Improving automatic speech recognition performance and speech inteligibility with harmonicity based dereverberation.
Keisuke KinoshitaTomohiro NakataniMasato MiyoshiPublished in: INTERSPEECH (2004)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- word error rate
- broadcast news
- hidden markov models
- conversational speech
- recognition errors
- speech corpus
- noisy environments
- spoken words
- word recognition
- speech sounds
- acoustic features
- spontaneous speech
- speaker identification
- error rate
- speech retrieval
- speech segments
- speech synthesis
- vocal tract
- non stationary
- computer vision