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 |
|---|---|---|---|---|
| Fake Speech Detection | 1 | 1 | Feb 18, 2026 | |
| Transcription Prediction | 1 | 1 | Feb 18, 2026 | |
| Speech reconstruction via differential pressure sensors | 1 | 1 | Mar 10, 2026 | |
| Audio-Visual Joint Reasoning | 1 | 1 | Feb 18, 2026 | |
| Audio-Visual Speaker Identification | 1 | 1 | Mar 10, 2026 | |
| Audio Multiple-Choice Question Answering | 1 | 1 | Mar 10, 2026 | |
| Sounding Object Localization | 1 | 1 | Feb 18, 2026 | |
| Close-ended Spoken Question Answering | 1 | 1 | Mar 10, 2026 | |
| Audio-driven face reenactment |
| 1 |
| 1 |
| Feb 18, 2026 |
| Joint Audio-Visual Generation | 1 | 1 | Mar 10, 2026 |
|---|
| Audio Bandwidth Extension (8→48 kHz) | 1 | 1 | Mar 10, 2026 |
|---|
| Streaming Speech Generation | 1 | 1 | Feb 18, 2026 |
|---|
| Audio Bandwidth Extension (12→48 kHz) | 1 | 1 | Mar 10, 2026 |
|---|
| Human evaluation of prosodic grounding and reasoning quality | 1 | 1 | Feb 18, 2026 |
|---|
| Audio Bandwidth Extension (16→48 kHz) | 1 | 1 | Mar 10, 2026 |
|---|
| Continuous Speech Recognition | 1 | 1 | Feb 18, 2026 |
|---|
| Affective vocal burst recognition (HIGH task) | 1 | 1 | Feb 18, 2026 |
|---|
| Voice Chatting | 1 | 1 | Feb 18, 2026 |
|---|
| Accented Speech Synthesis | 1 | 1 | Mar 10, 2026 |
|---|
| Long Audio-Video Question Answering | 1 | 2 | Feb 20, 2026 |
|---|
| Audio-visual Synchronization | 1 | 1 | Mar 10, 2026 |
|---|
| Affective vocal burst recognition (CULTURE task) | 1 | 1 | Feb 18, 2026 |
|---|
| MMI Scoring | 1 | 1 | Feb 18, 2026 |
|---|
| Acoustic Event Classification | 1 | 1 | Mar 10, 2026 |
|---|
| Vocal Imitation Classification | 1 | 1 | Mar 10, 2026 |
|---|