Linguistic and acoustic features depending on different situations - the experiments considering speech recognition rate.
Shinya YamadaToshihiko ItohKenji ArakiPublished in: INTERSPEECH (2005)
Keyphrases
- recognition rate
- acoustic features
- speech signal
- automatic speech recognition
- speaker verification
- face recognition
- music information retrieval
- visual features
- recognition accuracy
- audio features
- speech recognition
- mel frequency cepstral coefficients
- cross correlation
- natural language processing
- noisy environments
- non stationary
- hidden markov models
- natural language
- speaker identification
- face databases
- artificial neural networks
- pattern recognition
- similarity measure
- web pages
- feature selection