Suprasegmental duration modelling with elastic constraints in automatic speech recognition.
Laurence MolloyStephen IsardPublished in: ICSLP (1998)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- hidden markov models
- word error rate
- broadcast news
- conversational speech
- noisy environments
- recognition errors
- spontaneous speech
- speech retrieval
- spoken words
- word recognition
- acoustic features
- language model
- noise reduction
- video sequences
- compound words