Speech Processing

This review examines how researchers have approached speech errors across a wide range of studies, drawing on work from databases such as Scopus, Web of Science, and Google Scholar. Rather than beginning with fixed categories, patterns were allowed to emerge gradually through close engagement with the literature. The analysis brought to light six recurring themes: (1) speech errors are explainable, often reflecting identifiable processes; (2) they are traceable and identifiable across different contexts; (3) they are largely unavoidable, yet speakers frequently manage to repair them in interaction; (4) they serve as valuable evidence for understanding how language functions in real-time; (5) they are consistently interpreted through established theoretical frameworks; and (6) they have remained a subject of continued interest, with recent studies revisiting and extending earlier insights. Taken together, these themes point to speech errors as systematic, shaped by cognitive processes, and far from random or trivial. Beyond showing how language is processed and produced, they offer practical insights, particularly for English Language Teaching (ELT). At the same time, the review highlights areas where further research is needed, especially on lesser-studied languages, multilingual contexts, and the potential of emerging technologies for speech analysis. By bringing these strands together, the review offers a more connected view of speech errors and their relevance to language education, psycholinguistics, and communication studies.

This paper presents a method for extracting MFCC parameters from a normalised power spectrum density. The underlined spectral normalisation method is based on the fact that the speech regions with less energy need more robustness, since in these regions the noise is more dominant, thus the speech is more corrupted. Less energy speech regions contain usually sounds of unvoiced nature where are included nearly half of the consonants, and are by nature the least reliable ones due to the effective noise presence even when the speech is acquired under controlled conditions. This spectral normalisation was tested under additive artificial white noise in an Isolated Speech Recogniser and showed very promising results . It is well known that concerned to speech representation, MFCC parameters appear to be more effective than power spectrum based features. This paper shows how the cepstral speech representation can take advantage of the abovereferred spectral normalisation and shows some results in the continuous speech recognition paradigm in clean and artificial noise conditions.

Normally, voice activity detection (VAD) refers to speech processing algorithms for detecting the presence or absence of human speech in segments of audio signals. In this paper, however, we focus on speech detection algorithms that take VoIP traffic instead of audio signals as input. We call this category of algorithms network-level VAD. Traditional VAD usually plays a fundamental role in speech processing systems because of its ability to delimit speech segments. Network-level VAD, on the other hand, can be quite helpful in network management, which is the motivation for our study. We propose the first real-time network-level VAD algorithm that can extract voice activity from encrypted and non-silence-suppressed Skype traffic. We evaluate the speech detection accuracy of the proposed algorithm with extensive reallife traces. The results show that our scheme achieve reasonably good performance even high degree of randomness has been injected into the network traffic.

Recent developments in large vocabulary continuous speech recognition (LVCSR) have shown the effectiveness of discriminative training approaches, employing the following three representative techniques: discriminative Gaussian training using the minimum phone error (MPE) criterion, discriminately trained features estimated by multilayer perceptrons (MLPs); and discriminative feature transforms such as feature-level MPE (fMPE). Although MLP features, MPE models, and fMPE transforms have each been shown to improve recognition accuracy, no previous work has applied all three in a single LVCSR system. This paper uses a state-of-the-art Mandarin recognition system as a platform to study the interaction of all three techniques. Experiments in the broadcast news and broadcast conversation domains show that the contribution of each technique is nonredundant, and that the full combination yields the best performance and has good domain generalization.

A lower-error and lower-variance n X ?Z multiplier is suitably proposed for VLSI design. Considering next lower significant stage in P,-' column and useful error-compensation model in the least significant part, and utilizing a near optimized index to classify the error terms are our strategies in order to achieve lower error and variance as compared with previously proposed structure in the subproduct-array of Baugh-Wooley algorithm. This novel structure applied to the fixed-width lowpass digital FIR filter for speech signal processing system has excellent performance in reducing maximum error, average error, and variation of errors as shown in given tables and figures.

Given the importance of speech in our day-to-day activities and almost all forms of communication, it is crucial to address issues that hinder effective communication. Often, in critical security and military applications, the intelligibility of speech is of higher importance than the quality. In such cases, it is crucial that the speech utterance is comprehended for the exact message it was meant to convey, while the pleasantness of the speech and how good it sounds assumes secondary importance. In cases where noise degrades speech intelligibility, it is vital to develop measures that allow speech utterances to retain their intelligibility despite the ambient noise. When modified in a certain way, the intelligibility is improved over the original voice in the presence of noise. This is known as the Lombard effect. Of the several techniques to achieve Lombard speech, one effective approach is formant shifting, where the formant frequencies are relocated to regions in the spectrum where the noise cannot mask the phonetic information they contain. This shift was guided by a trapezoidal voice transformation function (TVTF) that mapped the original locations of formant frequencies in the spectrum to new locations. However, when done empirically, formant shifting results in artifacts.

{Hence, the objective of this thesis is to ascertain techniques to optimize such shifts in formants in order to maximize the boost in intelligibility in a near-end noisy environment. Such optimization should encompass factors like the language being spoken, the presence of realistic noises that are frequently encountered, as well as variation in noise intensities in terms of signal SNR.} {To that end, as the first contribution of this thesis}, we propose optimizing the shaping parameters of the TVTF via a genetic optimization technique called comprehensive learning particle swarm optimization (CLPSO). {Such optimization was specific to a certain combination of language, noise type, and SNR level. Next}, we propose a joint enhancement scheme where we combine several voice modification techniques with formant shifting to preserve speech quality while boosting intelligibility. These include time-scale modification, energy redistribution, and smoothing of formant contours. Although the performance increased, the optimization, which was already computationally intensive, took even longer to converge due to the increased dimension of the input vector corresponding to the additional techniques used in Lombard speech generation. To address this, {as yet another contribution,} a statistical configuration of the VTF is proposed - the Gaussian voice transformation function (GVTF), which had just three parameters to be optimized (instead of five in the TVTF). This reduced the convergence time and resulted in a smoother contour of the shifted formants across the frames.

In case of changes in the ambient conditions of SNR levels, language, and/or noise type, {our contributions focus on the proposition of} transfer learning on all environmental factors like SNR, languages, and noise types. The transfer learning across SNR levels was achieved through a Gaussian process regression, where the known VTF parameters at some SNR levels were used to estimate the unknown parameters for other SNR levels. In case of a change in the language, the comparative analysis of pitch and formant frequencies between the source and target languages was used to modify the shaping parameters of the VTF to conform to the target language. However, the transfer across noises was only made possible through GVTF. This is handled through comparative analysis of the Gaussian approximations of the noise magnitude spectra of the source and target noises. Finally, we establish a mechanism for combined transfer learning across languages and noises for dealing with cases where both those conditions change.

To demonstrate the efficacy of the proposed algorithms in real-time, the entire optimization cycle, using TVTF and GVTF, along with all transfer learning mechanisms, have all been built into an application user interface developed in the AppDesigner in MATLAB. As a practical application of the optimization used in this thesis, the importance of an optimal dataset generated through CLPSO has been demonstrated towards training a lightweight ANN on a resource-constrained Raspberry Pi to suggest optimal microphone location in a room relative to a speaker.

A novel technique based on dynamic stochastic resonance (DSR) in discrete cosine transform (DCT) domain has been proposed in this paper for the enhancement of dark as well as low-contrast images. In conventional DSR-based techniques, the performance of a system can be improved by addition of external noise. However, in the proposed DSR-based work, the intrinsic noise of an image has been utilized to create a noise-induced transition of a dark image to a state of good contrast. The proposed technique significantly enhances the image contrast and color information without losing any image or color data by optimization of bistable system parameters. The performance of the proposed methodology has been measured in terms of relative contrast enhancement factor, perceptual quality measure, and color enhancement factor. When compared with the existing enhancement techniques, such as adaptive histogram equalization, gamma correction, single-scale retinex, multi-scale retinex, modified high-...

In many functional magnetic resonance imaging (fMRI) studies blind humans were found to show cross-modal reorganization engaging the visual system in non-visual tasks. For example, blind people can manage to understand (synthetic) spoken language at very high speaking rates up to ca. 20 syllables/s (syl/s). FMRI data showed that hemodynamic activation within right-hemispheric primary visual cortex (V1), bilateral pulvinar (Pv), and left-hemispheric supplementary motor area (pre-SMA) covaried with their capability of ultra-fast speech (16 syllables/s) comprehension. It has been suggested that right V1 plays an important role with respect to the perception of ultra-fast speech features, particularly the detection of syllable onsets. Furthermore, left pre-SMA seems to be an interface between these syllabic representations and the frontal speech processing and working memory network. So far, little is known about the networks linking V1 to Pv, auditory cortex (A1), and (mesio-) frontal areas. Dynamic causal modeling (DCM) was applied to investigate (i) the input structure from A1 and Pv toward right V1 and (ii) output from right V1 and A1 to left pre-SMA. As concerns the input Pv was significantly connected to V1, in addition to A1, in blind participants, but not in sighted controls. Regarding the output V1 was significantly connected to pre-SMA in blind individuals, and the strength of V1-SMA connectivity correlated with the performance of ultra-fast speech comprehension. By contrast, in sighted controls, not understanding ultra-fast speech, pre-SMA did neither receive input from A1 nor V1. Taken together, right V1 might facilitate the "parsing" of the ultra-fast speech stream in blind subjects by receiving subcortical auditory input via the Pv (= secondary visual pathway) and transmitting this information toward contralateral pre-SMA.

This paper proposes an acoustic phonetic study of the foreign accents in the Arabic language. To analyze on a large scale of the connected variations, the contribution of the automatic tools acoustico-phonetic decoding tools along the adaptation forces. Based on the results of the uses of these tools, we managed to differentiate between three major forms of accents: The English language speaker accent (American and British population's accent), the European people accent (French speaker accent, German speaker accent) and the Persian speaker accent.

In this paper, we propose an emotion recognition system from speech signal using both spectral and prosodic features. Most traditional systems have focused on spectral features or prosodic features. Since both the spectral and the prosodic features contain emotion information, it is believed that combining spectral features and prosodic features will improve the performance of the emotion recognition system. Therefore, we propose to use both spectral and prosodic features. For spectral features, a GMM super vector based SVM is applied. For prosodic features, a set of prosodic features that are clearly correlated with speech emotional states and SVM is also used for emotion recognition. The combination of both spectral features and prosodic features is done and an SVM is trained using the combined feature vector. The emotion recognition accuracy of our experiments allow us to explain which features carry the most emotional information and why. It also allows us to develop criteria to...

Several techniques have been introduced over the years to mitigate the effect of howling sound production in sound reinforcement applications. The algorithmic computational complexity of the howling controllers directly affects their implementability on resource-constrained hardware platforms. This work introduces a computationally cheap acoustic howling control algorithm that requires a single multiplication operation for its implementation. The algorithm was modelled, simulated and tested using MATLAB® to obtain its performance metrics. Simulation results showed that the developed technique has average sound quality indices of 1.1746 and 1.2118 for speech and audio signals respectively. Also, for speech and audio signals, Maximum Stable Gain (MSG) Increase figures of 11.29 dB and 9.858 dB were obtained respectively. These results showed that, compared to the standard Adaptive Feedback Control (AFC) technique, the developed algorithm has comparable MSG Increase figures, negligibly small computational cost and low sound quality. This result implied that the howling controller can be easily implemented on a resource-constrained hardware platform at the expense of some degradation in sound quality.

This article presents a full end-to-end pipeline for Arabic Dialect Identification (ADI) using intonation patterns and acoustic representations. Recent approaches to language and dialect identification use linguistic-aware deep architectures that are able to capture phonetic differences amongst languages and dialects. Specifically, in ADI tasks, different combinations of linguistic features and acoustic representations have been successful with deep learning models. The approach presented in this article uses intonation patterns and hybrid residual and bidirectional LSTM networks to learn acoustic embeddings with no additional linguistic information. Results of the experiments show that intonation patterns for Arabic dialects provide sufficient information to achieve state-of-the-art results on the Var-Dial 17 ADI dataset, outperforming single-feature systems. The pipeline presented is robust to data sparsity, in contrast to other deep learning approaches that require large quantities of data. We conjecture on the importance of sufficient information as a criterion for optimality in a deep learning ADI task, and more generally, its application to acoustic modeling problems. Small intonation patterns, when sufficient in an information-theoretic sense, allow deep learning architectures to learn more accurate speech representations.

The autonomous vehicle market is experiencing significant growth, with indications of transitioning from the "trough of disillusionment" to the "slope of enlightenment" on the Gartner hype cycle chart. Fundamental technologies encompassing extensive data analytics, computational capabilities, and sensor fusion techniques have already been established, and all stakeholders in this industry are persistently exploring novel approaches to enhance the overall perception of end users in terms of safety and trustworthiness. In this context, this project aims to develop and implement an Environmental Sound Recognition (ESR) algorithm in an embedded system for deployment in autonomous vehicles for Smart Cities in 2025, targeting advanced functionalities for early warning systems. Due to hardware constraints, a regular passenger vehicle was used, embedding the ESR algorithm in a Raspberry Pi with a microphone array. The limited literature on ESR algorithms for vehicles primarily focuses on siren detection without real-time inferences, and to address this, a dataset benchmarking study confirmed classifiers’ accuracy, leading to the creation of a new dataset tailored to autonomous vehicles. This new dataset provided a comprehensive baseline where several classifiers were trained and evaluated for accuracy, memory usage, and prediction time, with CNN 2D using aggregated features emerging as the top-performing model, achieving an average accuracy of 80% in the sliding window process. During the indoor experiment, the total prediction time attained an average of 47.6 ms, validating the algorithm’s performance with weighted F1-scores close to or better than cross-validation results. In the final phase of the methodology, real-world tests conducted in a passenger vehicle yielded similar results. However, inconsistencies were observed in certain classes due to insufficient sample diversity and environmental noise, which affected their accuracy. The results of this project indicate that its general objective was successfully achieved, contributing to understanding of ESR algorithms in embedded systems within passenger vehicles, and it is ready for integration into the electric and electronic architecture of autonomous vehicles for Smart Cities. Additionally, upon conducting further experiments across various vehicle categories to assess cabin insulation effects, this project could potentially enhance safety features for drivers with hearing impairments by adapting the ESR algorithm as an add-on feature in regular passenger vehicles.

This paper investigates the performance of a selection of state-of-the-art array signal-processing techniques for the purpose of predicting the binaural listening experiments from the equalization and cancellation (EC) paper by Durlach written in 1963. Two different array signal-processing techniques are analyzed, 1) filter and sum beamforming (FS), and 2) minimum variance distortionless response (MVDR) beamforming. The theoretical properties of these beamformers for the specific situation of prediction of binaural masking level differences are analyzed in conjunction with the EC model. Also, the performance of the different beamformers on the data sets in the Durlach paper from 1963 is compared to the EC model.

This study delves into designing intelligent voice assistants through the implementation of opensource speech recognition algorithms. Developers can build AI-powered voice interfaces by utilizing technologies such as Whisper, DeepSpeech, and Kaldi, enabling them to process spoken language, understand user goals, and produce responses. Open-source options provide flexibility and cost-effectiveness, but difficulties persist in terms of accuracy disparities, background noise disturbances, and the computational requirements that accompany them. Protecting user privacy and preventing unauthorized access requires secure data handling practices. Improvements in deep learning, multilingual capabilities, and bespoke customization can improve speech recognition performance and user interaction. Implementing emotion-sensing artificial intelligence and contextual memory capabilities can enhance conversational flow and responsiveness. Responsible AI deployment necessitates the resolution of ethical concerns. Future studies should concentrate on refining AI models to improve real-time processing capabilities and enhance their comprehension of context. Continuous enhancements enable open-source voice assistants to serve as a viable alternative to proprietary systems. This research focuses on important methods, obstacles, and possible improvements in the creation of voice assistants.

In this paper a methodology for extraction of features in emotional speech recognition is presented. Different emotional states of a speaker produce physiological changes in the human speech system, which is reflected in the variation of voice parameters. Processing techniques applied in this work are: time-frequency representations, linear prediction and raw data.

Employing the methodology of Editorial Criticism, this article seeks to demonstrate that Book II of the Psalter (i.e., Psalms 42-72) consists of three parallel, compositional arcs that take the form of a journey. Based on keyword links, as well as clear organizational clues found in the superscriptions, the psalms of Book II are deliberately arranged to portray three parallel depictions of the same progression of events. Mirroring the general sequence of eschatological events portrayed in the prophets, Book II presents a threefold analogous deliverance out of exile into a global kingdom ruled by the Davidic king. While each journey highlights one compelling facet of that future kingdom, together they provide a multiperspectival and even complementary vision of the future which signals a renewed hope in the Davidic promises. Thus, this article will argue that the design of Book II of the Psalter does not extol the glorious days of a bygone era, but rather orients the reader to anticipate the ultimate eschatological fulfillment of what God had guaranteed in the future. The net effect of these compositional arcs (or journeys) for the readers would inevitably be to sustain them through the disorienting experiences of captivity and provide invincible hope for the age to come.

In numerous applications that rely on audible voice signals, including speech recognition, audio recording, and telecommunications, the suppression of background noise is an essential component. The present study introduces an innovative methodology for mitigating noise in audio transmission by employing digital signal processing. Preceding post-processing for refinement, it is necessary to estimate and reduce noise in the input speech signals. The successful implementation of the proposed approach requires this. The proposed method incorporates spectral shaping as a post-processing step. Noise estimation is performed using minimal statistics, and spectrum analysis is executed via short-time Fourier transform. The studies' findings indicate that the intelligibility and audibility of communication in chaotic environments are significantly improved by the proposed method. Anthology-perceptual evaluation scores of voice quality, improved signalto-noise ratios, and decreased word error rates are some objective criteria utilized in quantitative evaluation. Furthermore, subjective hearing tests were employed to authenticate the exceptional quality of the speech signals that were processed. The method that was suggested has demonstrated encouraging outcomes, suggesting that it might be viable to improve the functionality of voice-reliant applications in real-world scenarios. The algorithm implementation is proposed for FPGA and DSP component specific UVM TB verification technique is modelled.

When the audio and visual portions of a speech stimulus are presented synchronously, the resulting enhancement in intelligibility is generally much larger than the one obtained when the audio and visual stimuli are presented sequentially. However, perfect synchronization is not required to obtain a substantial audiovisual (AV) benefit: many studies have shown that AV integration is maximum when the audio signal is slightly delayed relative to the visual signal, and other studies have shown that substantial AV ...

In any signal noise is an undesired quantity, however most of thetime every signal get mixed with noise at different levels of theirprocessing and application, due to which the information containedby the signal gets distorted and makes the whole signal redundant.A speech signal is very prominent with acoustical noises like bubblenoise, car noise, street noise etc. So for removing the noises researchershave developed various techniques which are called filtering. Basicallyall the filtering techniques are not suitable for every application,hence based on the type of application some techniques are betterthan the others. Broadly, the filtering techniques can be classifiedinto two categories i.e. linear filtering and non-linear filtering.In this paper a study is presented on some of the filtering techniqueswhich are based on linear and nonlinear approaches. These techniquesincludes different adaptive filtering based on algorithm like LMS,NLMS and RLS etc., Kalman filter, ARMA and NARMA...

Speech is a form of communication that most people came across in their day to day life. Speech can be used for many purposes like speech communication, speech recognition, speaker identification etc. In all of these applications a noise free speech signal is highly desired. Therefore to get a noise free speech, different speech processing and speech filtering techniques are used. In this paper we have presented a review on speech processing and different speech filtering techniques. The techniques that we have investigated in this paper are Adaptive filtering, Kalman Filtering, Neural Networks and adaptive neuro-fuzzy filtering and it is found that LMS gives good result in linear noise depending upon the order of the filter and hybrid filtering techniques like ANFIS because it gives the better result in case of non-stationary noise. Keywords: Adaptive Filter, noise cancellation, least mean square adaptive filter, Autoregressive, Kalman filter, neural network, Adaptive neuro-fuzzy f...

In recent years, the established link between the various human communication production domains has become more widely utilised in the field of speech processing. In this work, a state of the art Semi Adaptive Appearance Model (SAAM) approach developed by the authors is used for automatic lip tracking, and an adapted version of our vowel based speech segmentation system is employed to automatically segment speech. Canonical Correlation Analysis (CCA) on segmented and non segmented data in a range of noisy speech environments finds that segmented speech has a significantly better audiovisual correlation, demonstrating the feasibility of our techniques for further development as part of a proposed audiovisual speech enhancement system.

To automate assessments of beginning readers, especially those still learning English, we have investigated the types of knowledge sources that teachers use and have tried to incorporate them into an automated system. We describe a set of speech recognition and verification experiments and compare teacher scores with automatic scores in order to decide when a novel pronunciation is best viewed as a reading error or as dialect variation. Since no one classroom teacher is expected to be familiar with as many dialect systems as might occur in an urban classroom, making progress in automated assessments in this area can improve the consistency and fairness of reading assessment. We found that automatic methods performed best when the acoustic models were trained on both native and non-native speech, and argue that this training condition is necessary for automatic reading assessment since a child's reading ability is not directly observable in one utterance. We also found assessment of emerging reading skills in young children to be an area ripe for more research!

Recent advancements in self-supervised speech-representation learning for automatic speech recognition (ASR) approaches have significantly improved the results on many benchmarks with low-cost data labeling. In this paper, we train two self-supervised frameworks for ASR, namely wav2vec, and data2vec, in which we conduct multiple experiments and analyze their results. Furthermore, we introduce Aswat dataset, which covers multiple genres and features speakers with vocal variety. Aswat contains 732 hours of clean Arabic speech that can be used in the pretraining task for learning latent speech representations, which results in achieving a lower word error rate (WER) in Arabic ASR. We report the baseline results and achieve state-ofthe-art WERs of 11.7% and 10.3% on Common Voice (CV) and the second round of Multi-Genre Broadcast (MGB-2) respectively, as a result of including our dataset Aswat.

Listening to speech in noise depletes cognitive resources, affecting speech processing. The present study investigated how remaining resources or cognitive spare capacity (CSC) can be deployed by young adults with normal hearing. We administered a test of CSC (CSCT; along with a battery of established cognitive tests to 20 participants with normal hearing. In the CSCT, lists of two-digit numbers were presented with and without visual cues in quiet, as well as in steady-state and speechlike noise at a high intelligibility level. In low load conditions, two numbers were recalled according to instructions inducing executive processing (updating, inhibition) and in high load conditions the participants were additionally instructed to recall one extra number, which was the always the first item in the list. In line with previous findings, results showed that CSC was sensitive to memory load and executive function but generally not related to working memory capacity (WMC). Furthermore, CSCT scores in quiet were lowered by visual cues, probably due to distraction. In steady-state noise, the presence of visual cues improved CSCT scores, probably by enabling better encoding. Contrary to our expectation, CSCT performance was disrupted more in steady-state than speechlike noise, although only without visual cues, possibly because selective attention could be used to ignore the speech-like background and provide an enriched representation of target items in working memory similar to that obtained in quiet. This interpretation is supported by a consistent association between CSCT scores and updating skills.

The articulatory phonology study requires the simultaneous recording of the speech wave and as many articulatory parameters as possible. To this end, for many years,we have developed the integrated PHONART workstation for speech production analysis with the technologies available at the time. It consisted of a PC-compatible computer-driven workstation designed to record and process acoustic speech signals in relation to the corresponding physiological signals. These signals are obtained from various sources (flow-rate transducers, pressure transducers, position and movement gauges, electrodes, microphones, laryngophones, etc.). The parameters recorded with the PHONART system can be edited and processed with a new version of the PHONEDIT software. It is a signal editor that permits to edit, labelize and analyze various types of physiological signals i n relation with the speech signal.

A codec for wideband 12kHz speech and audio in a video conferencing application is proposed in this paper. The codec is based on warped linear predictive coding algorithm which utilizes the auditory Bark frequency resolution. The structure of the codec is described and the main issues on the real-time implementation are discussed. The codec is integrated to a video conferencing product which is a video codec PC-board. The algorithm is implemented in a Texas TMSC31 digital signal processor.

Frequency-warped signal processing techniques are attractive to many wideband speech and audio applications since they have a clear connection to the frequency resolution of human hearing. A warped version of linear predictive coding (LPC) is studied in this paper. The performance of conventional and warped LPC algorithms are compared in a simulated coding system using listening tests and conventional technical measures. The results indicate that the use of warped techniques is beneficial especially in wideband coding and may result in savings of one bit per sample compared to the conventional algorithm while retaining the same subjective quality.

The electromagnetic articulography (EMA) is a relatively exact and efficient method used in study on speech production physiology. It allows to precisely estimate movement trajectories of speech articulators like tongue, lips, jaw etc. by tracking position of sensors fixed to the articulators. This paper presents results of EMA research on Polish oral and nasalised vowels in orthography represented by the graphemes , , <ę>, <ą>. Inter-individual variability of tongue and lips position in X-axis direction during realization of the same phoneme has been estimated. Differences between oral and nasalised vowels in terms of movement of articulators in X-axis direction have been assessed too.

Speech recognition refers to the capability of software or hardware to receive a speech signal, identify the speaker’s features in the speech signal, and recognize the speaker thereafter. In general, the speech recognition process involves three main steps: acoustic processing, feature extraction, and classification/recognition. The purpose of feature extraction is to illustrate a speech signal using a predetermined number of signal components. This is because all information in the acoustic signal is excessively cumbersome to handle, and some information is irrelevant in the identification task. This study proposes a machine learning-based approach that performs feature parameter extraction from speech signals to improve the performance of speech recognition applications in real-time smart city environments. Moreover, the principle of mapping a block of main memory to the cache is used efficiently to reduce computing time. The block size of cache memory is a parameter that strongly...

It is argued in this article that the common interpretation of Ps 1 as a call for obedience, a view exemplified by Walter Brueggemann's influential article, "Bounded by Obedience and Praise: The Psalms as Canon," does not quite capture the emphasis of the text. While it is true that Ps 1 affirms the lifestyle of the "righteous," righteousness is not limited to or equated with "obedience." The psalm points to the affections rather than to behaviour as the key element of the righteous person-"his delight is in the Torah of Yahweh" (Ps 1:2). Instead of calling for obedience to the Torah, Ps 1 evokes affection for the Torah. This important move suggests that the study of biblical poetry in general and of the Psalms in particular can benefit from an approach that is attuned to the passions that are inherent in the text and the passions that are brought to the text by the interpreter.

In this work, handwritten word recognition problem is modeled in the framework of hidden Markov model (HMM). The states of HMM are identified with the letters of the alphabet. The optimum symbols are then generated by experimental study using fifteen different features. Both the first and second order HMM are used for the recognition task. Using the existing statistical knowledge of English, the calculation scheme for model probabilities are immensely simplified. Once the model is established, Viterbi algorithm is used to recognize the sequence of letters consisting the word. Very high recognition accuracy is obtained with the new scheme. Hidden Markov model (HMM) Feature selection Vector-quantizer Viterbi algorithm Hypothesis generation Pattern recognition Model probabilities 1. INTRODUCTION: OBJECTIVE AND SIGNIFICANCE

This paper investigates the effects of personality traits on listening-oriented dialogue to gain insight into building automated listening agents. The analysis of the frequency of dialogue act and the dialogue flow using Hidden Markov Models (HMMs) revealed that a dialogue becomes characteristically different depending on the personality traits of the listeners and the speakers, suggesting that automated listening agents must consider the personality traits of users to become good listeners.

Indicios de Percepción Binaural. Guillermo Jardon-2022 Resumen El siguiente artículo es una adaptación de los capítulos 1, 2 y 3 del libro Head Related Transfer Function and Acoustic Virtual Reality de Kazuhiro Iida (Springer; 2019) donde se explica el funcionamiento de la percepción binaural de los seres humanos.

Signal processing methods can improve the quality and intelligibility of oesophageal speech. Current methods show only moderate improvement leaving potential for better results. Quantifying parameters of oesophageal speech relative to laryngeal (normal) speech would help in the design of future enhancement methods for oesophageal speech. We quantified parameters of a source-filter model on a database of sustained vowels in Spanish from 4 oesophageal and 4 normal speakers. A ten-parameter glottal waveform model was used as the source and an autoregressive model was used as the filter. Classification, using a log-spectral distance measure, showed that all oesophageal speech samples were classified as whisper voice types; a voice type with a signal to noise ratio of -20 dB. Filter parameters representing spectral amplitudes and bandwidths had a large degree of variation for oesophageal speech comparative to the degree of variation for normal speech (Brown-Forsythe test, F < 0.001). Source metrics, noise to harmonic ratio (NHR) and variation in fundamental frequency, were also significantly greater for oesophageal speech (t-test, P < 0.001). These results show a greater degree of nonstationarity, and a noisier glottal waveform, for oesophageal speech comparative to normal speech.

Signal processing methods can improve the quality and intelligibility of oesophageal speech. Current methods show only moderate improvement leaving potential for better results. Quantifying parameters of oesophageal speech relative to laryngeal (normal) speech would help in the design of future enhancement methods for oesophageal speech. We quantified parameters of a source-filter model on a database of sustained vowels in Spanish from 4 oesophageal and 4 normal speakers. A ten-parameter glottal waveform model was used as the source and an autoregressive model was used as the filter. Classification, using a log-spectral distance measure, showed that all oesophageal speech samples were classified as whisper voice types; a voice type with a signal to noise ratio of -20 dB. Filter parameters representing spectral amplitudes and bandwidths had a large degree of variation for oesophageal speech comparative to the degree of variation for normal speech (Brown-Forsythe test, F < 0.001). Source metrics, noise to harmonic ratio (NHR) and variation in fundamental frequency, were also significantly greater for oesophageal speech (t-test, P < 0.001). These results show a greater degree of nonstationarity, and a noisier glottal waveform, for oesophageal speech comparative to normal speech.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

Artificial Intelligence hasn’t left a facet of life untouched. As it makes its mark in every step of an organization, its application in the field of Human Resource(HR) needs critical analysis. Recruitment is the backbone of a well-functioning organization. In this paper, we will be highlighting the various methods to perform applicant resume screening, automating the technical HR round, engaging, shortlisting and hiring. Automating this process allows an organization to focus on building and regulating policies. This paper highlights the cascading impact of the various AI frameworks used in the HR recruitment process giving a deeper insight into it.Mixed Reality approach is used to simulate the virtual environment, giving a realistic feel to the applicant. Keywords— Natural Language Processing, Artificial Intelligence, Neural Networks, Mixed Reality, Mixed Reality Architecture, Resume Screening, Automating Interview ,Virtual Reality, Immersive Environment

The adoption of electronics learning (e-learning) as a method of disseminating knowledge in the global educational system is growing at a rapid rate, and has created a shift in the knowledge acquisition methods from the conventional classrooms and tutors to the distributed e-learning technique that enables access to various learning resources much more conveniently and flexibly. However, notwithstanding the adaptive advantages of learner-centric contents of e-learning programmes, the distributed e-learning environment has unconsciously adopted few international languages as the languages of communication among the participants despite the various accents (mother language influence) among these participants. Adjusting to and accommodating these various accents has brought about the introduction of accents-based automatic speech recognition into the e-learning to resolve the effects of the accent differences. This paper reviews over 50 research papers to determine the development so far made in the design and implementation of accents-based automatic recognition models for the purpose of elearning between year 2001 and 2021. The analysis of the review shows that 50% of the models reviewed adopted English language, 46.50% adopted the major Chinese and Indian languages and 3.50% adopted Swedish language as the mode of communication. It is therefore discovered that majority of the ASR models are centred on the European, American and Asian accents, while unconsciously excluding the various accents peculiarities associated with the less technologically resourced continents.

The adoption of accent-based automatic speech recognition (ASR) to remove the limitations of accent variations among the e-learning participants from different accents background has been considered a milestone. Several accents-based speech recognition systems have been developed by researchers in America, Asia and Europe to promote accents independent e-learning participation, unfortunately, these systems are not designed to cater for the Africans English speakers' accents variation, particularly, that of the Nigerian major ethnic groups. This study developed an accent-based automatic speech recognition model for the three major Nigerian ethnic groups' English speakers. The study used sixty-five (65) speakers across the three major Nigerian ethnic groups as its dataset, twenty-five (25) speakers from Igbo ethnic group, twenty (20) from the Hausa ethnic group and twenty (20) from the Yoruba ethnic group with thirty-three (33) males and thirty-two (32) females across different professions. Mel-Frequency Cepstral Coefficients (MFCC) feature extraction algorithm was used for the data pre-processing to extract the audio features while ensemble Restricted Boltzmann Machine-Long Short Term Memory (RBM-LSTM) architecture was adopted for the data processing using python-based open-source platform (TensorFlow). The model was trained using an error back-propagation through time training technique. The model's performance was evaluated using word error rate (WER) and character error rate (CER) with recorded words accuracy rate of 34.027875 % for Hausa accent, 76.352568 % for Igbo Accent and 74.195622 % for Yoruba accent.

The fast development of multimedia computing has led to the demand of using digital speech and images. The manipulation, storage and transmission of speech and images in their raw form is very expensive, and significantly slows the transmission and make storage costly. Efficient speech and image compression solutions are becoming critical with the recent growth of data intensive, multimedia based applications. Many techniques are now available and much effort is being expended in determining the optimum compression technique. Recently compression techniques using Wavelet Transform (WT) have received great attention, because of their promising compression ratio, ability to analyze the temporal and spectral properties of speech and image signals and flexibility in representing non stationary signals like speech and images by taking into account human perception system. In this paper we describe the application of Discrete Wavelet Transform (DWT) for analysis, processing and compression of multimedia signals like speech and image. More specifically we explore the major issues concerning the wavelet based speech and image compression which include choosing optimal wavelet, decomposition levels and thresholding criteria. The simulation results prove the effectiveness of DWT based techniques in attaining an efficient compression ratio of 2.31 for speech and 2.67 for images, achieving higher signal to noise ratio (SNR), better peak signal to noise ratio (PSNR), while the retained signal energy is 99.9885% and the resulting signals are generally much smoother

The interaction of humans and robots has the potential to set new grounds in industrial applications as well as in service robotics because it combines the strengths of humans, such as flexibility and adaptability, and the strengths of robots, such as power and precision. However, for a successful interaction the safety of the human has to be guaranteed at all times. This goal can be reached by the use of specialised robot hardware but we argue that safety in human-robot interaction can also be done with regular industrial robots, if they are equipped with additional sensors to track the human's position and to analyse the human's verbal and non-verbal utterances, and if the software that is controlling the robot is especially designed towards safety in the interaction. For this reason, we propose three design principles for an increased safety in robot architectures and any other software component that controls a robot for human-robot interaction: robustness, fast reaction time, and context awareness. We present a robot architecture that is based on these principles and show approaches for speech processing, vision processing, and robot control that also follow these guidelines.

Variations of the basic string-alignment algorithm are commonly used for the detection and classification of speech-recognition errors. In this procedure, reference and system-output hypothesis speech transcriptions are first aligned using the string-alignment algorithm that is based on primitive edit operations. The edit operations needed to transform one transcription into the other are then tallied as speech-recognition errors. The algorithms normally detect approximately the same total number of errors; however, they can produce different error classifications. This paper investigates these differences and several criterion functions that can be used for the comparison and evaluation of the algorithms for the detection and classification of speech-recognition errors. The proposed criterion functions were used for the experimental evaluation of the standard algorithms that are implemented as part of the CUED HTK and the NIST SCTK, and were used for the detection and classification of phone-recognition errors from the TIMIT speech database.

Turkiy adabiyotning buyuk siymosi Alisher Navoiy butun hayoti, ijodi va kuch
– qudratlarini inson baxt saodati uchun kurashga bag’ishladi. Shoirning o‘lmas
asarlarida o‘zi yashagan zamon va muhitning barcha muhim masalalarini qamrab oldi,
insonparvarlik, haqparvarlik g‘oyalarini ilgari surdi. Birinchi Prezidentimiz I.A.
Karimov bu ulug‘ zot to‘g‘risida quydagi fikrlarni bejizga takrorlamagan: “O‘zbek
xalqi ma’naviy dunyosining shakllanishiga kuchli va samarali ta’sir ko‘rsatgan ulug‘
zotlardan biri –bu Alisher Navoiy bobomizmizdir. Biz uning mo‘’tabar nomi, ijodiy
merosining boqiyligi, badiiy dahosi zamon va makon chegaralarini bilmasligi haqida
doimo faxrlanib so‘z yuritamiz. Alisher Navoiy xalqimizning ongi va tafakkuri, badiiy
madaniyati tarixida butun bir davrni tashkil etadigan buyuk shaxs, milliy
adabiyotimizning tengsiz namoyondasi, millatning g‘ururi, sha’nu – sharafini dunyoga
tarannum qilgan o‘lmas so‘z san’tkoridir. Ta’bir joiz bo‘lsa, olamda turkiy va forsiy
tilda so‘zlovchi biron – bir inson yo‘qki, u Navoiyni bilmasa, u Navoiyni sevmasa,
Navoiyga sadoqat va e’tiqod bilan qaramasa. Agar bu ulug‘ zotni avliyo desak,
avliyolarning avliyosi, mutafakkir desak, mutafakkirlarning mutafakkiri, shoir desak,
shoirlarning sultonidir” 7