7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

Algorithms for Distributed Speech Recognition in a Noisy Automobile Environment

Hong Kook Kim, Richard C. Rose

AT&T Labs - Research, USA

In this paper, we evaluate the performance of several robust speech recognition algorithms in a noisy automobile environment as characterized by the Finnish SpeechDat-Car ASR task [1]. By applying acoustic feature compensation, model compensation, and speech detection algorithms to this task, a 51% reduction in word error rate (WER) was obtained relative to the ETSI standard ASR front-end. In addition, these same techniques achieved an average 35% WER reduction for clean condition training and multiple condition training on a simulated speech-in-noise task as characterized by the Aurora 2 ASR task [2]. The paper also presents alternatives for how these algorithms can be implemented in a distributed speech recognition framework.

Full Paper

Bibliographic reference.  Kim, Hong Kook / Rose, Richard C. (2002): "Algorithms for distributed speech recognition in a noisy automobile environment", In ICSLP-2002, 233-236.