Use of spectral centre of gravity for generating speaker invariant features for automatic speech recognition.
D. Rama SanandV. BalajiRani R. SandhyaSrinivasan UmeshPublished in: INTERSPEECH (2008)
Keyphrases
- automatic speech recognition
- invariant features
- speech recognition
- speaker adaptation
- speech signal
- hidden markov models
- word error rate
- speech sounds
- acoustic features
- image matching
- conversational speech
- shape features
- broadcast news
- noisy environments
- spontaneous speech
- keypoints
- speech retrieval
- texture images
- linear prediction
- pattern recognition
- acoustic models
- speech corpus