Time-Domain Speech Enhancement for Robust Automatic Speech Recognition.
Yufeng YangAshutosh PandeyDeLiang WangPublished in: CoRR (2022)
Keyphrases
- noisy environments
- automatic speech recognition
- speech enhancement
- speech signal
- speech recognition
- speaker verification
- noise reduction
- hidden markov models
- word error rate
- speaker identification
- background noise
- vocal tract
- frequency domain
- conversational speech
- broadcast news
- speech retrieval
- pattern recognition
- linear prediction
- acoustic features
- additive noise
- feature vectors
- bayesian networks