An Empirical Study on Speech Restoration Guided by Self-Supervised Speech Representation.
Jaeuk ByunYouna JiSoo-Whan ChungSoyeon ChoeMin-Seok ChoiPublished in: ICASSP (2023)
Keyphrases
- speech recognition
- speech signal
- recognition engine
- audio visual
- speech synthesis
- text to speech
- endpoint detection
- image representation
- automatic speech recognition
- spoken language
- vocal tract
- case study
- audio stream
- spoken dialogue systems
- speaker identification
- speaker recognition
- audio features
- speech processing
- multi stream
- representation scheme
- multi modal
- pattern recognition
- multiscale
- data sets
- text to speech synthesis