A Compact Phoneme-To-Audio Aligner for Singing Voice.
Meizhen ZhengPeng BaiXiaodong ShiPublished in: ADMA (2) (2023)
Keyphrases
- prosodic features
- speech synthesis
- text to speech
- music information retrieval
- emotion recognition
- audio features
- speech recognition
- multimedia
- voice activity detection
- speech sounds
- audio visual
- visual information
- acoustic features
- real time
- speaker dependent
- signal processing
- audio recordings
- visual data
- speaker identification
- mel frequency cepstral coefficients
- e learning
- data sets
- audio content
- visual speech
- neural network
- metadata
- high level
- pattern recognition
- context dependent
- facial expressions