Toward parametric representation of speech for speaker recognition systems
نویسندگان
چکیده
The front-end used in many speaker recognition systems extracts, from the input speech signal, a set of coe cients based on a mel-cepstrum technique. This paper addresses the problem of e ciency of melcepstrum coe cients in a speaker recognition system and suggests a technique permitting an appropriate choice of these coe cients. It is shown, by the results obtained, that this technique can signi cantly increase the performance of a speaker recognition system.
منابع مشابه
S 15 a . 13 A STUDY OF LSF REPRESENTATION FOR SPEAKER - DEPENDENT AND SPEAKER - INDEPENDENT HMM - BASED SPEECH RECOGNITION SYSTEMS
In this paper, the line spectral-pair frequency (LSF) representation is used as the parametric representation for speech recognition. Its performance is compared with that of the cepstral cc-efficient (CC) representation for the speaker-dependent and speaker-independent hidden Markov model (HMM) based isolated word recognition systems. It is shown that the CC and the LSF representations result ...
متن کاملOn the use of line spectral frequency parameters for speech recognition
The line spectral frequency (LSF) representation has been proposed by Itakura [l] as an alternative linear prediction (LP) parametric representation. In the context of speech coding, it has been shown [2-61 that this representation has better quantization properties than the other LP parametric representations (such as log area ratios and reflection coefficients). The LSF representation is capa...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملشبکه عصبی پیچشی با پنجرههای قابل تطبیق برای بازشناسی گفتار
Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov mo...
متن کامل