Wavebender GAN: An architecture for phonetically meaningful speech manipulation.
Gustavo Teodoro Döhler BeckUlme WennbergZofia MaliszGustav Eje HenterPublished in: CoRR (2022)
Keyphrases
- structuring elements
- speech signal
- speech recognition
- audio visual
- text to speech
- endpoint detection
- automatic speech recognition systems
- speech synthesis
- spoken language
- gray scale
- automatic speech recognition
- information retrieval
- higher level
- multi modal
- speech processing
- multi stream
- color images
- case study
- text to speech synthesis