Fourth European Conference on Speech Communication and Technology

Madrid, Spain
September 18-21, 1995

Training Data Clustering for Improved Speech Recognition

Ananth Sankar, Frangoise Beaufays, Vassilios Digalakis

SRI International, Menlo Park, CA, USA

We present an approach to cluster the training data for automatic speech recognition (ASR). A relative-entropy based distance metric between training data clusters is defined. This metric is used to hierarchically cluster the training data. The metric can also be used to select the closest training data clusters given a small amount of data from the test speaker. The selected clusters are then used to estimate a set of hidden Markov models (HMMs) for recognizing the speech from the test speaker. We present preliminary experimental results of the clustering algorithm and its application to ASR.

Full Paper

Bibliographic reference.  Sankar, Ananth / Beaufays, Frangoise / Digalakis, Vassilios (1995): "Training data clustering for improved speech recognition", In EUROSPEECH-1995, 503-506.