Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Extraction of Relevant Speech Features Using the Information Bottleneck Method

Ron M. Hecht (1), Naftali Tishby (2)

(1) Tel-Aviv University, Israel; (2) Hebrew University, Israel

We propose a novel approach to the design of efficient representations of speech for various recognition tasks. Using a principled information theoretic framework - the Information Bottleneck method - which enables quantization that preserves relevant information, we demonstrate that significantly smaller representations of the signal can be obtained that still capture most of the relevant information about phonemes or speakers. The significant implications for building more efficient speech and speaker recognition systems are discussed.

Full Paper

Bibliographic reference.  Hecht, Ron M. / Tishby, Naftali (2005): "Extraction of relevant speech features using the information bottleneck method", In INTERSPEECH-2005, 353-356.