A technique for the use of global context in text recognition is presented that determines equivalences between word images in a passage of text. Initial hypotheses for the identities of words are then generated by matching the word groups to language statistics that predict the frequency at which certain words will occur. This is followed by a recognition step and a relaxation-based control st...

The MIT Faculty has made this article openly available. Please share how this access benefits you. Your story matters. Recommended by Stephen Voran We describe an FFT-based companding algorithm for preprocessing speech before recognition. The algorithm mimics tone-to-tone suppression and masking in the auditory system to improve automatic speech recognition performance in noise. Moreover, it is...

This paper proposes a new technique for speech feature estimation under noise circumstances. This new approach yields noise-robust continuous speech recognition (CSR). Noiserobust techniques for isolated word speech recognition typically employ the running spectrum analysis (RSA), the running spectrum filtering (RSF) and the dynamic range adjustment (DRA) methods. Among them, only RSA has been ...

Data from earlier studies that presented 70 words at 24 to 0 dB signal-to-babble (S/B) ratios indicated that most young listeners with normal hearing required 0 to 6 dB S/B ratios to attain 50% correct word recognition. Older listeners with hearing loss often required a >12 dB S/B ratio to attain 50% correct word recognition. In our study, we converted the Words in Noise test from one 70-word l...

Conventional hidden Markov models (HMMs) have weak duration constraints. This may cause the decoder to produce word matches with unrealistic durations in noisy situations. This paper describes techniques for modelling context-dependent word duration cues and incorporating them directly in a multi-stack decoding algorithm. The proposed model is capable of penalising duration constraints of a wor...

Subband-autocorrelation (SBCOR) analysis is a noise robust acoustic analysis based on filter bank and autocorrelation analysis, and aims to extract periodicities associated with the inverse of the center frequency in a subband. In this paper, it is derived that SBCOR results in the lateral inhibitive weighting (LIW) processing of power spectrum, and shown that the LIW is significantly effective...

This paper discusses the problem of automatic word boundary detection in the presence of variable-level background noise. Commonly used robust word boundary detection algorithms always assume that the background noise level is fixed. In fact, the background noise level may vary during the procedure of recording. This is the major reason that most robust word boundary detection algorithms cannot...

During language acquisition, infants frequently encounter ambient noise. We present a computational model to address whether specific acoustic processing abilities are necessary to detect known words in moderate noise--an ability attested experimentally in infants. The model implements a general purpose speech encoding and word detection procedure. Importantly, the model contains no dedicated p...

This work presents a noise spectrum estimator based on the Gaussian mixture model (GMM)-based speech presence probability (SPP) for robust speech recognition. Estimated noise spectrum is then used to compute a subband a posteriori signal-to-noise ratio (SNR). A sigmoid shape weighting rule is formed based on this subband a posteriori SNR to enhance the speech spectrum in the auditory domain, wh...