Using Broad Phonetic Group Experts for Improved Speech Recognition

Patricia Scanlon; Daniel P. W. Ellis; Richard B. Reilly

Using Broad Phonetic Group Experts for Improved Speech Recognition
Scanlon, Patricia
Ellis, Daniel P. W.
Reilly, Richard B.
Electrical Engineering
Persistent URL:
Book/Journal Title:
IEEE Transactions on Audio, Speech, and Language Processing
In phoneme recognition experiments, it was found that approximately 75% of misclassified frames were assigned labels within the same broad phonetic group (BPG). While the phoneme can be described as the smallest distinguishable unit of speech, phonemes within BPGs contain very similar characteristics and can be easily confused. However, different BPGs, such as vowels and stops, possess very different spectral and temporal characteristics. In order to accommodate the full range of phonemes, acoustic models of speech recognition systems calculate input features from all frequencies over a large temporal context window. A new phoneme classifier is proposed consisting of a modular arrangement of experts, with one expert assigned to each BPG and focused on discriminating between phonemes within that BPG. Due to the different temporal and spectral structure of each BPG, novel feature sets are extracted using mutual information, to select a relevant time-frequency (TF) feature set for each expert. To construct a phone recognition system, the output of each expert is combined with a baseline classifier under the guidance of a separate BPG detector. Considering phoneme recognition experiments using the TIMIT continuous speech corpus, the proposed architecture afforded significant error rate reductions up to 5% relative.
Computer engineering
Publisher DOI:
Item views
text | xml
Suggested Citation:
Patricia Scanlon, Daniel P. W. Ellis, Richard B. Reilly, , Using Broad Phonetic Group Experts for Improved Speech Recognition, Columbia University Academic Commons, .

Columbia University Libraries | Policies | FAQ