5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Word Verification Using Confidence Measures in Speech Recognition

M. Carmen Benitez, Antonio Rubio, Pedro Garcia, Jesus Diaz-Verdejo

Universidad de Granada, Spain

In this work we propose a novel way of discriminating the words that are recognized by a speech recognition system as correctly or incorrectly detected words. The procedure consists of the extraction of a set of characteristics for each word. Utilizing these characteristics, we have built two classifiers: the first one is a vector quantizer, while the second one, though also a vector quantizer, was trained using adaptative technique learning (LVQ). The results obtained show an improvement in the performance of the recognizer achieved by reducing the number of insertions with no significant reduction in the correctly detected words.

Full Paper

Bibliographic reference.  Benitez, M. Carmen / Rubio, Antonio / Garcia, Pedro / Diaz-Verdejo, Jesus (1998): "Word verification using confidence measures in speech recognition", In ICSLP-1998, paper 1082.