Speaker-independent HMM-based voice conversion using quantized fundamental frequency.
Takashi NoseTakao KobayashiPublished in: INTERSPEECH (2010)
Keyphrases
- fundamental frequency
- speaker independent
- hidden markov models
- speech signal
- speech recognition
- speaker identification
- speaker dependent
- automatic speech recognition
- noisy environments
- speech recognizer
- speaker recognition
- vocal tract
- non stationary
- speech recognition systems
- pattern recognition
- multiscale
- natural language processing
- low level
- image processing
- sound source
- feature vectors
- acoustic features
- image retrieval