Detail publikace

Data Driven Design of Filter Bank for Speech Recognition

BURGET, L., HERMANSKY, H.

Originální název

Data Driven Design of Filter Bank for Speech Recognition

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

Filter bank approach is commonly used in feature extraction phase of speech recognition (e.g. Mel frequency cepstral coefficients). Filter bank is applied for modification of magnitude spectrum according to physiological and psychological findings. However, since mechanism of human auditory system is not fully understood,the optimal filter bank parameters are not known. This work presents a method where the filter bank, optimized for discriminability between phonemes, is derived directly from phonetically labeled speech data using Linear Discriminant Analysis. This work can be seen as another proof of the fact that incorporation of psychoacoustic findings into feature extraction can lead to better recognition performance.

Klíčová slova v angličtině

mel filterbank, speech recognition, linear discriminant analysis

Autoři

BURGET, L., HERMANSKY, H.

Rok RIV

2001

Vydáno

1. 9. 2001

Nakladatel

Springer Verlag

Místo

Zelezna Ruda

ISBN

3-540-42557-8

Kniha

Proc. 4th Intl. Conference Text, Speech Dialogue

Strany od

299

Strany do

304

Strany počet

6

BibTex

@{BUT70064
}