Environmental robustness in automatic speech recognition

Abstract

This dissertation describes a number of algorithms developed to increase the robustness of automatic speech recognition systems with respect to changes in the environment. These algorithms attempt to improve the recognition accuracy of speech recognition systems when they are trained and tested in different acoustical environments, and when a desk-top microphone (rather than a close-talking microphone) is used for speech input. Without such processing, mismatches between training and testing conditions produce an unacceptable degradation in recognition accuracy.Two kinds of environmental variability are introduced by the use of desk-top microphones and different training and testing conditions: additive noise and spectral tilt introduced by linear filtering. An important attribute of the novel compensation algorithms described in this thesis is that they provide joint rather than independent compensation for these two types of degradation.Acoustical compensation is applied in our algorithms as an additive correction in the cepstral domain. This allows a higher degree of integration within SPHINX, the Carnegie Mellon speech recognition system, that uses the cepstrum as its feature vector. Therefore, these algorithms can be implemented very efficiently. Processing in many of these algorithms is based on instantaneous signal-to-noise ratio (SNR), as the appropriate compensation represents a form of noise suppression at low SNRs and spectral equalization at high SNRs.The compensation vectors for additive noise and spectral transformations are estimated by minimizing the differences between speech feature vectors obtained from a "standard" training corpus of speech and feature vectors that represent the current acoustical environment. In our work this is accomplished by a minimizing the distortion of vector-quantized cepstra that are produced by the feature extraction module in SPHINX.In this dissertation we describe several algorithms including the SNR-Dependent Cepstral Normalization, (SDCN) and the Codeword-Dependent Cepstral Normalization (CDCN). With CDCN, the accuracy of SPHINX when trained on speech recorded with a close-talking microphone and tested on speech recorded with a desk-top microphone is essentially the same obtained when the system is trained and tested on speech from the desk-top microphone.An algorithm for frequency normalization has also been proposed in which the parameter of the bilinear transformation that is used by the signal-processing stage to produce frequency warping is adjusted for each new speaker and acoustical environment. The optimum value of this parameter is again chosen to minimize the vector-quantization distortion between the standard environment and the current one. In preliminary studies, use of this frequency normalization produced a moderate additional decrease in the observed error rate.

Speech Recognition Using Dynamic Grammar and Parallel Listening Events

“…In the conventional approach, sound is listened by a single process which gives it to the SR engine for comparison on the basis of static grammar [2] loaded before the execution of SR system. The listener finds the probability of the recognized word and gives the result on the basis of more probability in single attempt.…”

Multi-microphone correlation-based processing for robust speech recognition

“…The CMU SPHINX-I speech recognizer [10] was trained using speech recorded in an office environment using the speakerindependent alphanumeric census database [1] with the omnidirectional desktop Crown PZM6FS microphone. Identical samples of 1018 training utterances from this database from 74 speakers were presented to the inputs of the multi-microphone system described in Figure 1.…”

“…Results of several studies have demonstrated that even automatic speech recognition systems that are designed to be speaker independent can perform very poorly when they are tested using a different type of microphone or acoustical environment from the one with which they were trained, even in a relatively quiet office environment (e.g. [1]). Applications such as speech recognition over telephones, in automobiles, on a factory floor, or outdoors demand an even greater degree of environmental robustness.…”

Noise suppression method for preprocessor of time-lag speech recognition system based on bidirectional optimally modified log spectral amplitude estimation

“…For example, introducing a new type of feature [1,2] or applying a feature normalization algorithm [3][4][5][6][7] requires retraining of the acoustic model. Acoustic model adaptation [8,9] can be used only when one has access to the detailed structure of the acoustic model.…”