High-performance connected digit recognition using maximum mutual information estimation

Normandin, Yves; Cardin, R.; Mori, Renato De

doi:10.1109/89.279279

Cited by 89 publications

(55 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When using mixture densities, the string error rate can be reduced down to 0.71%. This error rate is actually the lowest reported [7], [9], [11], [12], [21]. Two more results for the mel-cepstrum with an acoustic vector consisting of nine components are given in Table VI.…”

Section: ) Recognition Resultsmentioning

confidence: 71%

Formant estimation for speech recognition

Welling

Ney

1998

IEEE Trans. Speech Audio Process.

View full text Add to dashboard Cite

Abstract-This paper presents a new method for estimating formant frequencies. The formant model is based on a digital resonator. Each resonator represents a segment of the short-time power spectrum. The complete spectrum is modeled by a set of digital resonators connected in parallel. An algorithm based on dynamic programming produces both the model parameters and the segment boundaries that optimally match the spectrum.We used this method in experimental tests that were carried out on the TI digit string data base. The main results of the experimental tests are: 1) the presented approach produces reliable estimates of formant frequencies across a wide range of sounds and speakers; and 2) the estimated formant frequencies were used in a number of variants for recognition. The best set-up resulted in a string error rate of 4.2% on the adult corpus of the TI digit string data base.

show abstract

Section: ) Recognition Resultsmentioning

confidence: 71%

Formant estimation for speech recognition

Welling

Ney

1998

IEEE Trans. Speech Audio Process.

View full text Add to dashboard Cite

show abstract

“…A solution [7] is to weight the contribution from each sub-band using probability exponents as follows: where wb is the weighting factor corresponding to the sub-band b. In this paper, we investigate weights computed from the subband signal-to-noise ratio (SNR) and from the inverse conditional entropy of each band.…”

Section: Likelihood Recombination (Lc)mentioning

confidence: 99%

Multi-band speech recognition in noisy environments

Okawa

Bocchieri

Potamianos

Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181

View full text Add to dashboard Cite

This paper presents a new approach for multi-band based automatic speech recognition (ASR). Recent work by Bourlard and Hermansky suggests that multi-band ASR gives more accurate recognition, especially in noisy acoustic environments, by combining the likelihoods of different frequency bands. Here we evaluate this likelihood recombination (LC) approach to multi-band ASR, and propose an alternative method, namely feature recombination (FC). In the FC system, after different acoustic analyzers are applied to each sub-band individually, a vector is composed by combining the sub-band features. The speech classifier then calculates the likelihood from the single vector. Thus, band-limited noise affects only few of the feature components, as in multi-band LC system, but, at the same time, all feature components are jointly modeled, as in conventional ASR. The experimental results show that the FC system can yield better performance than both the conventional ASR and the LC strategy for noisy speech.

show abstract

“…The maximum mutual information (MMI) [1,2], minimum classification error (MCE) [3,4], and minimum phone error (MPE) [5] have been successfully deployed in ASR. Recently the concept of large margin has been adopted in the discriminative training of acoustic models of ASR system [6,7].…”

Section: Introductionmentioning

confidence: 99%

Discriminative Output Coding Features for Speech Recognition

Dehzangi

Chng

et al. 2008

2008 6th International Symposium on Chinese Spoken Language Processing

View full text Add to dashboard Cite

This paper presents a novel approach of discriminative acoustic feature extraction for speech recognition using output coding technique. A high dimensional feature space for higher discriminative capability is constructed by expanding MFCC coefficients with polynomial expansion. In order to fit the discriminative features in the hidden Markov model structure of speech recognition, the high dimensional feature vectors are further projected into a low dimensional feature space using the output scores of a set of SVMs. Each of the SVMs is trained in one phone versus the rest manner so that each of the resulting feature dimensions can provide effective information to differ one phone from the others. The discriminative features have been evaluated in the speech recognition task of the TIMIT corpus, and 72.18% phone accuracy has been achieved.

show abstract

High-performance connected digit recognition using maximum mutual information estimation

Cited by 89 publications

References 21 publications

Formant estimation for speech recognition

Formant estimation for speech recognition

Multi-band speech recognition in noisy environments

Discriminative Output Coding Features for Speech Recognition

Contact Info

Product

Resources

About