Evaluating the performance of speech recognisers at the acoustic-phonetic level.
Gérard CholletAlain AstierMario RossiPublished in: ICASSP (1981)
Keyphrases
- speech recognition
- speech sounds
- emotional speech
- speaker independent
- speech recognition systems
- acoustic models
- speech signal
- levels of abstraction
- hidden markov models
- spoken term detection
- speech recognizers
- multi modal
- pattern recognition
- speaker identification
- speech synthesis
- speech recognizer
- emotion recognition
- acoustic signal
- language model
- spoken document retrieval
- underwater acoustic
- broadcast news
- automatic speech recognition
- prosodic features
- audio visual
- speech segments
- endpoint detection