论文信息 - COMPLEMENTARY CUES FOR SPEECH RECOGNITION

COMPLEMENTARY CUES FOR SPEECH RECOGNITION

In this paper, we discuss the role of different complementary cues at three different levels: acoustic, aerodynamic and articulatory on a speech recognition task. The recognition system is a standard speaker dependant HMM recognizer. The corpus is based on CVCV sequences uttered by one speaker. It is shown that aerodynamic and articulatory cues used in combination with Mel frequency cepstral coefficients lead to a substantial increase of the system recognition score.

Marco Saerens | Alain Soquet | Marco Saerens | A. Soquet

[1] Stan Davis,et al. Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Se , 1980 .

[2] Biing-Hwang Juang,et al. Hidden Markov Models for Speech Recognition , 1991 .

[3] Daniel Recasens,et al. An electropalatographic study of stop consonant clusters , 1993, Speech Commun..

[4] Igor Zlokarnik. Experiments with an articulatory speech recognizer , 1993, EUROSPEECH.

[5] Marco Saerens,et al. A comparison of different acoustic and articulatory representations for the determination of place of articulation of plosives , 1994, ICSLP.

[6] Li Deng,et al. Production models as a structural basis for automatic speech recognition , 1997, Speech Commun..

[7] Jacques C. Koreman,et al. Do phonetic features help to improve consonant identification in ASR? , 1998, ICSLP.