Performance estimation of spontaneous speech recognition using non-reference acoustic features.
Ling GuoTakeshi YamadaShoji MakinoPublished in: APSIPA (2016)
Keyphrases
- spontaneous speech
- automatic speech recognition
- acoustic features
- speech recognition
- speech signal
- human machine interaction
- hidden markov models
- spoken language
- visual features
- music information retrieval
- broadcast news
- speaker verification
- multi modal
- image processing
- audio features
- user interface
- cross correlation
- feature extraction