An investigation of acoustic features for singing voice conversion based on perceptual age.
Kazuhiro KobayashiHironori DoiTomoki TodaTomoyasu NakanoMasataka GotoGraham NeubigSakriani SaktiSatoshi NakamuraPublished in: INTERSPEECH (2013)
Keyphrases
- acoustic features
- mel frequency cepstral coefficients
- speaker verification
- music information retrieval
- audio features
- visual features
- music genre classification
- automatic speech recognition
- cross correlation
- emotion recognition
- speech signal
- low level
- environmental sounds
- audio visual
- visual information
- multi modal
- gaussian mixture model
- speech recognition
- similarity measure
- web pages