Abstract
This paper considers training data selection for discriminative training of acoustic models for broadcast news speech recognition. Three novel data selection approaches were proposed. First, the average phone accuracy over all hypothesized word sequences in the word lattice of a training utterance was utilized for utterancelevel data selection. Second, phone-level data selection based on the difference between the expected accuracy of a phone arc and the average phone accuracy of the word lattice was investigated. Finally, frame-level data selection based on the normalized frame-level entropy of Gaussian posterior probabilities obtained from the word lattice was explored. The underlying characteristics of the presented approaches were extensively investigated and their performance was verified by comparison with the standard discriminative training approaches. Experiments conducted on the Mandarin broadcast news collected in Taiwan shown that both phone- and frame-level data selection could achieve slight but consistent improvements over the baseline systems at lower training iterations.
Original language | English |
---|---|
Pages | 284-289 |
Number of pages | 6 |
Publication status | Published - 2007 |
Event | 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007 - Kyoto, Japan Duration: 2007 Dec 9 → 2007 Dec 13 |
Other
Other | 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007 |
---|---|
Country/Territory | Japan |
City | Kyoto |
Period | 2007/12/09 → 2007/12/13 |
Keywords
- Acoustic models
- Data selection
- Discriminative training
- Entropy
- Speech recognition
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Software
- Artificial Intelligence