Lexicon expansion using pronunciation variations extracted on the basis of speaker-related deviation in recognition error statistics.
Yoshifumi OnishiPublished in: INTERSPEECH (2008)
Keyphrases
- speech recognition
- recognition rate
- speaker independent
- object recognition
- automatic speech recognition
- recognition accuracy
- feature extraction
- error rate
- speaker identification
- automatic speech recognition systems
- hidden markov models
- character recognition
- language learning
- recognition process
- extracting features
- mel frequency cepstral coefficients
- recognition algorithm
- noisy environments
- action recognition
- face recognition