Model based feature enhancement for automatic speech recognition in reverberant environments.
Alexander KruegerReinhold Haeb-UmbachPublished in: INTERSPEECH (2009)
Keyphrases
- automatic speech recognition
- speech signal
- speech recognition
- hidden markov models
- word error rate
- conversational speech
- broadcast news
- recognition errors
- noisy environments
- spoken words
- image processing
- speech retrieval
- vocal tract
- acoustic features
- spontaneous speech
- non stationary
- speech corpus
- word recognition
- feature vectors
- multi modal
- speech sounds
- multiscale