Leveraging Symmetrical Convolutional Transformer Networks for Speech to Singing Voice Style Transfer.
Shrutina AgarwalNaoya TakahashiSriram GanapathyPublished in: INTERSPEECH (2022)
Keyphrases
- text to speech
- emotion recognition
- fuzzy logic
- voice activity detection
- speech synthesis
- speech recognition errors
- speech recognition
- information transfer
- audio features
- automatic speech recognition
- speech quality
- network design
- machine learning
- speech signal
- network structure
- fault diagnosis
- power system
- multi modal
- synthesized speech
- sparse coding
- complex networks
- broadcast news
- fundamental frequency
- low level
- social networks
- cross domain learning
- learning algorithm