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 |
|---|---|---|---|---|
| Vision-Audio-Language (VAL) | 1 | 1 | Apr 16, 2026 | |
| Passive Sonar Classification | 1 | 2 | Jun 2, 2026 | |
| Audio Generation (Average) | 1 | 1 | Feb 18, 2026 | |
| Audio Perception | 1 | 1 | Apr 20, 2026 | |
| Custom-voice speech generation | 1 | 1 | Apr 20, 2026 | |
| Dominance Regression | 1 | 1 | Feb 18, 2026 | |
| Speech Segmentation | 1 | 1 | Feb 18, 2026 | |
| Audio Query QA | 1 | 1 | Apr 20, 2026 | |
| Egocentric Emotion Recognition | 1 | 1 | Apr 20, 2026 | |
| 1 |
| 1 |
| Apr 20, 2026 |
| Video-to-Audio Stereo Alignment | 1 | 1 | Apr 21, 2026 |
|---|
| Audio-visual video forgery detection | 1 | 1 | Feb 18, 2026 |
|---|
| 3D Sound Speed Field Reconstruction | 1 | 1 | Feb 21, 2026 |
|---|
| Context-backchannel matching | 1 | 1 | Apr 21, 2026 |
|---|
| Cross-lexical backchannel similarity | 1 | 1 | Apr 21, 2026 |
|---|
| Speech-driven 3D talking head generation | 1 | 1 | Apr 21, 2026 |
|---|
| Expressive Speech-to-Speech Translation | 1 | 1 | Apr 21, 2026 |
|---|
| Many-to-one Audio Generation ((T+I) → A) | 1 | 1 | Feb 21, 2026 |
|---|
| Breathing pattern classification | 1 | 1 | Apr 21, 2026 |
|---|
| Speaker personality trait recognition | 1 | 1 | Feb 18, 2026 |
|---|
| 3D Sound Event Localization and Detection | 1 | 1 | Apr 21, 2026 |
|---|
| Text-to-(Image+Audio) Generation | 1 | 1 | Feb 21, 2026 |
|---|
| Timing-Controlled Audio Generation | 1 | 1 | Apr 21, 2026 |
|---|
| Intelligible Audio Generation | 1 | 1 | Apr 21, 2026 |
|---|
| Audio-to-(Text+Image) Generation | 1 | 1 | Feb 21, 2026 |
|---|