Speech Enhancement for Noise-Robust Speech Synthesis Using Wasserstein GAN.
Nagaraj AdigaYannis PantazisVassilis TsiarasYannis StylianouPublished in: INTERSPEECH (2019)
Keyphrases
- speech enhancement
- speech synthesis
- vocal tract
- noisy environments
- speech recognition
- speech signal
- noise reduction
- text to speech
- background noise
- hidden markov models
- signal to noise ratio
- automatic speech recognition
- noisy speech
- speaker verification
- wiener filter
- machine learning
- language model
- pattern recognition
- linear prediction
- edge preserving
- prediction error
- high frequency
- smoothing algorithm
- information retrieval