EMOCONV-Diff: Diffusion-Based Speech Emotion Conversion for Non-Parallel and in-the-Wild Data.
Navin Raj PrabhuBunlong LaySimon WelkerNale Lehmann-WillenbrockTimo GerkmannPublished in: ICASSP (2024)
Keyphrases
- data sets
- synthetic data
- training data
- data sources
- data collection
- data quality
- statistical analysis
- data mining techniques
- anisotropic diffusion
- database
- data distribution
- experimental data
- speech recognition
- computer systems
- data processing
- image data
- data analysis
- data points
- missing data
- probability distribution
- prior knowledge
- original data
- high quality
- learning algorithm