Discriminative utterance verification for connected digits recognition
Authors:
- Chin-Hui LeeCLChin-Hui Lee
- Biing-Hwang JuangBJBiing-Hwang Juang
- 1 May 1997
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Speech and Audio Processing
- Vol. 5 (3) , 266-277
Abstract
Utterance verification represents an important technology in the design of user-friendly speech recognition systems. It involves the recognition of keyword strings and the rejection of nonkeyword strings. This paper describes a hidden Markov model-based (HMM-based) utterance verification system using the framework of statistical hypothesis testing. The two major issues on how to design keyword and string scoring criteria are addressed. For keyword verification, different alternative hypotheses are proposed based on the scores of antikeyword models and a general acoustic filler model. For string verification, different measures are proposed with the objective of detecting nonvocabulary word strings and possibly erroneous strings (so-called putative errors). This paper also motivates the need for discriminative hypothesis testing in verification. One such approach based on minimum classification error training is investigated in detail. When the proposed verification technique was integrated into a state-of-the-art connected digit recognition system, the string error rate for valid digit strings was found to decrease by 57% when setting the rejection rate to 5%. Furthermore, the system was able to correctly reject over 99.9% of nonvocabulary word strings.Keywords
This publication has 15 references indexed in Scilit:
- A study on minimum error discriminative training for speaker recognitionThe Journal of the Acoustical Society of America, 1995
- A MINIMUM ERROR RATE PATTERN RECOGNITION APPROACH TO SPEECH RECOGNITIONInternational Journal of Pattern Recognition and Artificial Intelligence, 1994
- Task independent wordspotting using decision tree based allophone clustering1993
- Keyword-spotting using SRI's DECIPHER large-vocabulary speech-recognition system1993
- Rejection techniques for digit recognition in telecommunication applications1993
- A two pass classifier for utterance rejection in keyword spotting1993
- Discriminative learning for minimum error classification (pattern recognition)IEEE Transactions on Signal Processing, 1992
- Rejection and keyword spotting algorithms for a directory assistance city name recognition application1992
- Segmental GPD training of HMM based speech recognizer1992
- Automatic recognition of keywords in unconstrained speech using hidden Markov modelsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1990