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 |
|---|---|---|---|---|
| Text-to-audio Grounding | 1 | 1 | Apr 2, 2026 | |
| End-to-end Speech Named Entity Recognition | 1 | 1 | Apr 3, 2026 | |
| Speech Named Entity Recognition | 1 | 1 | Apr 3, 2026 | |
| Speech Intent Classification and Slot Filling | 1 | 1 | Feb 18, 2026 | |
| Audio Aesthetic | 1 | 1 | Feb 19, 2026 | |
| Chord Steering | 1 | 1 | Apr 6, 2026 | |
| Phoneme Identity Classification | 1 | 1 | Apr 6, 2026 | |
| Speech Enhancement (3 Speakers) | 1 | 1 | Feb 18, 2026 | |
| Manner of Articulation Classification | 1 | 1 | Apr 6, 2026 |
| Place of Articulation Classification | 1 | 1 | Apr 6, 2026 |
|---|
| Video-to-Binaural Audio Generation | 1 | 1 | Feb 19, 2026 |
|---|
| Audio-driven Navigation | 1 | 4 | Apr 8, 2026 |
|---|
| Spatial Audio Synthesis | 1 | 1 | Apr 6, 2026 |
|---|
| Frame-level Spoofing Detection | 1 | 1 | Apr 6, 2026 |
|---|
| Lip synchronisation | 1 | 1 | Feb 18, 2026 |
|---|
| VAD Regression | 1 | 1 | Feb 20, 2026 |
|---|
| Audio Question | 1 | 1 | Apr 7, 2026 |
|---|
| ASR-OCR Alignment | 1 | 1 | Feb 20, 2026 |
|---|
| Audio-Visual Question | 1 | 1 | Apr 7, 2026 |
|---|
| Audio-driven half-body human video generation | 1 | 1 | Feb 18, 2026 |
|---|
| Holistic Audio Generation | 1 | 1 | Apr 7, 2026 |
|---|
| Lip motion prediction | 1 | 1 | Feb 18, 2026 |
|---|
| Speaker Identification in a Crowd | 1 | 1 | Feb 18, 2026 |
|---|
| Voice recognition | 1 | 2 | Mar 6, 2026 |
|---|
| Universal Holistic Audio Generation | 1 | 1 | Apr 7, 2026 |
|---|