WaveVC: Speech and Fundamental Frequency Consistent Raw Audio Voice Conversion.
Kyungdeuk KoDonghyeon KimKyungseok OhHanseok KoPublished in: Neural Process. Lett. (2024)
Keyphrases
- fundamental frequency
- speech signal
- speaker identification
- multimedia
- acoustic features
- text to speech
- signal processing
- visual information
- raw data
- audio visual
- audio signals
- speech recognition
- audio stream
- audio video
- prosodic features
- mel frequency cepstral coefficients
- neural network
- cepstral features
- audio signal
- automatic speech recognition
- non stationary
- visual features
- information retrieval systems
- high level