Speaker-independent HMM-based voice conversion using adaptive quantization of the fundamental frequency.
Takashi NoseTakao KobayashiPublished in: Speech Commun. (2011)
Keyphrases
- fundamental frequency
- speaker independent
- adaptive quantization
- hidden markov models
- speech signal
- speech recognition
- shape coding
- rate distortion
- speaker identification
- speaker dependent
- low bit rate
- automatic speech recognition
- image compression
- noisy environments
- subband coding
- bit rate
- speech recognizer
- speech recognition systems
- subband
- mel frequency cepstral coefficients
- coding scheme
- feature selection