Markov model based noise modeling and its application to noisy speech recognition using dynamical features of speech

Kobayashi, Tetsuo; Mine, Ryuji; Shirai, Katsuhiko

doi:10.1109/icassp.1994.389719

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, from Eqs. (5), (6), 7, (8), and (9), we obtain (10) Two averages of undistorted speech, wi and vi, retain information regarding both utterance contents and speaker individualities. The derivations of this equation imply that they have no significant difference.…”

Section: (7)mentioning

confidence: 99%

Rapid environment adaptation for speech recognition.

Takagi

Hattori

Watanabe

1995

J. Acoust. Soc. Jpn. (E), J Acoust Soc Jpn E

View full text Add to dashboard Cite

This paper proposes a rapid environment adaptation algorithm based on spectrum equalization (REALISE). In practical speech recognition applications, differences between training and testing environments often seriously diminish recognition accuracy. These environmental differences can be classified into two types: difference in additive noise and difference in multiplicative noise in the spectral domain. The proposed method calculates time-alignment between a testing utterance and the closest reference pattern to it, and then calculates the noise differences between the two according to the timealignment. Then, we adapt all reference patterns to the testing environment using the differences. Finally, the testing utterance is recognized using the adapted reference patterns. In a 250 Japanese word recognition task, in which the training and testing microphones were of two different types, REALISE improved recognition accuracy from 87% to 96%.

show abstract

Section: (7)mentioning

confidence: 99%