Speaker adaptable phoneme recognition selecting reliable acoustic features based on mutual information.
Katsuhiko ShiraiNaoki HosakaEiichiro KitagawaT. EndoPublished in: ICSLP (1990)
Keyphrases
- acoustic features
- phoneme recognition
- mutual information
- automatic speech recognition
- speaker dependent
- mel frequency cepstral coefficients
- speech recognition
- cross correlation
- hidden markov models
- speaker verification
- speech signal
- image registration
- speaker identification
- feature selection
- broadcast news
- visual features
- music information retrieval
- similarity measure
- audio features
- audio signal
- noisy environments
- speaker recognition
- image processing
- image retrieval
- multimedia
- speaker independent
- low level