Differences in the effect of time-expanded and time-contracted speech on intelligibility by phonetic feature.
Toru ShibuyaYosuke KobayashiHitomi WatanabeKazuhiro KondoPublished in: ICASSP (2012)
Keyphrases
- speech recognition
- speech recognizer
- automatic speech recognition
- speech signal
- hidden markov models
- speech synthesis
- language model
- pattern recognition
- speaker independent
- image features
- spoken term detection
- feature set
- spoken document retrieval
- feature vectors
- recognition engine
- speech recognition systems
- speaker identification
- learning algorithm
- speaker adaptation