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 |
|---|---|---|---|---|
| Word-level gesture recognition | 1 | 1 | Jun 1, 2026 | |
| Generation Success Rate | 1 | 1 | Feb 21, 2026 | |
| Syllable prominence detection | 1 | 1 | Jun 2, 2026 | |
| Text-audio relevance prediction | 1 | 1 | Feb 21, 2026 | |
| Pitch reconstruction | 1 | 1 | Jun 2, 2026 | |
| Audio Frontend Inference | 1 | 1 | Jun 2, 2026 | |
| Emotion Regression | 1 | 1 | Feb 18, 2026 | |
| Video-Driven Text-to-Speech | 1 | 1 | Feb 18, 2026 | |
| Emotion Induction | 1 | 1 | Jun 2, 2026 | |
| Speech Recognition and Diarization |
|---|
| 1 |
| 1 |
| Jun 2, 2026 |
| Audio-driven head video generation | 1 | 1 | Jun 2, 2026 |
|---|
| Long-form Video Soundtrack Generation | 1 | 1 | Jun 2, 2026 |
|---|
| 3D Face Reconstruction from Voice | 1 | 1 | Feb 18, 2026 |
|---|
| Speech Prompted Semantic Segmentation | 1 | 1 | Feb 18, 2026 |
|---|
| Speech captioning | 1 | 1 | Jun 2, 2026 |
|---|
| Electrolarynx-to-Speech conversion | 1 | 1 | Jun 2, 2026 |
|---|
| Electro-Larynx-to-Speech (EL2SP) | 1 | 1 | Jun 2, 2026 |
|---|
| Sound Prompted Semantic Segmentation | 1 | 1 | Feb 18, 2026 |
|---|
| Electrolaryngeal-to-Speech conversion | 1 | 1 | Jun 2, 2026 |
|---|
| Electro-Larynx-to-Speech Conversion | 1 | 1 | Jun 2, 2026 |
|---|
| Music Information Retrieval | 1 | 1 | Feb 18, 2026 |
|---|
| Electrolaryngeal Speech-to-Speech (EL2SP) conversion | 1 | 1 | Jun 2, 2026 |
|---|
| Speaker / content factorisation gap | 1 | 1 | Jun 2, 2026 |
|---|
| Auditory Scene Analysis | 1 | 1 | Feb 21, 2026 |
|---|
| Dynamic K routing | 1 | 1 | Jun 2, 2026 |
|---|