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 |
|---|---|---|---|---|
| Underwater Acoustic Classification | 1 | 2 | Apr 20, 2026 | |
| Audio-to-Motion Generation | 1 | 1 | Feb 18, 2026 | |
| Self-supervised pretraining | 1 | 1 | Feb 19, 2026 | |
| System-level human MOS correlation | 1 | 1 | Mar 25, 2026 | |
| Audio-to-video synthesis | 1 | 1 | Mar 25, 2026 | |
| Generalized Zero-Shot Retrieval (Text-to-Audio) | 1 | 1 | Feb 18, 2026 | |
| Speech-driven 3D Holistic Body Motion Generation | 1 | 1 | Feb 18, 2026 | |
| Unified Audio and Video Generation | 1 | 1 |
| Mar 25, 2026 |
| Audio-based Referring Video Object Segmentation | 1 | 1 | Mar 25, 2026 |
|---|
| Audio-driven human animation | 1 | 1 | Mar 25, 2026 |
|---|
| Speech-to-speech response generation | 1 | 1 | Mar 25, 2026 |
|---|
| Target Speaker Tracking | 1 | 1 | Mar 26, 2026 |
|---|
| Audio-to-Text Classification | 1 | 1 | Mar 26, 2026 |
|---|
| Generalized Zero-Shot Retrieval (Text-to-Audio-Video) | 1 | 1 | Feb 18, 2026 |
|---|
| 5-speaker speech separation | 1 | 1 | Feb 18, 2026 |
|---|
| Voice Empathy | 1 | 1 | Feb 19, 2026 |
|---|
| Text-to-Audio Classification | 1 | 1 | Mar 26, 2026 |
|---|
| Open QA (Speech to Text) | 1 | 1 | Feb 19, 2026 |
|---|
| Speech Synthesis Quality Evaluation Correlation Analysis | 1 | 1 | Mar 26, 2026 |
|---|
| Audio-to-Text temporal grounding | 1 | 1 | Feb 27, 2026 |
|---|
| Text-to-Audio temporal grounding | 1 | 2 | Jul 7, 2026 |
|---|
| Speech Evaluation | 1 | 1 | Mar 27, 2026 |
|---|
| Spoken command recognition | 1 | 2 | Feb 18, 2026 |
|---|
| Video-to-Audio temporal grounding | 1 | 2 | Jul 7, 2026 |
|---|
| Hotword Retrieval | 1 | 1 | Mar 27, 2026 |
|---|