Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition.
Chris DonahueBo LiRohit PrabhavalkarPublished in: CoRR (2017)
Keyphrases
- speech recognition
- noisy environments
- speech enhancement
- speech signal
- noisy speech
- hidden markov models
- language model
- background noise
- automatic speech recognition
- spectral subtraction
- speaker identification
- pattern recognition
- noise reduction
- speech synthesis
- vocal tract
- generative model
- speech recognition systems
- image processing
- multi channel
- computer vision
- spectral analysis
- signal to noise ratio