Singing Voice Synthesis Using Differentiable LPC and Glottal-Flow-Inspired Wavetables.
Chin-Yun YuGyörgy FazekasPublished in: ISMIR (2023)
Keyphrases
- speech signal
- speech quality
- speech recognition
- fundamental frequency
- acoustic features
- mel frequency cepstral coefficients
- automatic speech recognition
- non stationary
- texture synthesis
- linear predictive
- flow patterns
- music information retrieval
- linear prediction
- hidden markov models
- flow field
- speaker identification
- computer vision
- information flow
- loss function
- blood flow
- pattern recognition
- data sets
- real time