Sixth International Conference on Spoken Language Processing (ICSLP 2000) Beijing, China October 16-20, 2000

Speech and Word Detection Algorithms for Hands-Free Applications

Duanpei Wu, X. Menendez-Pidal, L. Olorenshaw, R. Chen, M. Tanaka, M. Amador

Spoken Language Technology, Sony US Research Laboratories

This paper describes a robust speech detection algorithm for speech-activated hands-free applications. The system consists of three techniques: (1) noise suppression with efficient implementation, (2) robust endpoint detection and (3) speech verification using garbage modeling and confidence measure. With efficient implementation, noise suppression improves the SNR by roughly 10-20 dB. The endpoint detection uses the technique described in [1] with improvement for non-stationary noise. Garbage modeling and confidence measure are used to handle out-of-vocabulary (OOV) words and background pulse noise.

Reference

1. Wu, D., M. Tanaka, R. Chen and L. Olorenshaw, "A Robust Endpoint Detection Algorithm for Speech Recognition in Cars" Proceedings-97 of Sony Research Forum, Tokyo, 1997.

Full Paper

Bibliographic reference.  Wu, Duanpei / Menendez-Pidal, X. / Olorenshaw, L. / Chen, R. / Tanaka, M. / Amador, M. (2000): "Speech and word detection algorithms for hands-free applications", In ICSLP-2000, vol.4, 398-401.