A Strategy for Improved Phone-Level Lyrics-to-Audio Alignment for Speech-to-Singing Synthesis.
David AyllónFernando VillavicencioPierre LanchantinPublished in: INTERSPEECH (2019)
Keyphrases
- audio features
- music information retrieval
- acoustic features
- audio visual
- audio signals
- audio recordings
- low level
- visual features
- audio signal
- feature set
- digital audio
- music retrieval
- genre classification
- multi modal
- speaker identification
- audio stream
- emotion recognition
- speech signal
- text data
- speech processing
- automatic speech recognition
- emotional speech
- digital music
- broadcast news
- speech recognition
- mobile phone
- speaker verification
- information retrieval
- acoustic models
- emotion classification
- information retrieval systems