Automatic segmentation of speech based on hidden Markov models and acoustic features.
Laura Docío FernándezCarmen García-MateoPublished in: INTERSPEECH (2000)
Keyphrases
- automatic segmentation
- hidden markov models
- acoustic features
- automatic speech recognition
- speech signal
- speech recognition
- segmentation algorithm
- visual speech
- speaker verification
- speaker identification
- broadcast news
- automatic speech recognition systems
- noisy environments
- mel frequency cepstral coefficients
- visual features
- image processing
- music information retrieval
- speaker recognition
- image data