CONF
pinto:ICSLP:2007/IDIAP
Exploiting Phoneme Similarities in Hybrid HMM-ANN Keyword Spotting
Pinto, Joel Praveen
Lovitt, Andrew
Hermansky, Hynek
EXTERNAL
https://publications.idiap.ch/attachments/papers/2007/pinto-ICSLP-2007.pdf
PUBLIC
https://publications.idiap.ch/index.php/publications/showcite/pinto:rr07-11
Related documents
2007
IDIAP-RR 07-11
We propose a technique for generating alternative models for keywords in a hybrid hidden Markov model - artificial neural network (HMM-ANN) keyword spotting paradigm. Given a base pronunciation for a keyword from the lookup dictionary, our algorithm generates a new model for a keyword which takes into account the systematic errors made by the neural network and avoiding those models that can be confused with other words in the language. The new keyword model improves the keyword detection rate while minimally increasing the number of false alarms.
REPORT
pinto:rr07-11/IDIAP
Exploiting Phoneme Similarities in Hybrid HMM-ANN Keyword Spotting
Pinto, Joel Praveen
Lovitt, Andrew
Hermansky, Hynek
EXTERNAL
https://publications.idiap.ch/attachments/reports/2007/pinto-idiap-rr-07-11.pdf
PUBLIC
Idiap-RR-11-2007
2007
IDIAP
Submitted for publication
We propose a technique for generating alternative models for keywords in a hybrid hidden Markov model - artificial neural network (HMM-ANN) keyword spotting paradigm. Given a base pronunciation for a keyword from the lookup dictionary, our algorithm generates a new model for a keyword which takes into account the systematic errors made by the neural network and avoiding those models that can be confused with other words in the language. The new keyword model improves the keyword detection rate while minimally increasing the number of false alarms.