Leveraging Symmetrical Convolutional Transformer Networks for Speech to Singing Voice Style Transfer.
Shrutina AgarwalSriram GanapathyNaoya TakahashiPublished in: CoRR (2022)
Keyphrases
- text to speech
- speech synthesis
- speech recognition
- speech signal
- speech recognition errors
- speech quality
- fuzzy logic
- voice activity detection
- fundamental frequency
- network structure
- complex networks
- fault diagnosis
- network design
- emotion recognition
- information retrieval
- social networks
- text to speech synthesis
- speech sounds
- deep learning
- recognition engine
- acoustic features
- audio features
- network architecture
- knowledge transfer
- transfer learning
- information transfer
- music information retrieval
- genetic algorithm