Deep Speech Inpainting of Time-Frequency Masks.
Mikolaj KeglerPierre BeckmannMilos CernakPublished in: INTERSPEECH (2020)
Keyphrases
- speech recognition
- signal processing
- speech signal
- speech synthesis
- image restoration
- frequency domain
- spoken language
- wavelet transform
- denoising
- texture synthesis
- endpoint detection
- speech processing
- text to speech
- audio visual
- edge detection
- pattern recognition
- hidden markov models
- image inpainting
- speaker recognition
- image processing
- data sets
- audio stream
- short time fourier transform
- recognition engine
- vocal tract
- resolution enhancement
- information retrieval
- multi stream
- computer graphics
- broadcast news
- automatic speech recognition
- human computer interaction