Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

A Vector Space Approach to Environment Modeling for Robust Speech Recognition

Yu Tsao, Chin-Hui Lee

Georgia Institute of Technology, USA

We propose a vector space approach to characterizing environments for robust speech recognition. We represent a given environment by a super-vector formed by concatenating all the mean vectors of the Gaussian mixture components of the state observation densities of all hidden Markov models trained in the particular environment. New environment super-vectors can now be obtained either by an interpolation method with a collection of super-vectors trained from many real or simulated environments or by a transformation performed on an anchor super-vector for a specific environment, such as a clean condition. At a 5dB signal-to-noise (SNR) level, both interpolationand transformation-based approaches achieve a significant error rate reduction of close to 47% from a baseline system with cepstral mean subtraction (CMS) with only two adaptation utterances. When incorporating N-best information to perform unsupervised adaptation at 5dB SNR with the same two utterances, we achieve a relative error reduction of about 40%, close to that achieved in the supervised mode.

Full Paper

Bibliographic reference.  Tsao, Yu / Lee, Chin-Hui (2006): "A vector space approach to environment modeling for robust speech recognition", In INTERSPEECH-2006, paper 1617-Tue1A2O.5.