A new perceptually motivated MVDR-based acoustic front-end (PMVDR) for robust automatic speech recognition.
Umit H. YapanelJohn H. L. HansenPublished in: Speech Commun. (2008)
Keyphrases
- automatic speech recognition
- acoustic features
- speech recognition
- noisy environments
- speech sounds
- speech signal
- conversational speech
- hidden markov models
- broadcast news
- speech recognizers
- speech segments
- word error rate
- speech recognition systems
- spoken words
- speech retrieval
- spontaneous speech
- acoustic models
- recognition errors
- speech recognizer
- face recognition
- neural network
- information retrieval