4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

A User-Configurable System for Voice Label Recognition

Richard C. Rose (1), Eduardo Lleida-Solano (2), G. W. Erhart (3), R. V. Grubbe (3)

(1) AT&T Research, Murray Hill, NJ, USA
(2) University of Zaragoza, Spain
(3) Lucent Technologies, Columbus, OH, USA

A set of techniques for configuring a speech recognition system to a particular user are described in the context of voice label recognition over the public switched telephone network. User-configurable vocabularies are provided through automatic acoustic baseform determination based on an inventory of speaker independent subword acoustic units. The tendency of input utterances to contain out-of-vocabulary or non-speech information is accounted for using likelihood ratio based utterance verification procedures. Mismatch between a given user's utterances and the HMM model is accounted for using a frequency warping approach to speaker normalization. The performance of these techniques was evaluated on utterances taken from a trial version of a voice label recognition service.

Full Paper

Bibliographic reference.  Rose, Richard C. / Lleida-Solano, Eduardo / Erhart, G. W. / Grubbe, R. V. (1996): "A user-configurable system for voice label recognition", In ICSLP-1996, 582-585.