Automatic modeling for adding new words to a large-vocabulary continuous speech recognition system
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 305-308 vol.1
- https://doi.org/10.1109/icassp.1991.150337
Abstract
The authors report on the detection of new words for the speaker-dependent and speaker-independent paradigms. A useful operating point in a speaker-dependent paradigm is defined at 71% detection rate and 1% false alarm rate. The authors present a novel technique for obtaining a phonetic transcription for a new word, which is needed to add the new word to the system. The technique utilizes DECtalk's text-to-sound rules to obtain an initial phonetic transcription for the new word. Since these text-to-sound rules are imperfect, a probabilistic transformation technique is used that produces a phonetic pronunciation network of all possible pronunciations given DECtalk's transcription. The network is used to constrain a phonetic recognition process that results in an improved phonetic transcription for the new word. The resulting transcriptions are sufficient for speech recognition purposes.<>Keywords
This publication has 7 references indexed in Scilit:
- BYBLOS: The BBN continuous speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- An information theoretic approach to the automatic determination of phonemic baseformsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Classifying words for improved statistical language modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Automatic detection of new words in a large vocabulary continuous speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A new paradigm for speaker-independent training and speaker adaptationPublished by Association for Computational Linguistics (ACL) ,1990
- Automatic phonetic baseform determinationPublished by Association for Computational Linguistics (ACL) ,1990
- Estimation of probabilities from sparse data for the language model component of a speech recognizerIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987