Search

This study is part of adaptive mechanisms research in speech production. We were interested to acoustic variations of the voice message when the speaker is placed in a noisy environment. We propose a methodology to highlight the articulatory strategies adopted by the speaker to adapt to the noisy environment. This methodology consists of two parts: a noise effect analysis on the timing in the one hand and on the frequency envelope of the speech signal in the other. In addition, we also highlighted the strategies adopted in the event of significant decrease of auditory feedback in the presence of noise [1]. The results are considered good because they rejoin those found in literature[1][22]. Furthermore, the methodology proposed in this study can be used in rehabilitation for the deaf (test the degree of hearing loss before and after treatment), in communication systems (level estimation of the signal alteration by noise before its transmission, in coding speech, recognition, synthesis etc…) [ABSTRACT FROM PUBLISHER]

This article develops a speaker-dependent Arabic phonemes recognition system using MFCC analysis and the VQ-LBG algorithm. The system is examined with and without vector quantization in order to analyze the effect of compression in an acoustic parameterization phase. Our experimental results show that vector quantization using a codebook of size 16 achieves good results compared to the system without quantization for a majority of the phonemes studied. [ABSTRACT FROM PUBLISHER]

Speaker recognition is the process of automatically recognizing who is speaking on the basis of individual information included in speech waves. Feature extraction for speech recognition is a subject of a major interest today; different features have been investigated in speech recognition systems. The perceptual linear predictive PLP: this technique uses three concepts from the psychophysics of hearing to derive an estimate of the auditory spectrum: (1) the critical-band spectral resolution, (2) the equal loudness curve, and (3) the intensity-loudness power law. This paper discusses the development of a speaker identification and phoneme classification system. In particular, we develop an artificial neural network: multilayer perceptron MLP using PLP coefficients of voice signal. The performance of the system has been tested in experiments using 14 Arabic phonemes, specifically the Arabic fricatives uttered by 4 Algerian native speakers. Our results demonstrates the efficiency of the PLP-MLP algorithm, a good recognition rate was obtained. [ABSTRACT FROM AUTHOR]