Loading the SOTA2 catalog…
SOTA2 Research · tasks
Explore the problems researchers are working on and the benchmarks used to measure progress.
| Task Name | Domain | Benchmarks | Papers | Last Update |
|---|---|---|---|---|
| Artwork-to-Music Generation | 2 | 1 | Feb 22, 2026 | |
| Time-stretching | 2 | 1 | Feb 22, 2026 | |
| Cross-style Speech Synthesis | 2 | 1 | Feb 21, 2026 | |
| Speech-driven gesture synthesis | 2 | 1 | Feb 22, 2026 | |
| Speaking Target Identification | 2 | 1 | Feb 18, 2026 | |
| Subjective Speech Evaluation Prediction | 2 | 1 | Feb 22, 2026 | |
| Text-audio retrieval | 2 | 1 | Feb 22, 2026 | |
| Automatic Video Dubbing | 2 | 1 | Feb 18, 2026 | |
| Music Structure Modelling |
| 2 |
| 1 |
| Feb 21, 2026 |
| Multi-Source Vocal Separation | 2 | 1 | Feb 21, 2026 |
|---|
| Arousal Emotion Recognition | 2 | 3 | Feb 21, 2026 |
|---|
| Network dissimilarity analysis | 2 | 1 | Feb 21, 2026 |
|---|
| heart murmur detection | 2 | 1 | Feb 18, 2026 |
|---|
| Audio-driven Digital Human Generation | 2 | 1 | Feb 22, 2026 |
|---|
| Note-level Singing Voice Transcription | 2 | 1 | Feb 18, 2026 |
|---|
| Video Background Music Generation | 2 | 1 | Feb 18, 2026 |
|---|
| Human Recognition | 2 | 2 | Mar 31, 2026 |
|---|
| Alzheimer's Disease Recognition from Speech | 2 | 2 | Feb 22, 2026 |
|---|
| Speech-to-Singing conversion | 2 | 1 | Feb 18, 2026 |
|---|
| Named Entity Correction | 2 | 1 | Feb 22, 2026 |
|---|
| Linear correlation between human MOS and automatic metrics | 2 | 1 | Feb 21, 2026 |
|---|
| Style Prompt Adherence evaluation | 2 | 1 | Feb 21, 2026 |
|---|
| Speaking Speed Control | 2 | 1 | Feb 21, 2026 |
|---|
| Sound Event Separation | 2 | 1 | Feb 21, 2026 |
|---|
| Text-Only Speech Synthesis | 2 | 1 | Feb 21, 2026 |
|---|