Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks.
Dominik WagnerIlja BaumannTobias BockletPublished in: CoRR (2023)
Keyphrases
- endpoint detection
- generative model
- speech recognition
- social networks
- parallel implementation
- parallel processing
- complex networks
- unsupervised learning
- data mining
- recognition engine
- speech signal
- packet switched
- network structure
- speech synthesis
- interconnection networks
- broadcast news
- network size
- language acquisition
- distributed memory
- dialogue system
- network design
- automatic speech recognition
- massively parallel
- parallel computing
- pattern recognition
- shared memory
- audio visual
- network analysis
- probabilistic model