Africa is a democratic country with a historical record of racially-motivated marginalisation and exclusion of the majority. During the apartheid era the country was run along pieces of legislation and policies based on racial segregation. The system held a tight clamp on interracial mixing which forced people to remain in segregated areas. For example, a citizen from the Indian community could not own property in an area allocated to white people. In this way, a great majority of people were denied basic human rights. Now, there is a supreme constitution with an entrenched justiciable Bill of Rights founded on democratic values of social justice, human dignity, equality and the advancement of human rights and freedoms. The Constitution also enshrines the values of non-racialism and non-sexism. The Constitutional Court has the power to declare unconstitutional any law or conduct considered to be inconsistent with it. Now, more than two decades down the line, despite the abolition of apartheid, there is evidence that South Africa still experiences hate crimes which violate the entrenched right of vulnerable groups not to be discriminated against on the basis of race, sexual orientation, gender, national origin, occupation, or disability. To remedy this mischief parliament has responded by drafting the Prevention and Combatting of Hate Crimes and Hate Speech Bill. The Bill has been disseminated for public comment and suggestions. It is intended to combat hate crimes and hate speech based on sheer prejudice. The other purpose of the Bill is to bring South Africa in line with international human rights instruments against racism, racial discrimination, xenophobia and related expressions of intolerance identified in several international instruments. It is against this backdrop that this paper intends to analyse the impact of the Bill on the rights to human dignity, equality, and freedom. This study is significant because the Bill was highly contested and creates a huge debate. This study relies on a qualitative evaluative approach based on desktop and library research. The article recurs to primary and secondary sources. For comparative purpose, the paper compares South Africa with countries such as Australia, Canada, Kenya, Cuba, and United Kingdom which have criminalised hate crimes and hate speech. The finding from this study is that despite the Bill’s expressed positive intentions, this draft legislation is problematic for several reasons. The main reason is that it generates considerable controversy mostly because it is considered to infringe the right to freedom of expression. Though the author suggests that the Bill should not be rejected in its entirety, she notes the brutal psychological effect of hate crimes on their direct victims and the writer emphasises that a legislature can succeed to combat hate-crimes only if it provides for them as a separate stand-alone category of offences. In view of these findings, the study recommended that since hate speech clauses have a negative impact on freedom of expression it can be promulgated, subject to the legislature enacting the Prevention and Combatting of Hate-Crimes Bill as a stand-alone law which criminalises hate crimes.

Keywords: freedom of expression, hate crimes, hate speech, human dignity

Procedia PDF Downloads 145

Authors: Mary Titilayo Olowe

Abstract:

The controversies that trailed the political campaign and eventual choice of Donald Trump as the American president is so great that expectations are high as to what the content of his inaugural speech will portray. Given the fact that language is a dynamic vehicle of expressing intentions, the speech needs to be objectively assessed so as to access its content in the manner intended through the three strands of meaning postulated by the Systemic Functional Grammar (SFG): the ideational, the interpersonal and the textual. The focus of this paper, however, is on the interpersonal meaning which deals with how language exhibits social roles and relationship. This paper, therefore, attempts to analyse President Donald Trump’s inaugural speech to elicit interpersonal meaning in it. The analysis is done from the perspective of mood and modality which are housed in SFG. Results of the mood choice which is basically declarative, reveal an information-centered speech while the high option for the modal verb operator ‘will’ shows president Donald Trump’s ability to establish an equal and reliant relationship with his audience, i.e., the Americans. In conclusion, the appeal of the speech to different levels of Interpersonal meaning is largely responsible for its overall effectiveness. One can, therefore, understand the reason for the massive reaction it generates at the center of global discourse.

Keywords: interpersonal, modality, mood, systemic functional grammar

Procedia PDF Downloads 196

Authors: S. B. Rathna Kumar, Sandya K. Varudhini, Aparna Ravichandran

Abstract:

Telugu is a south central Dravidian language spoken in Andhra Pradesh, a southern state of India. The available speech identification tests in Telugu have been developed to determine the communication problems of individuals having a flat frequency hearing loss. These conventional speech audiometric tests would provide redundant information when used on individuals with high-frequency sloping hearing loss because of better hearing sensitivity in the low- and mid-frequency regions. Hence, conventional speech identification tests do not indicate the true nature of the communication problem of individuals with high-frequency sloping hearing loss. It is highly possible that a person with a high-frequency sloping hearing loss may get maximum scores if conventional speech identification tests are used. Hence, there is a need to develop speech identification test materials that are specifically designed to assess the speech identification performance of individuals with high-frequency sloping hearing loss. The present study aimed to develop speech identification test for individuals with high-frequency sloping hearing loss in Telugu. Individuals with high-frequency sloping hearing loss have difficulty in perception of voiceless consonants whose spectral energy is above 1000 Hz. Hence, the word lists constructed with phonemes having mid- and high-frequency spectral energy will estimate speech identification performance better for such individuals. The phonemes /k/, /g/, /c/, /ṭ/ /t/, /p/, /s/, /ś/, /ṣ/ and /h/are preferred for the construction of words as these phonemes have spectral energy distributed in the frequencies above 1000 KHz predominantly. The present study developed two word lists in Telugu (each word list contained 25 words) for evaluating speech identification performance of individuals with high-frequency sloping hearing loss. The performance of individuals with high-frequency sloping hearing loss was evaluated using both conventional and high-frequency word lists under recorded voice condition. The results revealed that the developed word lists were found to be more sensitive in identifying the true nature of the communication problem of individuals with high-frequency sloping hearing loss.

Keywords: speech identification test, high-frequency sloping hearing loss, recorded voice condition, Telugu

Procedia PDF Downloads 399

Authors: Harisudha Kuresan, Dhanalakshmi Samiappan, T. Rama Rao

Abstract:

In modern telecommunication applications, Glottal Closure Instants location finding is important and is directly evaluated from the speech waveform. Here, we study the GCI using Speech Event Detection using Residual Excitation and the Mean Based Signal (SEDREAMS) algorithm. Speech coding uses parameter estimation using audio signal processing techniques to model the speech signal combined with generic data compression algorithms to represent the resulting modeled in a compact bit stream. This paper proposes a sub-band coder SBC, which is a type of transform coding and its performance for GCI detection using SEDREAMS are evaluated. In SBCs code in the speech signal is divided into two or more frequency bands and each of these sub-band signal is coded individually. The sub-bands after being processed are recombined to form the output signal, whose bandwidth covers the whole frequency spectrum. Then the signal is decomposed into low and high-frequency components and decimation and interpolation in frequency domain are performed. The proposed structure significantly reduces error, and precise locations of Glottal Closure Instants (GCIs) are found using SEDREAMS algorithm.

Keywords: SEDREAMS, GCI, SBC, GOI

Procedia PDF Downloads 335

Authors: Thiago Spilborghs Bueno Meyer, Plinio Thomaz Aquino Junior

Abstract:

Through speech, which privileges the functional and interactive nature of the text, it is possible to ascertain the spatiotemporal circumstances, the conditions of production and reception of the discourse, the explicit purposes such as informing, explaining, convincing, etc. These conditions allow bringing the interaction between humans closer to the human-robot interaction, making it natural and sensitive to information. However, it is not enough to understand what is said; it is necessary to recognize emotions for the desired interaction. The validity of the use of neural networks for feature selection and emotion recognition was verified. For this purpose, it is proposed the use of neural networks and comparison of models, such as recurrent neural networks and deep neural networks, in order to carry out the classification of emotions through speech signals to verify the quality of recognition. It is expected to enable the implementation of robots in a domestic environment, such as the HERA robot from the RoboFEI@Home team, which focuses on autonomous service robots for the domestic environment. Tests were performed using only the Mel-Frequency Cepstral Coefficients, as well as tests with several characteristics of Delta-MFCC, spectral contrast, and the Mel spectrogram. To carry out the training, validation and testing of the neural networks, the eNTERFACE’05 database was used, which has 42 speakers from 14 different nationalities speaking the English language. The data from the chosen database are videos that, for use in neural networks, were converted into audios. It was found as a result, a classification of 51,969% of correct answers when using the deep neural network, when the use of the recurrent neural network was verified, with the classification with accuracy equal to 44.09%. The results are more accurate when only the Mel-Frequency Cepstral Coefficients are used for the classification, using the classifier with the deep neural network, and in only one case, it is possible to observe a greater accuracy by the recurrent neural network, which occurs in the use of various features and setting 73 for batch size and 100 training epochs.

Keywords: emotion recognition, speech, deep learning, human-robot interaction, neural networks

Procedia PDF Downloads 137