Speech recognition in noisy environments: a survey

Since the statistics of the speech signal as well as of the noise are not explicitly available, and the most perceptually meaningful distortion measure is not known, model-based approaches have recently been extensively studied and applied to the three basic problems of speech enhancement: signal estimation from a given sample function of noisy speech, signal coding when only noisy speech is available, and recognition of noisy speech signals in man-machine communication. Research on the model-based approach is integrated and put into perspective with other more traditional approaches for speech enhancement. A unified statistical approach for the three basic problems of speech enhancement is developed, using composite source models for the signal and noise and a fairly large set of distortion measures. >

Statistical-model-based speech enhancement systems

Achieving reliable performance for a speech recogniser is an important challenge, especially in the context of mobile telephony applications where the user can access telephone functions through voice The breakthrough of such a technology is appealing, since the driver can concentrate completely and safely on his task while composing and conversing in a “full” hands-free mode This paper addresses the problem of speaker-dependent discrete utterance recognition in noise Special reference is made to the mismatch effects due to the fact that training and testing are made in different environments A novel technique for noise compensation is proposed: nonlinear spectral subtraction (NSS) Robust variance estimates and robust pdf evaluations (projection) are also introduced and combined with NSS into the HMM framework We show that the lower limit of applicability of the projection (low SNR values) can be loosened after combination with NSS Experimental results are reported The performance of an HMM-based recogniser rises from 56% (no compensation) to 98% after speech enhancement More than 3300 utterances have been used to evaluate the systems (three databases, two European languages) This result is achieved by the use of robust training/recognition schemes and by preprocessing the noisy speech by NSS

Experiments with a Nonlinear Spectral Subtractor (NSS), Hidden Markov Models and the projection, for robust speech recognition in cars

Speech recognition in adverse environments

An acoustical mismatch between the training and the testing conditions of hidden Markov model (HMM)-based speech recognition systems often causes a severte degradation in the recognition performance. In telephone speech recognition, for example, undesirable signal components due to ambient noise and channel distortion, as well as due to different variations of telephone handsets render the recognizer unusable for real- world applications. This paper presents a signal bias removal (SBR) method based on maximum likelihood1 estimation for the minimization of these undesirable effects. The proposed method is readily applicable in various architectures, i.e., dis- crete (vector-quantization based), semicontinuous and continuous density HMM. In this paper, the SBR method, integrated into a discrete density HMM, is applied to telephone speech recognition where the contamination due to extraneous signal components is assumed to be unknown. To enable real-time implementation, a sequential method for the estimation of the bias is presented. Experimental results for speaker-independent connected digit recognition show a reduction in the per digit error rate by up to 41% and 14% during mismatched and matclhed training and testing conditions, respectively.

Signal bias removal by maximum likelihood estimation for robust telephone speech recognition

The authors address the problem of speech enhancement in a car environment. After describing the method used to characterize the noisy environment, the main effects of the noise on speech processing for speech recognition and transmission are presented. Most of the noise reduction methods proposed in past years have been developed and evaluated in the case of additive white noise. The authors have found that the results obtained by this approach, without modification, are poor. With preprocessing of the noisy signal, improvements are shown, especially for speech recognition. >

Car noise processing for speech input

The authors propose a low cost 6 kbps multipulse-excited linear prediction coder for 8 kbps transmissions on 12.5 kHz radio channels. The main purpose of this system is to give good intelligibility and good speaker recognition. Against transmission errors, the authors present a correcting strategy and an extrapolation method that hides lost speech frames. >

Medium band speech coding for mobile radio communications

Vector Quantization has recently been used in the realization of a speaker-independent digit recognizer, based uniquely on the spectral content of the speech signal. On the other hand, the Hidden Markov Models proved their ability in modelling temporal distortions between different utterances of a word pronounced by several speakers. In term of recognition rate, HMMs are as efficient as the conventional DTW matching, but they need less computation and memory. This paper presents a speaker-independent digit recognition system that combines word-based VQ with HMM, the cost of which is low enough to be implemented on a single signal processor available today. It is the first result of a cooperation project between ENST and the MATRA company, financially supported by the French government. The proposed recognizer is structured in two parts. First, a VQ-preprocessor, with one vector codebook per vocabulary word, performs a coding of the short-time spectrum of the speech signal and realizes an initial sorting. Then HMMs are used to take the final recognition decision.

A. Tassy

Papers

Car noise processing for speech input

Medium band speech coding for mobile radio communications

Speaker-independent French digits recognition using word-based vector quantization and hidden Markov models