Search results for: speech recognition performance

Authors: Christian Arcos, Marley Vellasco, Abraham Alcaim

Abstract:

In this paper, we present a wavelet coefficients masking based on Local Binary Patterns (WLBP) approach to enhance the temporal spectra of the wavelet coefficients for speech enhancement. This technique exploits the wavelet denoising scheme, which splits the degraded speech into pyramidal subband components and extracts frequency information without losing temporal information. Speech enhancement in each high-frequency subband is performed by binary labels through the local binary pattern masking that encodes the ratio between the original value of each coefficient and the values of the neighbour coefficients. This approach enhances the high-frequency spectra of the wavelet transform instead of eliminating them through a threshold. A comparative analysis is carried out with conventional speech enhancement algorithms, demonstrating that the proposed technique achieves significant improvements in terms of PESQ, an international recommendation of objective measure for estimating subjective speech quality. Informal listening tests also show that the proposed method in an acoustic context improves the quality of speech, avoiding the annoying musical noise present in other speech enhancement techniques. Experimental results obtained with a DNN based speech recognizer in noisy environments corroborate the superiority of the proposed scheme in the robust speech recognition scenario.

Keywords: binary labels, local binary patterns, mask, wavelet coefficients, speech enhancement, speech recognition

Procedia PDF Downloads 229

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 161

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 127

Authors: Saurabh Farkya, Govinda Surampudi

Abstract:

Optical Character Recognition is one of the current major research areas. This paper is focussed on recognition of Devanagari script and its sound generation. This Paper consists of two parts. First, Optical Character Recognition of Devnagari handwritten Script. Second, speech synthesis of the recognized text. This paper shows an implementation of support vector machines for the purpose of Devnagari Script recognition. The Support Vector Machines was trained with Multi Domain features; Transform Domain and Spatial Domain or Structural Domain feature. Transform Domain includes the wavelet feature of the character. Structural Domain consists of Distance Profile feature and Gradient feature. The Segmentation of the text document has been done in 3 levels-Line Segmentation, Word Segmentation, and Character Segmentation. The pre-processing of the characters has been done with the help of various Morphological operations-Otsu's Algorithm, Erosion, Dilation, Filtration and Thinning techniques. The Algorithm was tested on the self-prepared database, a collection of various handwriting. Further, Unicode was used to convert recognized Devnagari text into understandable computer document. The document so obtained is an array of codes which was used to generate digitized text and to synthesize Hindi speech. Phonemes from the self-prepared database were used to generate the speech of the scanned document using concatenation technique.

Keywords: Character Recognition (OCR), Text to Speech (TTS), Support Vector Machines (SVM), Library of Support Vector Machines (LIBSVM)

Procedia PDF Downloads 499

Authors: Khenfer-Koummich Fatima, Mesbahi Larbi, Hendel Fatiha

Abstract:

This paper presents a recognition system for isolated words like robot commands. It’s carried out by Time Delay Neural Networks; TDNN. To teleoperate a robot for specific tasks as turn, close, etc… In industrial environment and taking into account the noise coming from the machine. The choice of TDNN is based on its generalization in terms of accuracy, in more it acts as a filter that allows the passage of certain desirable frequency characteristics of speech; the goal is to determine the parameters of this filter for making an adaptable system to the variability of speech signal and to noise especially, for this the back propagation technique was used in learning phase. The approach was applied on commands pronounced in two languages separately: The French and Arabic. The results for two test bases of 300 spoken words for each one are 87%, 97.6% in neutral environment and 77.67%, 92.67% when the white Gaussian noisy was added with a SNR of 35 dB.

Keywords: TDNN, neural networks, noise, speech recognition

Procedia PDF Downloads 289

Authors: Naouel Zoghlami

Abstract:

Spoken-word recognition involves the simultaneous activation of potential word candidates which compete with each other for final correct recognition. In continuous speech, the activation-competition process gets more complicated due to speech reductions existing at word boundaries. Lexical processing is more difficult in L2 than in L1 because L2 listeners often lack phonetic, lexico-semantic, syntactic, and prosodic knowledge in the target language. In this study, we investigate the on-line lexical segmentation hypotheses that French listeners of L2 English form and then revise as subsequent perceptual evidence is revealed. Our purpose is to shed further light on the processes of L2 spoken-word recognition in context and better understand L2 listening difficulties through a comparison of skilled and unskilled reactions at the point where their working hypothesis is rejected. We use a variant of the gating experiment in which subjects transcribe an English sentence presented in increments of progressively greater duration. The spoken sentence was “And this amazing athlete has just broken another world record”, chosen mainly because it included common reductions and phonetic features in English, such as elision and assimilation. Our preliminary results show that there is an important difference in the manner in which proficient and less-proficient L2 listeners handle connected speech. Less-proficient listeners delay recognition of words as they wait for lexical and syntactic evidence to appear in the gates. Further statistical results are currently being undertaken.

Keywords: gating paradigm, spoken word recognition, online lexical segmentation, L2 listening

Procedia PDF Downloads 464

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 283

Authors: Maha Saliba Foster

Abstract:

Speech perception has been recognized as a bi-sensory process involving the auditory and visual channels. Compared to the auditory modality, the contribution of the visual signal to speech perception is not very well understood. Studying how the visual modality affects speech recognition can have pedagogical implications in second language learning, as well as clinical application in speech therapy. The current investigation explores the potential effect of speech visual cues on the perception of Arabic emphatics (AEs). The corpus consists of 36 minimal pairs each containing two contrasting consonants, an AE versus a non-emphatic (NE). Movies of four Lebanese speakers were edited to allow perceivers to have partial view of facial regions: lips only, lips-cheeks, lips-chin, lips-cheeks-chin, lips-cheeks-chin-neck. In the absence of any auditory information and relying solely on visual speech, perceivers were above chance at correctly identifying AEs or NEs across vowel contexts; moreover, the models were able to predict the probability of perceivers’ accuracy in identifying some of the COIs produced by certain speakers; additionally, results showed an overlap between the measurements selected by the computer and those selected by human perceivers. The lack of significant face effect on the perception of AEs seems to point to the lips, present in all of the videos, as the most important and often sufficient facial feature for emphasis recognition. Future investigations will aim at refining the analyses of visual cues used by perceivers by using Principal Component Analysis and including time evolution of facial feature measurements.

Keywords: Arabic emphatics, machine learning, speech perception, visual speech perception

Procedia PDF Downloads 306

Authors: Thein Thein, Kalyar Myo San

Abstract:

Lip reading system is one of the different supportive technologies for hearing impaired, or elderly people or non-native speakers. For normal hearing persons in noisy environments or in conditions where the audio signal is not available, lip reading techniques can be used to increase their understanding of spoken language. Hearing impaired persons have used lip reading techniques as important tools to find out what was said by other people without hearing voice. Thus, visual speech information is important and become active research area. Using visual information from lip movements can improve the accuracy and robustness of a speech recognition system and the need for lip reading system is ever increasing for every language. However, the recognition of lip movement is a difficult task because of the region of interest (ROI) is nonlinear and noisy. Therefore, this paper proposes method to detect the accurate lips shape and to localize lip movement towards automatic lip tracking by using the combination of Otsu global thresholding technique and Moore Neighborhood Tracing Algorithm. Proposed method shows how accurate lip localization and tracking which is useful for speech recognition. In this work of study and experiments will be carried out the automatic lip localizing the lip shape for Myanmar consonants using the only visual information from lip movements which is useful for visual speech of Myanmar languages.

Keywords: lip reading, lip localization, lip tracking, Moore neighborhood tracing algorithm

Procedia PDF Downloads 352

Authors: Krishna Mohan Bathula, Fatou Bintou Loucoubar, FNU Kaleemunnisa, Christelle Scharff, Mark Anthony De Castro

Abstract:

Voice recognition algorithms such as automatic speech recognition and text-to-speech systems with African languages can play an important role in bridging the digital divide of Artificial Intelligence in Africa, contributing to the establishment of a fully inclusive information society. This paper proposes a Deep Learning model that can classify the user responses as inputs for an interactive voice response system. A dataset with Wolof language words ‘yes’ and ‘no’ is collected as audio recordings. A two stage Data Augmentation approach is adopted for enhancing the dataset size required by the deep neural network. Data preprocessing and feature engineering with Mel-Frequency Cepstral Coefficients are implemented. Convolutional Neural Networks (CNNs) have proven to be very powerful in image classification and are promising for audio processing when sounds are transformed into spectra. For performing voice response classification, the recordings are transformed into sound frequency feature spectra and then applied image classification methodology using a deep CNN model. The inference model of this trained and reusable Wolof voice response recognition system can be integrated with many applications associated with both web and mobile platforms.

Keywords: automatic speech recognition, interactive voice response, voice response recognition, wolof word classification

Procedia PDF Downloads 116

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 121

Authors: Aishwarya Ravindra Fursule, Shruti Kshirsagar

Abstract:

In the intersection of artificial intelligence and human-centered computing, this paper delves into speech emotion recognition (SER). It presents a comparative analysis of machine learning models such as K-Nearest Neighbors (KNN),logistic regression, support vector machines (SVM), decision trees, ensemble classifiers, and random forests, applied to SER. The research employs four datasets: Crema D, SAVEE, TESS, and RAVDESS. It focuses on extracting salient audio signal features like Zero Crossing Rate (ZCR), Chroma_stft, Mel Frequency Cepstral Coefficients (MFCC), root mean square (RMS) value, and MelSpectogram. These features are used to train and evaluate the models’ ability to recognize eight types of emotions from speech: happy, sad, neutral, angry, calm, disgust, fear, and surprise. Among the models, the Random Forest algorithm demonstrated superior performance, achieving approximately 79% accuracy. This suggests its suitability for SER within the parameters of this study. The research contributes to SER by showcasing the effectiveness of various machine learning algorithms and feature extraction techniques. The findings hold promise for the development of more precise emotion recognition systems in the future. This abstract provides a succinct overview of the paper’s content, methods, and results.

Keywords: comparison, ML classifiers, KNN, decision tree, SVM, random forest, logistic regression, ensemble classifiers

Procedia PDF Downloads 45

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 136

Authors: Sanja Seljan, Ivan Dunđer

Abstract:

The paper presents combined automatic speech recognition (ASR) for English and machine translation (MT) for English and Croatian in the domain of business correspondence. The first part presents results of training the ASR commercial system on two English data sets, enriched by error analysis. The second part presents results of machine translation performed by online tool Google Translate for English and Croatian and Croatian-English language pairs. Human evaluation in terms of usability is conducted and internal consistency calculated by Cronbach's alpha coefficient, enriched by error analysis. Automatic evaluation is performed by WER (Word Error Rate) and PER (Position-independent word Error Rate) metrics, followed by investigation of Pearson’s correlation with human evaluation.

Keywords: automatic machine translation, integrated language technologies, quality evaluation, speech recognition

Procedia PDF Downloads 484

Authors: Xiang Shijie, Zhou Dong, Tian Dan

Abstract:

Speaker recognition is a crucial task in the field of speech processing, aimed at identifying individuals based on their vocal characteristics. However, existing speaker recognition methods face numerous challenges. Traditional methods primarily rely on audio signals, which often suffer from limitations in noisy environments, variations in speaking style, and insufficient sample sizes. Additionally, relying solely on audio features can sometimes fail to capture the unique identity of the speaker comprehensively, impacting recognition accuracy. To address these issues, we propose a multi-modal network architecture that simultaneously processes both audio and text signals. By gradually integrating audio and text features, we leverage the strengths of both modalities to enhance the robustness and accuracy of speaker recognition. Our experiments demonstrate significant improvements with this multi-modal approach, particularly in complex environments, where recognition performance has been notably enhanced. Our research not only highlights the limitations of current speaker recognition methods but also showcases the effectiveness of multi-modal fusion techniques in overcoming these limitations, providing valuable insights for future research.

Keywords: feature fusion, memory network, multimodal input, speaker recognition

Procedia PDF Downloads 32

Authors: Prasad Kalagura, B. Veeresh kumar

Abstract:

We constructed an interface system that would allow a similarly paralyzed user to interact with a computer with almost full functional capability. A real-time tracking algorithm is implemented based on adaptive skin detection and motion analysis. The clicking of the mouse is activated by the user's eye blinking through a sensor. The keyboard function is implemented by voice recognition kit.

Keywords: embedded ARM7 processor, mouse pointer control, voice recognition

Procedia PDF Downloads 578

Authors: Babatunde Olumide Olawale, Oyebode Olumide Oyediran

Abstract:

The security safe is a place or building where classified document and precious items are kept. To prevent unauthorised persons from gaining access to this safe a lot of technologies had been used. But frequent reports of an unauthorised person gaining access into security safes with the aim of removing document and items from the safes are pointers to the fact that there is still security gap in the recent technologies used as access control for the security safe. In this paper we try to solve this problem by developing a multimodal biometric system for physical access control into a security safe using face and voice recognition. The safe is accessed by the combination of face and speech pattern recognition and also in that sequential order. User authentication is achieved through the use of camera/sensor unit and a microphone unit both attached to the door of the safe. The user face was captured by the camera/sensor while the speech was captured by the use of the microphone unit. The Scale Invariance Feature Transform (SIFT) algorithm was used to train images to form templates for the face recognition system while the Mel-Frequency Cepitral Coefficients (MFCC) algorithm was used to train the speech recognition system to recognise authorise user’s speech. Both algorithms were hosted in two separate web based servers and for automatic analysis of our work; our developed system was simulated in a MATLAB environment. The results obtained shows that the developed system was able to give access to authorise users while declining unauthorised person access to the security safe.

Keywords: access control, multimodal biometrics, pattern recognition, security safe

Procedia PDF Downloads 335

Authors: Rita Chattopadhyay, Vivek Anand Thoutam

Abstract:

Speech is the most acceptable means of communication where we can quickly exchange our feelings and thoughts. Quite often, people can communicate orally but cannot interact or work with computers or devices. It’s easy and quick to give speech commands than typing commands to computers. In the same way, it’s easy listening to audio played from a device than extract output from computers or devices. Especially with Robotics being an emerging market with applications in warehouses, the hospitality industry, consumer electronics, assistive technology, etc., speech-based human-machine interaction is emerging as a lucrative feature for robot manufacturers. Considering this factor, the objective of this paper is to design the “Audio-Visual Co-Data Processing Pipeline.” This pipeline is an integrated version of Automatic speech recognition, a Natural language model for text understanding, object detection, and text-to-speech modules. There are many Deep Learning models for each type of the modules mentioned above, but OpenVINO Model Zoo models are used because the OpenVINO toolkit covers both computer vision and non-computer vision workloads across Intel hardware and maximizes performance, and accelerates application development. A speech command is given as input that has information about target objects to be detected and start and end times to extract the required interval from the video. Speech is converted to text using the Automatic speech recognition QuartzNet model. The summary is extracted from text using a natural language model Generative Pre-Trained Transformer-3 (GPT-3). Based on the summary, essential frames from the video are extracted, and the You Only Look Once (YOLO) object detection model detects You Only Look Once (YOLO) objects on these extracted frames. Frame numbers that have target objects (specified objects in the speech command) are saved as text. Finally, this text (frame numbers) is converted to speech using text to speech model and will be played from the device. This project is developed for 80 You Only Look Once (YOLO) labels, and the user can extract frames based on only one or two target labels. This pipeline can be extended for more than two target labels easily by making appropriate changes in the object detection module. This project is developed for four different speech command formats by including sample examples in the prompt used by Generative Pre-Trained Transformer-3 (GPT-3) model. Based on user preference, one can come up with a new speech command format by including some examples of the respective format in the prompt used by the Generative Pre-Trained Transformer-3 (GPT-3) model. This pipeline can be used in many projects like human-machine interface, human-robot interaction, and surveillance through speech commands. All object detection projects can be upgraded using this pipeline so that one can give speech commands and output is played from the device.

Keywords: OpenVINO, automatic speech recognition, natural language processing, object detection, text to speech

Procedia PDF Downloads 80

Authors: Yishu Gong, Liangliang Yang, Jianyu Zhang, Zhengyu Chen, Sihong He, Xusheng Zhang, Wei Zhang

Abstract:

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that affects millions of people worldwide and is characterized by cognitive decline and behavioral changes. People living with Alzheimer’s disease often find it hard to complete routine tasks. However, there are limited objective assessments that aim to quantify the difficulty of certain tasks for AD patients compared to non-AD people. In this study, we propose to use speech emotion recognition (SER), especially the frustration level, as a potential biomarker for quantifying the difficulty patients experience when describing a picture. We build an SER model using data from the IEMOCAP dataset and apply the model to the DementiaBank data to detect the AD/non-AD group difference and perform longitudinal analysis to track the AD disease progression. Our results show that the frustration level detected from the SER model can possibly be used as a cost-effective tool for objective tracking of AD progression in addition to the Mini-Mental State Examination (MMSE) score.

Keywords: Alzheimer’s disease, speech emotion recognition, longitudinal biomarker, machine learning

Procedia PDF Downloads 113

Authors: Hajer Rahali, Zied Hajaiej, Noureddine Ellouze

Abstract:

The goal of speech parameterization is to extract the relevant information about what is being spoken from the audio signal. In speech recognition systems Mel-Frequency Cepstral Coefficients (MFCC) and Relative Spectral Mel-Frequency Cepstral Coefficients (RASTA-MFCC) are the two main techniques used. It will be shown in this paper that it presents some modifications to the original MFCC method. In our work the effectiveness of proposed changes to MFCC called Modified Function Cepstral Coefficients (MODFCC) were tested and compared against the original MFCC and RASTA-MFCC features. The prosodic features such as jitter and shimmer are added to baseline spectral features. The above-mentioned techniques were tested with impulsive signals under various noisy conditions within AURORA databases.

Keywords: auditory filter, impulsive noise, MFCC, prosodic features, RASTA filter

Procedia PDF Downloads 425

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

Abstract:

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

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

Procedia PDF Downloads 106

Authors: Punnoose A. K.

Abstract:

This paper presents an approach for identifying noisy speech recording using a multi-layer perception (MLP) trained to predict phonemes from acoustic features. Characteristics of the MLP posteriors are explored for clean speech and noisy speech at the frame level. Appropriate density functions are used to fit the softmax probability of the clean and noisy speech. A function that takes into account the ratio of the softmax probability density of noisy speech to clean speech is formulated. These phoneme independent scoring is weighted using a phoneme-specific weightage to make the scoring more robust. Simple thresholding is used to identify the noisy speech recording from the clean speech recordings. The approach is benchmarked on standard databases, with a focus on precision.

Keywords: noisy speech identification, speech pre-processing, noise robustness, feature engineering

Procedia PDF Downloads 127

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 499

Authors: Mahgfirah Firdaus Soberatta

Abstract:

Language cannot be separated from human life. Humans use language to convey ideas, thoughts, and feelings. We can use words for different things for example like asserted, advising, promise, give opinions, hopes, etc. Propaganda is an attempt which seeks to obtain stable behavior to adopt everyone to his everyday life. It also controls the thoughts and attitudes of individuals in social settings permanent. In this research, the writer will discuss about the speech act in a propaganda speech delivered by Martin Luther King Jr. in Washington at Lincoln Memorial on August 28, 1963. 'I Have a Dream' is a public speech delivered by American civil rights activist MLK, he calls from an end to racism in USA. In this research, the writer uses Searle theory to analyze the types of illocutionary speech act that used by Martin Luther King Jr. in his propaganda speech. In this research, the writer uses a qualitative method described in descriptive, because the research wants to describe and explain the types of illocutionary speech acts used by Martin Luther King Jr. in his propaganda speech. The findings indicate that there are five types of speech acts in Martin Luther King Jr. speech. MLK also used direct speech and indirect speech in his propaganda speech. However, direct speech is the dominant speech act that MLK used in his propaganda speech. It is hoped that this research is useful for the readers to enrich their knowledge in a particular field of pragmatic speech acts.

Keywords: speech act, propaganda, Martin Luther King Jr., speech

Procedia PDF Downloads 441

Authors: Kaleem Kashif, Tayyaba Anam, Yizhi Wu

Abstract:

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

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

Procedia PDF Downloads 63

Authors: Gheida J. Shahrour, Martin J. Russell

Abstract:

The 3D body movement signals captured during human-human conversation include clues not only to the content of people’s communication but also to their culture and personality. This paper is concerned with automatic extraction of this information from body movement signals. For the purpose of this research, we collected a novel corpus from 27 subjects, arranged them into groups according to their culture. We arranged each group into pairs and each pair communicated with each other about different topics. A state-of-art recognition system is applied to the problems of person, culture, and topic recognition. We borrowed modeling, classification, and normalization techniques from speech recognition. We used Gaussian Mixture Modeling (GMM) as the main technique for building our three systems, obtaining 77.78%, 55.47%, and 39.06% from the person, culture, and topic recognition systems respectively. In addition, we combined the above GMM systems with Support Vector Machines (SVM) to obtain 85.42%, 62.50%, and 40.63% accuracy for person, culture, and topic recognition respectively. Although direct comparison among these three recognition systems is difficult, it seems that our person recognition system performs best for both GMM and GMM-SVM, suggesting that inter-subject differences (i.e. subject’s personality traits) are a major source of variation. When removing these traits from culture and topic recognition systems using the Nuisance Attribute Projection (NAP) and the Intersession Variability Compensation (ISVC) techniques, we obtained 73.44% and 46.09% accuracy from culture and topic recognition systems respectively.

Keywords: person recognition, topic recognition, culture recognition, 3D body movement signals, variability compensation

Procedia PDF Downloads 541

Authors: Elizabeth Howarth, Dawn Green, Sean Connolly, Geena Vabulas, Sara Smolley

Abstract:

Through the EU Horizon 2020 Nuvoic Project, the project team recruited 70 individuals in the UK and Ireland to test the Voiceitt speech recognition app and provide user feedback to developers. The app is designed for people with dysarthric speech, to support communication with unfamiliar people and access to speech-driven technologies such as smart home equipment and smart assistants. Participants with atypical speech, due to a range of conditions such as cerebral palsy, acquired brain injury, Down syndrome, stroke and hearing impairment, were recruited, primarily through organisations supporting disabled people. Most had physical or learning disabilities in addition to dysarthric speech. The project team worked with individuals, their families and local support teams, to provide access to the app, including through additional assistive technologies where needed. Testing was user-led, with participants asked to identify and test use cases most relevant to their daily lives over a period of three months or more. Ongoing technical support and training were provided remotely and in-person throughout the testing period. Structured interviews were used to collect feedback on users' experiences, with delivery adapted to individuals' needs and preferences. Informal feedback was collected through ongoing contact between participants, their families and support teams and the project team. Focus groups were held to collect feedback on specific design proposals. User feedback shared with developers has led to improvements to the user interface and functionality, including faster voice training, simplified navigation, the introduction of gamification elements and of switch access as an alternative to touchscreen access, with other feature requests from users still in development. This work offers a case-study in successful and inclusive co-design with the disabled community.

Keywords: co-design, assistive technology, dysarthria, inclusive speech recognition

Procedia PDF Downloads 110

Authors: Surbhi Mathur, J. M. Vyas

Abstract:

Although the rapid development of forensic speaker recognition technology has been conducted, there are still many problems to be solved. The biggest problem arises when the cases involving disguised voice samples come across for the purpose of examination and identification. Such type of voice samples of anonymous callers is frequently encountered in crimes involving kidnapping, blackmailing, hoax extortion and many more, where the speaker makes a deliberate effort to manipulate their natural voice in order to conceal their identity due to the fear of being caught. Voice disguise causes serious damage to the natural vocal parameters of the speakers and thus complicates the process of identification. The sole objective of this doctoral project is to find out the possibility of rendering definite opinions in cases involving disguised speech by experimentally determining the effects of different disguise forms on personal identification and percentage rate of speaker recognition for various voice disguise techniques such as raised pitch, lower pitch, increased nasality, covering the mouth, constricting tract, obstacle in mouth etc by analyzing and comparing the amount of phonetic and acoustic variation in of artificial (disguised) and natural sample of an individual, by auditory as well as spectrographic analysis.

Keywords: forensic, speaker recognition, voice, speech, disguise, identification

Procedia PDF Downloads 368

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 154

Authors: Nassib Abdallah, Pierre Chauvet, Abd El Salam Hajjar, Bassam Daya

Abstract:

In this paper, we propose an optimized brain computer interface (BCI) system for unspoken speech recognition, based on the fact that the constructions of unspoken words rely strongly on the Wernicke area, situated in the temporal lobe. Our BCI system has four modules: (i) the EEG Acquisition module based on a non-invasive headset with 14 electrodes; (ii) the Preprocessing module to remove noise and artifacts, using the Common Average Reference method; (iii) the Features Extraction module, using Wavelet Packet Transform (WPT); (iv) the Classification module based on a one-hidden layer artificial neural network. The present study consists of comparing the recognition accuracy of 5 Arabic words, when using all the headset electrodes or only the 4 electrodes situated near the Wernicke area, as well as the selection effect of the subbands produced by the WPT module. After applying the articial neural network on the produced database, we obtain, on the test dataset, an accuracy of 83.4% with all the electrodes and all the subbands of 8 levels of the WPT decomposition. However, by using only the 4 electrodes near Wernicke Area and the 6 middle subbands of the WPT, we obtain a high reduction of the dataset size, equal to approximately 19% of the total dataset, with 67.5% of accuracy rate. This reduction appears particularly important to improve the design of a low cost and simple to use BCI, trained for several words.

Keywords: brain-computer interface, speech recognition, artificial neural network, electroencephalography, EEG, wernicke area

Procedia PDF Downloads 271