Digital Processing Of Speech Signals Research Articles

Improved Feature Parameter Extraction from Speech Signals Using Machine Learning Algorithm.

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 affects the cache performance. In particular, the implementation of such processes in real-time systems requires a high computation speed. Processing speed plays an important role in speech recognition in real-time systems. It requires the use of modern technologies and fast algorithms that increase the acceleration in extracting the feature parameters from speech signals. Problems with overclocking during the digital processing of speech signals have yet to be completely resolved. The experimental results demonstrate that the proposed method successfully extracts the signal features and achieves seamless classification performance compared to other conventional speech recognition algorithms.

Speech Enhancement Using Deep Learning Methods: A Review

Speech enhancement, which aims to recover the clean speech of the corrupted signal, plays an important role in the digital speech signal processing. According to the type of degradation and noise in the speech signal, approaches to speech enhancement vary. Thus, the research topic remains challenging in practice, specifically when dealing with highly non-stationary noise and reverberation. Recent advance of deep learning technologies has provided great support for the progress in speech enhancement research field. Deep learning has been known to outperform the statistical model used in the conventional speech enhancement. Hence, it deserves a dedicated survey. In this review, we described the advantages and disadvantages of recent deep learning approaches. We also discussed challenges and trends of this field. From the reviewed works, we concluded that the trend of the deep learning architecture has shifted from the standard deep neural network (DNN) to convolutional neural network (CNN), which can efficiently learn temporal information of speech signal, and generative adversarial network (GAN), that utilize two networks training.

Method for Measuring the Indicator of Acoustic Quality of Audio Recordings Prepared for Registration and Processing in the Unified Biometric System

The problem of automated quality control of audio recordings containing voice samples of individuals is considered. It is shown that in solving this problem the most acute impediment is the problem of small samples of observations. To overcome the problem, a new, high-speed method of acoustic measurements is proposed, based on the principle of relative stability of the frequency of the fundamental tone of a speech signal within a voice sample of short duration. An example of practical implementation of the developed method according to a scheme with inter-period signal accumulation is considered. Using proprietary software, a full-scale experiment was conducted in which statistical estimates of the effectiveness of the method in noise conditions were obtained. It is shown that when using the proposed method, if the signal-to-noise ratio is lower than 15 dB, an audio recording is rejected with a probability of 0.95 or more as unsuitable for biometric identification of a person. The results obtained are intended for use in the development of new systems and modernization of existing systems and technologies for collection and automated quality control of biometric personal data. The article is intended for a wide circle of specialists in the field of acoustic measurements and digital processing of speech signals, as well as for practitioners who organize the work of authorized organizations in preparing samples of biometric personal data for registration with the unified biometric system (UBS).

Linear and nonlinear versions of Phase Retrieval

The problem of Phase Retrieval or Phaseless Recovery can be briefly stated as follows: for a given amplitude or measurements obtained using a redundant system of measuring vectors to restore the original signal. This problem first arose in X-ray crystallography at the beginning of the 20th century. A similar non-linear reconstruction problem arises in the digital processing of speech signals, especially in speech recognition problems. Some achievements in this direction will be shown with simple examples in spaces of small dimensions.

Measurements method of the audio recordings acoustic quality indicator prepared for registration and processing in the Unified Biometric System

We consider the task of automated quality control of sound recordings containing voice samples of individuals. It is shown that in this task the most acute is the small sample size. In order to overcome this problem, we propose the novel method of acoustic measurements based on relative stability of the pitch frequency within a voice sample of short duration. An example of its practical implementation using aninter-periodic accumulation of a speech signal is considered. An experimental study with specially developed software provides statistical estimates of the effectiveness of the proposed method in noisy environments. It is shown that this method rejects the audio recording as unsuitable for a voice biometric identification with a probability of 0,95 or more for a signal to noise ratio below 15 dB. The obtained results are intended for use in the development of new and modifying existing systems of collecting and automated quality control of biometric personal data. The article is intended for a wide range of specialists in the field of acoustic measurements and digital processing of speech signals, as well as for practitioners who organize the work of authorized organizations in preparing for registration samples of biometric personal data.

Узел цифровой обработки речевого сигнала, обеспечивающий криптографическую защиту интерфейса с блоком шифрования данных для устройства скрытной передачи закрытой информации

Узел цифровой обработки речевого сигнала, обеспечивающий криптографическую защиту интерфейса с блоком шифрования данных для устройства скрытной передачи закрытой информации

Exploiting nonlinearity of the speech production system for voice disorder assessment by recurrence quantification analysis.

This work summarizes the research related to digital speech signal processing with recurrence quantification analysis (RQA) applied to voice disorder assessment. The main motivation for these studies is the fact that RQA is able to exploit the nonlinear dynamical nature of the speech production system. Due to the use of recurrence quantification measures to represent the behavior of speech signals, promising results were obtained in the characterization and classification of laryngeal pathologies and voice disorders. These contributions may help one to evaluate the usability and efficiency of RQA in vocal disorder assessment.

A speech communication educational platform with high-capacity information hiding scheme

A novel educational platform for voice over Internet protocol speech communication is proposed in this paper with the aim of further presenting a course of digital speech signal processing. The proposed platform can transmit a speech signal while a secret message is simultaneously embedded in the transmitted encoded bits of this speech signal. Data hiding techniques usually consider two issues, embedding capacity and speech quality. Consequently, in order to achieve high embedding capacity and good speech quality, a data hiding scheme combining discrete cosine transform and voice activity detection algorithms is presented in this paper. This work has two major contributions. First, the embedding capacity of secret speech is increased by 95%, while maintaining good secret speech quality because the secret speech is firstly encoded before embedding into the cover (carrier) speech. Secondly, the characteristics of speech signals can be understood and the proposed information hiding technique for speech signals can be explored. The results of an imperceptibility evaluation indicated that the average perceptual evaluation of the speech quality score degraded slightly by 0.03 relative to that of the cover speech that had no hidden data. The experimental results showed that our proposed hiding scheme not only achieves imperceptibility but also provides a high data-embedding capacity at an average of 8252 bits per second. Objective and subjective evaluations verified that our proposed hiding scheme can achieve a large data-embedding capacity with imperceptible distortion in the stego-speech quality.

Classificação de disfonias por meio da análise de medidas não lineares e de quantificação de recorrência

In recent years techniques of digital processing of speech signals have been used as an auxiliary tool in the evaluation of vocal deviations, providing the patient with greater comfort low cost and objectivity when compared to the techniques traditionally employed, such as perceptual-auditory analysis. The evaluation of vocal quality, through acoustic analysis of voice signals, is becoming a very popular clinical practice for the detection of vocal disorders that in some cases can be caused by laryngeal lesions or vocal abuse. In this research, we used some traditional non-linear measures combined with measures of recurrence quantification for the discriminative analysis of vocal deviations, breathiness, roughness and strain. The characteristics of the non-linear dynamic analysis,used in the classification process, were the Reconstruction Step (τ), the First Minimum of the Mutual Information Function (PM) and the Correlation Dimension (D2). The quantification measures employed were: Determinism (Det), Shannon entropy (Entr), Mean length of diagonal lines (Lmed), Maximum length of vertical lines (Vmax) and Transitivity (Trans). Through these statistical tests, the potential of each characteristic to discriminate the types of voice signals was evaluated. In the classification process, the neural network MLP (Multilayer Perceptron) was used, with supervised learning algorithm Graded Conjugate Gradient (SCG). There was an average accuracy of 90% in the discrimination between healthy and deviant voices. In the classification between healthy and strained voices, an average accuracy of 76% was obtained with the combined measures Trans, τ , Vmax, Lmed, Det and D2. In the detection of the roughness deviation, an average accuracy of 89% was obtained with the Lmed, Entr, Trans and D2 measures and in the distinction between healthy and breathy voices, 91.17% of accuracy was obtained with only two combined measures, Trans and τ , showing the promising character of the used technique.

Forensic Automatic Speaker Recognition [Exploratory DSP

This article discusses the approaches, potential, and limitations of forensic automatic speaker recognition (FASR) which is an exploratory application of digital speech signal processing and pattern recognition for judicial purposes, particularly for law enforcement

Template-based and HMM-based Approaches for Isolated Spanish Digit Recognition

Isolated word recognition is usually performed by two dieren t approaches, viz., Conventional Templatebased and Hidden Markov Models (HMM)-based. A comparison between these approaches for isolated digit recognition (in Spanish language) is performed in this paper. For the template-based approach, several Dynamic Time Warping algorithms are proposed and implemented in a Matlab environment, while for the HMM-based approach, the algorithms available in a freeware toolbox has been employed. The algorithms are tested on a database collected during a Course on Digital Processing of Speech Signals at the University of Rosario. The test results show that a better performance can be obtained with a HMM-based digit recognizer.

SpeechLab: PC software for digital speech signal processing

SpeechLab: PC software for digital speech signal processing

VLSI architecture for digital processing of speech signals

Due to the evolution of increasingly high performantdsp algorithms for bit rate reduction of speech signals in telecommunications,vlsi implementations of these applications are becoming more and more complex. The solutions currently being used for these applications are general purpose digital signal processors or dsp cores which are never fully adapted to the application in terms ofvlsi architecture, i.e. silicon area and power consumption. We propose an alternative to these solutions, based on a parametrable Harvard architecture, and a C compiler which gives an optimized microcode suited to this architecture and to the application. Finally we present two examples of audio applications implemented using this solution.

Digital speech signal processing for pitch change with jump control in accordance with pitch period

Digital processing of speech signals for compression/expansion pitch change is provided by writing and reading a ROM at different rates and controlling the discard/repeat segments of memory to be approximately integral multiples of the pitch period with means to track the pitch period as it is changing and modify the discard/repeat segments accordingly.

Digital processing of speech signals

Digital processing of speech signals

Digital Processing of Speech Signals, by L. R. Rabiner and R. W. Schafer

First Page

Digital processing of speech signals

Digital processing of speech signals

Book Review: Digital Processing of Speech Signals

Book Review: Digital Processing of Speech Signals

Book reviews - Digital processing of speech signals

Book reviews - Digital processing of speech signals

Digital Processing of Speech Signals

Digital Processing of Speech Signals