Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition.
Geon-min KimHwaran LeeBo-Kyeong KimSang-Hoon OhSoo-Young LeePublished in: IEEE Signal Process. Lett. (2019)
Keyphrases
- speech recognition
- noisy speech
- speech enhancement
- speech signal
- noisy environments
- speech recognition systems
- speaker independent
- acoustic features
- hidden markov models
- automatic speech recognition
- speech recognizers
- acoustic models
- language model
- speech recognizer
- sound source
- pattern recognition
- speaker identification
- noise reduction
- signal to noise ratio
- spectral subtraction
- background noise
- vocal tract
- wiener filter
- speaker verification
- single channel
- speech synthesis
- linear prediction
- mel frequency cepstral coefficients
- spectral analysis
- additive noise
- denoising
- image processing