Search results for: degraded speech perception

Authors: Douglas MacCutcheon, Florian Pausch, Robert Ljung, Lorna Halliday, Stuart Rosen

Abstract:

Contemporary classrooms are increasingly inclusive of children with mild to moderate disabilities and children from different language backgrounds (bilinguals, multilinguals), but classroom environments and standards have not yet been adapted adequately to meet these challenges brought about by this inclusivity. Additionally, classrooms are becoming noisier as a learner-centered as opposed to teacher-centered teaching paradigm is adopted, which prioritizes group work and peer-to-peer learning. Challenging listening conditions with distracting sound sources and background noise are known to have potentially negative effects on children, particularly those that are prone to struggle with speech perception in noise. Therefore, this research investigates two groups vulnerable to these environmental effects, namely children with a mild to moderate hearing loss (MMHLs) and sequential bilinguals learning in their second language. In the MMHL study, this group was assessed on speech-in-noise perception, and a number of receptive language and cognitive measures (auditory working memory, auditory attention) and correlations were evaluated. Speech reception thresholds were found to be predictive of language and cognitive ability, and the nature of correlations is discussed. In the bilinguals study, sequential bilingual children’s listening comprehension, speech-in-noise perception, listening effort and release from masking was evaluated under a number of different ecologically valid acoustic scenarios in order to pinpoint the extent of the ‘native language benefit’ for Swedish children learning in English, their second language. Scene manipulations included target-to-distractor ratios and introducing spatially separated noise. This research will contribute to the body of findings from which educational institutions can draw when designing or adapting educational environments in inclusive schools.

Keywords: sequential bilinguals, classroom acoustics, mild to moderate hearing loss, speech-in-noise, release from masking

Procedia PDF Downloads 306

Authors: Abdul Wahid

Abstract:

Inner speech, also known as verbal thinking, self-talk or private speech, is characterized by the subjective language experience in the absence of overt or audible speech. It is a psychological form of verbal activity which is being rehearsed without the articulation of any sound wave. In Psychology, self-limiting speech means the type of speech which contains information that inhibits the development of the self. People, in most cases, experience inner speech in their first language. It is very frequent in Bangladesh where the Bangla (L1) speaking students lose track of speech during their presentations in English (L2). This paper investigates into the long pauses (more than 0.4 seconds long) in English (L2) presentations by Bangla speaking students (18-21 year old) and finds the intervention of Bangla (L1) inner speech as one of its causes. The overt speeches of the presenters are placed on Audacity Audio Editing software where the length of pauses are measured in milliseconds. Varieties of inner speech questionnaire (VISQ) have been conducted randomly amongst the participants out of whom 20 were selected who have similar phenomenology of inner speech. They have been interviewed to describe the type and content of the voices that went on in their head during the long pauses. The qualitative interview data are then codified and converted into quantitative data. It was observed that in more than 80% cases students experience self-limiting inner speech/self-talk during their unwanted pauses in L2 presentations.

Keywords: Bangla-English Bilinguals, inner speech, L1 intervention in bilingualism, motor schema, pauses, phonological loop, phonological store, working memory

Procedia PDF Downloads 128

Authors: Tobias Schramm, Günther Prokop

Abstract:

Degraded vehicle shock absorbers represent a risk for road safety. The exact effect of degraded vehicle dampers on road safety is still the subject of research. This work is intended to contribute to estimating the effect of degraded twin-tube dampers of passenger cars on road safety. An axle model was built using a damper model to simulate different degradation levels. To parameterize the model, a realistic parameter space was estimated based on test rig measurements and database analyses, which is intended to represent the vehicle field in Germany. Within the parameter space, simulations of the axle model were carried out, which calculated the transmittable lateral forces of the various axle configurations as a function of vehicle speed, road surface, damper conditions and axle parameters. A degraded damper has the greatest effect on the transmittable lateral forces at high speeds and in poor road conditions. If a vehicle is traveling at a speed of 100 kph on a Class D road, a degraded damper reduces the transmissible lateral forces of an axle by 20 % on average. For individual parameter configurations, this value can rise to 50 %. The axle parameters that most influence the effect of a degraded damper are the vertical stiffness of the tire, the unsprung mass and the stabilizer stiffness of the axle.

Keywords: vehicle dynamics, vehicle simulation, vehicle component degradation, shock absorber model, shock absorber degradation

Procedia PDF Downloads 78

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 395

Authors: E. Krasnova, E. Bulgakova, V. Shchemelinin

Abstract:

The paper deals with acoustic-spectrographic voice identification method in terms of its performance in non-native language speech. Performance evaluation is conducted by comparing the result of the analysis of recordings containing native language speech with recordings that contain foreign language speech. Our research is based on Tajik and Russian speech of Tajik native speakers due to the character of the criminal situation with drug trafficking. We propose a pilot experiment that represents a primary attempt enter the field.

Keywords: speaker identification, acoustic-spectrographic method, non-native speech, performance evaluation

Procedia PDF Downloads 421

Authors: M. A. Ben Messaoud, A. Bouzid, N. Ellouze

Abstract:

Speech Segmentation is the measure of the change point detection for partitioning an input speech signal into regions each of which accords to only one speaker. In this paper, we apply two features based on multi-scale product (MP) of the clean speech, namely the spectral centroid of MP, and the zero crossings rate of MP. We focus on multi-scale product analysis as an important tool for segmentation extraction. The multi-scale product is based on making the product of the speech wavelet transform coefficients at three successive dyadic scales. We have evaluated our method on the Keele database. Experimental results show the effectiveness of our method presenting a good performance. It shows that the two simple features can find word boundaries, and extracted the segments of the clean speech.

Keywords: multiscale product, spectral centroid, speech segmentation, zero crossings rate

Procedia PDF Downloads 471

Authors: Seham El Kareh, Miramar Etman

Abstract:

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

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

Procedia PDF Downloads 181

Authors: Fawaz S. Al-Anzi, Dia AbuZeina

Abstract:

Speech recognition is of an important contribution in promoting new technologies in human computer interaction. Today, there is a growing need to employ speech technology in daily life and business activities. However, speech recognition is a challenging task that requires different stages before obtaining the desired output. Among automatic speech recognition (ASR) components is the feature extraction process, which parameterizes the speech signal to produce the corresponding feature vectors. Feature extraction process aims at approximating the linguistic content that is conveyed by the input speech signal. In speech processing field, there are several methods to extract speech features, however, Mel Frequency Cepstral Coefficients (MFCC) is the popular technique. It has been long observed that the MFCC is dominantly used in the well-known recognizers such as the Carnegie Mellon University (CMU) Sphinx and the Markov Model Toolkit (HTK). Hence, this paper focuses on the MFCC method as the standard choice to identify the different speech segments in order to obtain the language phonemes for further training and decoding steps. Due to MFCC good performance, the previous studies show that the MFCC dominates the Arabic ASR research. In this paper, we demonstrate MFCC as well as the intermediate steps that are performed to get these coefficients using the HTK toolkit.

Keywords: speech recognition, acoustic features, mel frequency, cepstral coefficients

Procedia PDF Downloads 233

Authors: B. Kuiper

Abstract:

When Dwight D. Eisenhower delivered his final Presidential speech in 1961, he was using the opportunity to bid farewell to America, but he was also trying to warn his fellow countrymen about deeper challenges threatening the country. In this analysis, Eisenhower’s speech is examined in light of the impact it had on American culture, communication concepts, and political ramifications. The paper initially highlights the previous literature on the speech, especially in light of its 50^th anniversary, and reveals a man whose main concern was how the speech’s words would affect his beloved country. The painstaking approach to the wording of the speech to reveal the intent is key, particularly in light of analyzing the motivations according to “virtuous communication.” This philosophical construct indicates that Eisenhower’s Farewell Address was crafted carefully according to a departing President’s deepest values and concerns, concepts that he wanted to pass along to his successor, to his country, and even to the world.

Keywords: Eisenhower, mass communication, political speech, rhetoric

Procedia PDF Downloads 249

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 104

Authors: Bency Jacob, S.B. Waykar

Abstract:

Degradations in historical document images appear due to aging of the documents. It is very difficult to understand and retrieve text from badly degraded documents as there is variation between the document foreground and background. Thresholding of such document images either result in broken characters or detection of false texts. Numerous algorithms exist that can separate text and background efficiently in the textual regions of the document; but portions of background are mistaken as text in areas that hardly contain any text. This paper presents a way to overcome these problems by a robust binarization technique that recovers the text from a severely degraded document images and thereby increases the accuracy of optical character recognition systems. The proposed document recovery algorithm efficiently removes degradations from document images. Here we are using the ostus method ,local thresholding and global thresholding and after the binarization training and recognizing the characters in the degraded documents.

Keywords: binarization, denoising, global thresholding, local thresholding, thresholding

Procedia PDF Downloads 313

Authors: Qianhua He, Weili Zhou, Aiwu Chen

Abstract:

A sparse representation speech denoising method based on adapted stopping residue error was presented in this paper. Firstly, the cross-correlation between the clean speech spectrum and the noise spectrum was analyzed, and an estimation method was proposed. In the denoising method, an over-complete dictionary of the clean speech power spectrum was learned with the K-singular value decomposition (K-SVD) algorithm. In the sparse representation stage, the stopping residue error was adaptively achieved according to the estimated cross-correlation and the adjusted noise spectrum, and the orthogonal matching pursuit (OMP) approach was applied to reconstruct the clean speech spectrum from the noisy speech. Finally, the clean speech was re-synthesised via the inverse Fourier transform with the reconstructed speech spectrum and the noisy speech phase. The experiment results show that the proposed method outperforms the conventional methods in terms of subjective and objective measure.

Keywords: speech denoising, sparse representation, k-singular value decomposition, orthogonal matching pursuit

Procedia PDF Downloads 474

Authors: Othmane Bouferroum, Malika Boudraa

Abstract:

In this study, a dual exponential model for CV formant transition is derived from locus theory of speech perception. Then, an algorithm for automatic vowel and consonant’s target formant frequency detection is developed and tested on real speech. The results show that vowels and consonants are detected through transitions rather than their small stable portions. Also, vowel reduction is clearly observed in our data. These results are confirmed by the observations made in perceptual experiments in the literature.

Keywords: acoustic invariance, coarticulation, formant transition, locus equation

Procedia PDF Downloads 238

Authors: Tinatin Kurdghelashvili

Abstract:

The paper deals with the usage of speech acts and politeness strategies in an EFL classroom in Georgia (Rep of). It explores the students’ and the teachers’ practice of the politeness strategies and the speech acts of apology, thanking, request, compliment/encouragement, command, agreeing/disagreeing, addressing and code switching. The research method includes observation as well as a questionnaire. The target group involves the students from Georgian public schools and two certified, experienced local English teachers. The analysis is based on Searle’s Speech Act Theory and Brown and Levinson’s politeness strategies. The findings show that the students have certain knowledge regarding politeness yet they fail to apply them in English communication. In addition, most of the speech acts from the classroom interaction are used by the teachers and not the students. Thereby, it is suggested that teachers should cultivate the students’ communicative competence and attempt to give them opportunities to practice more English speech acts than they do today.

Keywords: english as a foreign language, Georgia, politeness principles, speech acts

Procedia PDF Downloads 610

Authors: A. Shoiynbek, K. Kozhakhmet, P. Menezes, D. Kuanyshbay, D. Bayazitov

Abstract:

Speech emotion recognition has received increasing research interest all through current years. There was used emotional speech that was collected under controlled conditions in most research work. Actors imitating and artificially producing emotions in front of a microphone noted those records. There are four issues related to that approach, namely, (1) emotions are not natural, and it means that machines are learning to recognize fake emotions. (2) Emotions are very limited by quantity and poor in their variety of speaking. (3) There is language dependency on SER. (4) Consequently, each time when researchers want to start work with SER, they need to find a good emotional database on their language. In this paper, we propose the approach to create an automatic tool for speech emotion extraction based on facial emotion recognition and describe the sequence of actions of the proposed approach. One of the first objectives of the sequence of actions is a speech detection issue. The paper gives a detailed description of the speech detection model based on a fully connected deep neural network for Kazakh and Russian languages. Despite the high results in speech detection for Kazakh and Russian, the described process is suitable for any language. To illustrate the working capacity of the developed model, we have performed an analysis of speech detection and extraction from real tasks.

Keywords: deep neural networks, speech detection, speech emotion recognition, Mel-frequency cepstrum coefficients, collecting speech emotion corpus, collecting speech emotion dataset, Kazakh speech dataset

Procedia PDF Downloads 74

Authors: Suwimol Apapol, Punrapha Praditpong

Abstract:

The objectives of the study were to find out the frequencies of figures of speech in fragrance advertising captions as well as the types of figures of speech most commonly applied in captions. The relation between figures of speech and fragrance was also examined in order to analyze how figures of speech were used to represent fragrance. Thirty-five fragrance advertisements were randomly selected from the Internet. Content analysis was applied in order to consider the relation between figures of speech and fragrance. The results showed that figures of speech were found in almost every fragrance advertisement except one advertisement of several Goods service. Thirty-four fragrance advertising captions used at least one kind of figure of speech. Metaphor was most frequently found and also most frequently applied in fragrance advertising captions, followed by alliteration, rhyme, simile and personification, and hyperbole respectively which is in harmony with the research hypotheses as well.

Keywords: advertising captions, captions on internet, consumer purchasing decision, e-commerce

Procedia PDF Downloads 246

Authors: Tsegaw Abebe, Temesgen Abebe

Abstract:

Land degradation is one of a serious environmental challenge in Ethiopia and is one of the major underlying causes for declining agricultural productivity. The Ethiopia government realized the significance of environmental restoration specifically on deforested and degraded land after the 1973 and 1984/85 major famines that struck the country. Among the various conservation strategies, the establishment of area exclosures have been regarded as an effective response to halt and reverse the problems of land degradation. There are limited studies in Ethiopia dealing how the conversion of free grazing lands and degraded lands by closures increase biomass accumulation. However, these studies are not sufficient to conclude about the strength of area closures to restore degraded vegetations at the diverse agro-ecological condition. The overall objective of this study was, therefore, to assess and evaluate the usefulness of area closure technique in enhancing rehabilitation of degraded ecosystem and thereby increase the natural capital in the study site (southern Ethiopia). Woody plant species were collected from area exclosure for eight year and adjacent degraded land with similar landscape positions using systematic sampling plot design technique. Woody species diversity was determined by Shannon diversity. Comparative assessment result of woody plant species analysis showed that the density of woody species in the exclosure and degraded site were 778 and 222 individuals per hectare, respectively. A total of 16 woody species, representing 12 families were recorded in the study site. Out of the 12 families, all were recorded in the exclosure while 5 were recorded in the degraded site. Out of the 16 species, 15 were recorded in the exclosure while six were in the degraded site. A total of 10 species were recorded in the exclosure, which were absent in the degraded site. Similarly, one species was recorded in the degraded site which was not present in the exclosure. The results showed that protecting of degraded site from human and animal disturbances promotes woody plant species regenerations and productivity Apart from increasing woody plant species, the local communities have benefited from the exclosure in the form of both products (grass harvesting) and services (ecological). Due to this reason the local communities have positive attitudes and contribute a lot for the success of enclosures in the study site. The present study clearly showed that area closure interventions should be oriented towards managing and improving the productivity of the degraded land, in such a way that both the need for conservation of biodiversity and environmental sustainability, and the demands of the local people for biomass resources can be achieved.

Keywords: degraded land, exclosure, land restoration, woody vegetation

Procedia PDF Downloads 388

Authors: Pogula Rakesh, T. Kishore Kumar

Abstract:

Speech enhancement is a long standing problem with numerous applications like teleconferencing, VoIP, hearing aids, and speech recognition. The motivation behind this research work is to obtain a clean speech signal of higher quality by applying the optimal noise cancellation technique. Real-time adaptive filtering algorithms seem to be the best candidate among all categories of the speech enhancement methods. In this paper, we propose a speech enhancement method based on Recursive Least Squares (RLS) adaptive filter of speech signals. Experiments were performed on noisy data which was prepared by adding AWGN, Babble and Pink noise to clean speech samples at -5dB, 0dB, 5dB, and 10dB SNR levels. We then compare the noise cancellation performance of proposed RLS algorithm with existing NLMS algorithm in terms of Mean Squared Error (MSE), Signal to Noise ratio (SNR), and SNR loss. Based on the performance evaluation, the proposed RLS algorithm was found to be a better optimal noise cancellation technique for speech signals.

Keywords: adaptive filter, adaptive noise canceller, mean squared error, noise reduction, NLMS, RLS, SNR, SNR loss

Procedia PDF Downloads 450

Authors: Konysbek Aksaule

Abstract:

The purpose of this work is to explore new and effective ways of teaching English to students who are studying a foreign language since the timeliness of the problem disclosed in this article is due to the high level of English proficiency that potential specialists must have due to high competition in the context of global globalization. The article presents an analysis of the feasibility and effectiveness of using an authentic feature film in teaching English to students. The methodological basis of the study includes an assessment of the level of students' proficiency in a foreign language, the stage of evaluating the film, and the method of selecting the film for certain categories of students. The study also contains a list of practical tasks that can be applied in the process of viewing and perception of an original feature film in a foreign language, and which are aimed at developing language skills such as speaking and listening. The results of this study proved that teaching English to students through watching an original film is one of the most effective methods because it improves speech perception, speech reproduction ability, and also expands the vocabulary of students and makes their speech fluent. In addition, learning English through watching foreign films has a huge impact on the cultural views and knowledge of students about the country of the language being studied and the world in general. Thus, this study demonstrates the high potential of using authentic feature film in English lessons for pedagogical science and methods of teaching English in general.

Keywords: university, education, students, foreign language, feature film

Procedia PDF Downloads 123

Authors: Jarek Krajewski, Andre Wittenborn, Martin Sauerland

Abstract:

This abstract describes a promising approach for estimating post-traumatic stress disorder (PTSD) based on prosodic speech characteristics. It illustrates the validity of this method by briefly discussing results from an Arabic refugee sample (N= 47, 32 m, 15 f). A well-established standardized self-report scale “Reaction of Adolescents to Traumatic Stress” (RATS) was used to determine the ground truth level of PTSD. The speech material was prompted by telling about autobiographical related sadness inducing experiences (sampling rate 16 kHz, 8 bit resolution). In order to investigate PTSD-induced speech changes, a self-developed set of 136 prosodic speech features was extracted from the .wav files. This set was adapted to capture traumatization related speech phenomena. An artificial neural network (ANN) machine learning model was applied to determine the PTSD level and reached a correlation of r = .37. These results indicate that our classifiers can achieve similar results to those seen in speech-based stress research.

Keywords: speech prosody, PTSD, machine learning, feature extraction

Procedia PDF Downloads 69

Authors: A. Belmeguenai, K. Mansouri, R. Djemili

Abstract:

This work present a new algorithm based on the nonlinear filter generator for speech encryption and decryption. The proposed algorithm consists on the use a linear feedback shift register (LFSR) whose polynomial is primitive and nonlinear Boolean function. The purpose of this system is to construct Keystream with good statistical properties, but also easily computable on a machine with limited capacity calculated. This proposed speech encryption scheme is very simple, highly efficient, and fast to implement the speech encryption and decryption. We conclude the paper by showing that this system can resist certain known attacks.

Keywords: nonlinear filter generator, stream ciphers, speech encryption, security analysis

Procedia PDF Downloads 267

Authors: S. Jagadeesh Kumar

Abstract:

This expose presents a luculent of recent machine learning practices as employed in the modern and as pertinent to prospective automatic speech recognition schemes. The aspiration is to promote additional traverse ablution among the machine learning and automatic speech recognition factions that have transpired in the precedent. The manuscript is structured according to the chief machine learning archetypes that are furthermore trendy by now or have latency for building momentous hand-outs to automatic speech recognition expertise. The standards offered and convoluted in this article embraces adaptive and multi-task learning, active learning, Bayesian learning, discriminative learning, generative learning, supervised and unsupervised learning. These learning archetypes are aggravated and conferred in the perspective of automatic speech recognition tools and functions. This manuscript bequeaths and surveys topical advances of deep learning and learning with sparse depictions; further limelight is on their incessant significance in the evolution of automatic speech recognition.

Keywords: automatic speech recognition, deep learning methods, machine learning archetypes, Bayesian learning, supervised and unsupervised learning

Procedia PDF Downloads 415

Authors: Manjare Chandraprabha A., S. D. Shirbahadurkar, Manjare Anil S., Paithne Ajay N.

Abstract:

This paper proposes Intonation Modeling for Prosody generation in Neutral speech for Marathi (language spoken in Maharashtra, India) story telling applications. Nowadays audio story telling devices are very eminent for children. In this paper, we proposed tilt model for stressed words in Marathi for speech modification. Tilt model predicts modification in tone of neutral speech. GMM is used to identify stressed words for modification.

Keywords: tilt model, fundamental frequency, statistical parametric speech synthesis, GMM

Procedia PDF Downloads 362

Authors: Gautam Sharda

Abstract:

The concept of right speech is the third stage of the noble eightfold path as prescribed by the Buddha and followed by millions of practicing Buddhists. The Buddha lays a lot of importance on the notion of right speech (Samma Vacca). In the Angutara Nikaya, the Buddha mentioned what constitutes right speech, which is basically four kinds of abstentions; namely abstaining from false speech, abstaining from slanderous speech, abstaining from harsh or hateful speech and abstaining from idle chatter. The Buddha gives reasons in support of his view as to why abstaining from these four kinds of speeches is favourable not only for maintaining the peace and equanimity within an individual but also within a society. It is a known fact that when we say something harsh or slanderous to others, it eventually affects our individual peace of mind too. We also know about the many examples of hate speeches which have led to senseless cases of violence and which are well documented within our country and the world. Also, indulging in false speech is not a healthy sign for individuals within a group as this kind of a social group which is based on falsities and lies cannot really survive for long and will eventually lead to chaos. Buddha also told us to refrain from idle chatter or gossip as generally we have seen that idle chatter or gossip does more harm than any good to the individual and the society. Hence, if most of us actually inculcate this third stage (namely, right speech) of the noble eightfold path of the Buddha in our daily life, it would be highly beneficial both for the individual and for the harmony of the society.

Keywords: Buddhism, speech, individual, society

Procedia PDF Downloads 232

Authors: Khaled M. Alhawiti

Abstract:

This research study aims to present a retrospective study about speech recognition systems and artificial intelligence. Speech recognition has become one of the widely used technologies, as it offers great opportunity to interact and communicate with automated machines. Precisely, it can be affirmed that speech recognition facilitates its users and helps them to perform their daily routine tasks, in a more convenient and effective manner. This research intends to present the illustration of recent technological advancements, which are associated with artificial intelligence. Recent researches have revealed the fact that speech recognition is found to be the utmost issue, which affects the decoding of speech. In order to overcome these issues, different statistical models were developed by the researchers. Some of the most prominent statistical models include acoustic model (AM), language model (LM), lexicon model, and hidden Markov models (HMM). The research will help in understanding all of these statistical models of speech recognition. Researchers have also formulated different decoding methods, which are being utilized for realistic decoding tasks and constrained artificial languages. These decoding methods include pattern recognition, acoustic phonetic, and artificial intelligence. It has been recognized that artificial intelligence is the most efficient and reliable methods, which are being used in speech recognition.

Keywords: speech recognition, acoustic phonetic, artificial intelligence, hidden markov models (HMM), statistical models of speech recognition, human machine performance

Procedia PDF Downloads 446

Authors: Chafik Barnoussi, Mourad Talbi, Adnane Cherif

Abstract:

In this paper we propose a new speech compression system based on the application of the Bionic Wavelet Transform (BWT) combined with the psychoacoustic model. This compression system is a modified version of the compression system using a MDCT (Modified Discrete Cosine Transform) filter banks of 32 filters each and the psychoacoustic model. This modification consists in replacing the banks of the MDCT filter banks by the bionic wavelet coefficients which are obtained from the application of the BWT to the speech signal to be compressed. These two methods are evaluated and compared with each other by computing bits before and bits after compression. They are tested on different speech signals and the obtained simulation results show that the proposed technique outperforms the second technique and this in term of compressed file size. In term of SNR, PSNR and NRMSE, the outputs speech signals of the proposed compression system are with acceptable quality. In term of PESQ and speech signal intelligibility, the proposed speech compression technique permits to obtain reconstructed speech signals with good quality.

Keywords: speech compression, bionic wavelet transform, filterbanks, psychoacoustic model

Procedia PDF Downloads 358

Authors: Yili Liu, Honghao Ren, Mariko Kondo

Abstract:

In the field of second language (L2) speech learning, it is well-known that that learner’s first language (L1) phonetic and phonological characteristics will be transferred into their L2 production and perception, which lead to foreign accent. For L1 Mandarin learners of Japanese, the confusion of /u/ and /o/ in /CjV/ sequences has been observed in their utterance frequently. L1 transfer is considered to be the cause of this issue, however, other factors which influence the identification of /Cju/ and /Cjo/ sequences still under investigation. This study investigates the perception of Japanese /Cju/ and /Cjo/ units by L1 Mandarin learners of Japanese. It further examined whether learners’ proficiency, syllable position, phonetic features of preceding consonants and background noise affect learners’ performance in perception. Fifty-two Mandarin-speaking learners of Japanese and nine native Japanese speakers were recruited to participate in an identification task. Learners were divided into beginner, intermediate and advanced level according to their Japanese proficiency. The average correct rate was used to evaluate learners’ perceptual performance. Furthermore, the comparison of the correct rate between learners’ groups and the control group was conducted as well to examine learners’ nativelikeness. Results showed that background noise tends to pose an adverse effect on distinguishing /u/ and /o/ in /CjV/ sequences. Secondly, Japanese proficiency has no influence on learners’ perceptual performance in the quiet and in background noise. Then all learners did not reach a native-like level without the distraction of noise. Beginner level learners performed less native-like, although higher level learners appeared to have achieved nativelikeness in the multi-talker babble noise. Finally, syllable position tends to affect distinguishing /Cju/ and /Cjo/ only under the noisy condition. Phonetic features of preceding consonants did not impact learners’ perception in any listening conditions. Findings in this study can give an insight into a further understanding of Japanese vowel acquisition by L1 Mandarin learners of Japanese. In addition, this study indicates that L1 transfer is not the only explanation for the confusion of /u/ and /o/ in /CjV/ sequences, factors such as listening condition and syllable position are also needed to take into consideration in future research. It also suggests the importance of perceiving speech in a noisy environment, which is close to the actual conversation required more attention to pedagogy.

Keywords: background noise, Chinese learners of Japanese, /Cju/ and /Cjo/ sequences, second language perception

Procedia PDF Downloads 138

Authors: Nabil Shawkat, Jamil Saquer

Abstract:

Social media has accelerated our ability to engage with others and eliminated many communication barriers. On the other hand, the widespread use of social media resulted in an increase in online hate speech. This has drastic impacts on vulnerable individuals and societies. Therefore, it is critical to detect hate speech to prevent innocent users and vulnerable communities from becoming victims of hate speech. We investigate the performance of different deep learning and machine learning algorithms on three different datasets. Our results show that the BERT model gives the best performance among all the models by achieving an F1-score of 90.6% on one of the datasets and F1-scores of 89.7% and 88.2% on the other two datasets.

Keywords: hate speech, machine learning, deep learning, abusive words, social media, text classification

Procedia PDF Downloads 103

Authors: Rui Wang, Luodi Yu, Dan Huang, Hsuan-Chih Chen, Yang Zhang, Suiping Wang

Abstract:

Enhanced discrimination of pure tones but diminished discrimination of speech pitch (i.e., lexical tone) were found in children with autism who speak a tonal language (Mandarin), suggesting a speech-specific impairment of pitch perception in these children. However, in tonal languages, both lexical tone and vowel are phonemic cues and integrally dependent on each other. Therefore, it is unclear whether the presence of phonemic vowel dimension contributes to the observed lexical tone deficits in Mandarin-speaking children with autism. The current study employed a multi-feature oddball paradigm to examine how vowel and tone dimensions contribute to the neural responses for syllable change detection and involuntary attentional orienting in school-age Mandarin-speaking children with autism. In the oddball sequence, syllable /da1/ served as the standard stimulus. There were three deviant stimulus conditions, representing tone-only change (TO, /da4/), vowel-only change (VO, /du1/), and change of tone and vowel simultaneously (TV, /du4/). EEG data were collected from 25 children with autism and 20 age-matched normal controls during passive listening to the stimulation. For each deviant condition, difference waveform measuring mismatch negativity (MMN) was derived from subtracting the ERP waveform to the standard sound from that to the deviant sound for each participant. Additionally, the linear summation of TO and VO difference waveforms was compared to the TV difference waveform, to examine whether neural sensitivity for TV change detection reflects simple summation or nonlinear integration of the two individual dimensions. The MMN results showed that the autism group had smaller amplitude compared with the control group in the TO and VO conditions, suggesting impaired discriminative sensitivity for both dimensions. In the control group, amplitude of the TV difference waveform approximated the linear summation of the TO and VO waveforms only in the early time window but not in the late window, suggesting a time course from dimensional summation to nonlinear integration. In the autism group, however, the nonlinear TV integration was already present in the early window. These findings suggest that speech perception atypicality in children with autism rests not only in the processing of single phonemic dimensions, but also in the dimensional integration process.

Keywords: autism, event-related potentials , mismatch negativity, speech perception

Procedia PDF Downloads 175

Authors: Samba Raju, Chiluveru, Manoj Tripathy

Abstract:

Intelligibility is an essential characteristic of a speech signal, which is used to help in the understanding of information in speech signal. Background noise in the environment can deteriorate the intelligibility of a recorded speech. In this paper, we presented a simple variance subtracted - variable level discrete wavelet transform, which improve the intelligibility of speech. The proposed algorithm does not require an explicit estimation of noise, i.e., prior knowledge of the noise; hence, it is easy to implement, and it reduces the computational burden. The proposed algorithm decides a separate decomposition level for each frame based on signal dominant and dominant noise criteria. The performance of the proposed algorithm is evaluated with speech intelligibility measure (STOI), and results obtained are compared with Universal Discrete Wavelet Transform (DWT) thresholding and Minimum Mean Square Error (MMSE) methods. The experimental results revealed that the proposed scheme outperformed competing methods

Keywords: discrete wavelet transform, speech intelligibility, STOI, standard deviation

Procedia PDF Downloads 117