Deep Learning Based Dereverberation of Temporal Envelopesfor Robust Speech Recognition.
Anurenjan PurushothamanAnirudh SreeramRohit KumarSriram GanapathyPublished in: CoRR (2020)
Keyphrases
- speech recognition
- deep learning
- noisy environments
- hidden markov models
- language model
- speech recognizer
- automatic speech recognition
- pattern recognition
- speech signal
- speech synthesis
- unsupervised learning
- speech recognition technology
- speaker identification
- mental models
- speech recognition systems
- image processing
- feature selection
- model selection