Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition.
Geon-min KimHwaran LeeBo-Kyeong KimSang-Hoon OhSoo-Young LeePublished in: CoRR (2018)
Keyphrases
- noisy speech
- speech recognition
- speech enhancement
- noisy environments
- speech signal
- speech recognition systems
- acoustic features
- speaker independent
- hidden markov models
- speech recognizers
- pattern recognition
- language model
- sound source
- single channel
- signal to noise ratio
- speech recognizer
- automatic speech recognition
- background noise
- acoustic models
- noise reduction
- speaker identification
- vocal tract
- speech synthesis
- spectral subtraction
- linear prediction
- speaker verification
- information retrieval
- multiscale