A tutorial on signal processing in state-of-the-art speech recognition systems is presented, reviewing those techniques most commonly used. The four basic operations of signal modeling, i.e. spectral shaping, spectral analysis, parametric transformation, and statistical modeling, are discussed. Three important trends that have developed in the last five years in speech recognition are examined. First, heterogeneous parameter sets that mix absolute spectral information with dynamic, or time-derivative, spectral information, have become common. Second, similarity transform techniques, often used to normalize and decorrelate parameters in some computationally inexpensive way, have become popular. Third, the signal parameter estimation problem has merged with the speech recognition process so that more sophisticated statistical models of the signal's spectrum can be estimated in a closed-loop manner. The signal processing components of these algorithms are reviewed. >

/pdf/signal-modeling-techniques-in-speech-recognition-2s2amcdjv6.pdf

Signal modeling techniques in speech recognition

The authors present two simple tests for deciding whether the difference in error rates between two algorithms tested on the same data set is statistically significant. The first (McNemar's test) requires the errors made by an algorithm to be independent events and is found to be most appropriate for isolated-word algorithms. The second (a matched-pairs test) can be used even when errors are not independent events and is more appropriate for connected speech. >

/pdf/some-statistical-issues-in-the-comparison-of-speech-3seo703oi5.pdf

Some statistical issues in the comparison of speech recognition algorithms

Speech recognition in noisy environments: a survey

https://hal.archives-ouvertes.fr/hal-00499180/document

Automatic speech recognition and speech variability: A review

The performance of current speech recognition systems is far below that of humans. Neural nets offer the potential of providing massive parallelism, adaptation, and new algorithmic approaches to problems in speech recognition. Initial studies have demonstrated that multilayer networks with time delays can provide excellent discrimination between small sets of pre-segmented difficult-to-discriminate words, consonants, and vowels. Performance for these small vocabularies has often exceeded that of more conventional approaches. Physiological front ends have provided improved recognition accuracy in noise and a cochlea filter-bank that could be used in these front ends has been implemented using micro-power analog VLSI techniques. Techniques have been developed to scale networks up in size to handle larger vocabularies, to reduce training time, and to train nets with recurrent connections. Multilayer perceptron classifiers are being integrated into conventional continuous-speech recognizers. Neural net architectures have been developed to perform the computations required by vector quantizers, static pattern classifiers, and the Viterbi decoding algorithm. Further work is necessary for large-vocabulary continuous-speech problems, to develop training algorithms that progressively build internal word models, and to develop compact VLSI neural net hardware.

Review of neural networks for speech recognition

Several acoustic representations have been compared in speaker-dependent and independent connected and isolated-word recognition tests with undegraded speech and with speech degraded by adding white noise and by applying a 6-dB/octave spectral tilt. The representations comprised the output of an auditory model, cepstrum coefficients derived from an FFT-based mel-scale filter bank with various weighting schemes applied to the coefficients, cepstrum coefficients augmented with measures of their rates of change with time, and sets of linear discriminant functions derived from the filter-bank output and called IMELDA. The model outperformed the cepstrum representations except in noise-free connected-word tests, where it had a high insertion rate. The best cepstrum weighting scheme was derived from within-class variances. Its behavior may explain the empirical adjustments found necessary with other schemes. IMELDA outperformed all other representations in all conditions and is computationally simple. >

A comparison of several acoustic representations for speech recognition with degraded and undegraded speech

The performance of an auditory model has been compared with that of a conventional filterbank mel-cepstrum representation in speaker-dependent and speaker-independent spoken digit recognition tests. The model produces two outputs: one sensitive to voicing and onsets, and the other sensitive to formant structure and showing two-tone suppression. Linear discriminant analysis has been used to combine the outputs into eight coefficients. Undegraded, noisy and spectrally tilted male speech was tested with a quasi-isolated-word system. A subset of the tests were repeated with a connected-word system, and with undegraded female speech. In all cases the model performed better than the conventional representation. With degraded speech the differences were large. >

Speaker dependent and independent speech recognition experiments with an auditory model

An auditory model with two-tone suppression has previously been shown to perform better in speech recognition experiments than a conventional filterbank representation, particularly with noisy or distorted speech. It was, however, known to have several defects including an uneven response across the spectrum and a tendency to detect harmonics of F 0 rather than F 1 . We show that instants of glottal excitation can be derived from the model even with noisy speech. By using this information to carry out pitch-synchronous analysis in a slightly modified model the problem of interaction with harmonics of F 0 can be solved. An analysis of the behavior of the model leads to a specification of a class of processes showing two-tone suppression and hence to a redesigned model avoiding the known defects. The pitch-synchronous analysis is then no longer necessary, but the robust indication of excitation points may have other uses. Spectrograms from the old and new models illustrate the improvements obtained.

Speech recognition using an auditory model with pitch-synchronous analysis

At the 1984 IEEE ICASSP meeting Seneff described a computational model of the peripheral auditory system consisting of a bank of digital filters followed by compression and half-wave rectification stages and by a set of generalized synchrony detectors (gsd's) that respond to coherence in the signal at the center frequency of the channel We have added adjacent-channel cross-correlation and modified the gsd This results in improved sensitivity to formants in noise and allows human frequency masking measurements to be replicated quantitatively When the output of the model is used in a speech recognition task it shows an advantage over a conventional filter-bank representation both with undistorted speech and in the presence of noise and linear distortion Spectrograms generated from the model are presented both for artificially degraded speech and for speech recorded in flight in a helicopter and a fighter/trainer

Speech recognition using a cochlear model

Outputs of connected-word recognizers may contain substitution, deletion and insertion errors, and their interpretation is not trivial. Simulations show that the commonly used dynamic programming word-sequence matching algorithm has serious shortcomings as an evaluation method at low performance levels, though it is generally reliable at high performance levels. The strategy of comparing input and output words in strict sequence is found to have little to recommend it. A method using word end-point information, which provides precise, detailed performance analyses, is described. Tests with real data confirm the reliability of the end-point method and the presence of positive bias in performance estimates form the word-sequence matching method. >

M. Hunt

Papers

A comparison of several acoustic representations for speech recognition with degraded and undegraded speech

Speaker dependent and independent speech recognition experiments with an auditory model

Speech recognition using an auditory model with pitch-synchronous analysis

Speech recognition using a cochlear model

Evaluating the performance of connected-word speech recognition systems