Sixth European Conference on Speech Communication and Technology

Budapest, Hungary
September 5-9, 1999

Robust Feature Vector Compression Algorithm for Distributed Speech Recognition

Imre Kiss, Pekka Kapanen

Nokia Research Center, Speech and Audio Systems Laboratory, Tampere, Finland

In this paper we propose an algorithm for efficient compression of feature extracted parameters used in speech recognition. The algorithm provides a compression ratio of roughly 1:10 and causes negligible or no loss in recognition performance. It is also shown to be robust against enviromental noise. Combined with an appropriate framing structure, a complete system is obtained, which can be used for implementing speech recognition applications e.g. in a cellular mobile environment. The system achieves a gross bitrate as low as 4200 bps.

Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Kiss, Imre / Kapanen, Pekka (1999): "Robust feature vector compression algorithm for distributed speech recognition", In EUROSPEECH'99, 2183-2186.