LVCSR log-likelihood ratio scoring for keyword spotting
Author:
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 297-300
Abstract
A new scoring algorithm has been developed for generating wordspotting hypotheses and their associated scores. This technique uses a large-vocabulary continuous speech recognition (LVCSR) system to generate the N-best answers along with their Viterbi alignments. The score for a putative hit is computed by summing the likelihoods for all hypotheses that contain the keyword normalized by dividing by the sum of all hypothesis likelihoods in the N-best list. Using a test set of conversational speech from Switchboard Credit Card conversations, we achieved an 81% figure of merit (FOM). Our word recognition error rate on this same test set is 54.7%.Keywords
This publication has 11 references indexed in Scilit:
- Continuous hidden Markov modeling for speaker-independent word spotting2003
- A hidden Markov model based keyword recognition system2002
- Techniques to achieve an accurate real-time large-vocabulary speech recognition system1994
- Keyword-spotting using SRI's DECIPHER large-vocabulary speech-recognition system1993
- Large-vocabulary dictation using SRI's DECIPHER speech recognition system: progressive search techniques1993
- Reduced channel dependence for speech recognition1992
- Performance of SRI's DECIPHER#8482; speech recognition system on DARPA's CSR task1992
- SWITCHBOARD: telephone speech corpus for research and development1992
- A tree-trellis based fast search for finding the N Best sentence hypotheses in continuous speech recognition1990
- Efficient, high-performance algorithms for N-Best search1990