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 |
|---|---|---|---|---|
| Audio-to-Video temporal grounding | 1 | 2 | Jul 7, 2026 | |
| Multi-channel speech enhancement | 1 | 1 | Mar 27, 2026 | |
| Speaking Head Motion Generation | 1 | 1 | Mar 27, 2026 | |
| Listening Head Motion Generation | 1 | 1 | Mar 27, 2026 | |
| Explicit Emotion Steering | 1 | 1 | Mar 27, 2026 | |
| Implicit Emotion Steering | 1 | 1 | Mar 27, 2026 | |
| Music Auto-tagging | 1 | 1 | Feb 18, 2026 | |
| Speech Detection | 1 | 1 | Feb 27, 2026 | |
| Audio Safety Evaluation |
| 1 |
| 1 |
| Mar 27, 2026 |
| Full-duplex Speech Interaction Latency Analysis | 1 | 1 | Mar 30, 2026 |
|---|
| Mandarin Dialect Identification | 1 | 1 | Feb 19, 2026 |
|---|
| Ambisonics upscaling | 1 | 1 | Mar 31, 2026 |
|---|
| Accent Neutralization | 1 | 1 | Mar 31, 2026 |
|---|
| Identity Authentication | 1 | 1 | Feb 19, 2026 |
|---|
| Speaker Similarity Analysis | 1 | 1 | Mar 31, 2026 |
|---|
| Streaming Speech-to-Text Translation | 1 | 1 | Feb 18, 2026 |
|---|
| Sentence-level Forgery Detection | 1 | 1 | Mar 31, 2026 |
|---|
| Word-level Forgery Detection | 1 | 1 | Mar 31, 2026 |
|---|
| HRIR spatial up-sampling | 1 | 1 | Mar 31, 2026 |
|---|
| Music mood/theme tagging | 1 | 1 | Mar 31, 2026 |
|---|
| Predicting Sounds from Video | 1 | 1 | Feb 18, 2026 |
|---|
| Speech-Music Separation | 1 | 1 | Feb 18, 2026 |
|---|
| Impact sound synthesis | 1 | 1 | Feb 18, 2026 |
|---|
| Audio Imperceptibility Evaluation | 1 | 1 | Feb 19, 2026 |
|---|
| Genre tagging | 1 | 1 | Mar 31, 2026 |
|---|