A Real-time Audio-to-audio Karaoke Generation System for Monaural Recordings Based on Singing Voice Suppression and Key Conversion Techniques.
Hideyuki TachibanaYuu MizunoNobutaka OnoShigeki SagayamaPublished in: J. Inf. Process. (2016)
Keyphrases
- real time
- audio visual
- audio recordings
- multimedia
- music information retrieval
- acoustic features
- audio features
- music score
- emotion recognition
- visual information
- video recordings
- audio video
- audio signals
- multi modal
- cross modal
- vision system
- signal processing
- low cost
- audio signal
- text to speech
- media streams
- audio stream
- cepstral features
- spontaneous speech
- speaker diarization
- music retrieval
- multimedia information
- visual data
- multimedia databases
- image sequences
- data sets