CHiME-6 Track 2: Unsegmented Speech Recognition
Models identify who spoke when and transcribe dinner party recordings without utterance boundaries. The organizers rank systems by word error rate after matching speakers.
Teams use licensed recordings from distant microphone arrays. The organizers also report errors in assigning speech to speakers.
- Made by
- CHiME Challenge organizers
- Released
- December 2019
- Kind
- Speech recognition and translation
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- A version of another benchmark
- In views
- Audio and speech
STC-innovations Ltd, ITMO University tops the leaderboard with 42.7%
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 1 STC-innovations Ltd, ITMO University B (unconstrained LM) 42.7%
- 2 Johns Hopkins University B (unconstrained LM) 67.5%
- 3 University of Science and Technology of China (USTC) B (unconstrained LM) 68.4%
- 4 Paderborn University B (unconstrained LM) 68.5%
- 5 Brno University of Technology B (unconstrained LM) 69%
- 6 Cloudwalk-XMU A (constrained LM) 72.5%
- 7 City University of New York A (constrained LM) 72.7%
- 8 Academia Sinica A (constrained LM) 73.5%
- 9 Baseline A (constrained LM) 77.9%
Source: Official CHiME-6 Track 2: Unsegmented Speech Recognition leaderboard
| # | Entry | Score | Setting | Submitted by | Date | Link | Source |
|---|---|---|---|---|---|---|---|
| 1 | STC-innovations Ltd, ITMO University | 42.7% | B (unconstrained LM) | STC-innovations Ltd, ITMO University | chimechallenge.github.io | Official leaderboard | |
| 2 | Johns Hopkins University | 67.5% | B (unconstrained LM) | Johns Hopkins University | chimechallenge.github.io | Official leaderboard | |
| 3 | University of Science and Technology of China (USTC) | 68.4% | B (unconstrained LM) | University of Science and Technology of China (USTC) | chimechallenge.github.io | Official leaderboard | |
| 4 | Paderborn University | 68.5% | B (unconstrained LM) | Paderborn University | chimechallenge.github.io | Official leaderboard | |
| 5 | Brno University of Technology | 69% | B (unconstrained LM) | Brno University of Technology | chimechallenge.github.io | Official leaderboard | |
| 6 | Cloudwalk-XMU | 72.5% | A (constrained LM) | Cloudwalk-XMU | chimechallenge.github.io | Official leaderboard | |
| 7 | City University of New York | 72.7% | A (constrained LM) | City University of New York | chimechallenge.github.io | Official leaderboard | |
| 8 | Academia Sinica | 73.5% | A (constrained LM) | Academia Sinica | chimechallenge.github.io | Official leaderboard | |
| 9 | Baseline | 77.9% | A (constrained LM) | Baseline | chimechallenge.github.io | Official leaderboard |
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy.
Qwen 3.8 Max 88.7%
- LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization.
Gemini 4 Argon 91.7%
- MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy.
Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy.
Qwen 3.8 Max 90.8%
- FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better.
Phi-4-multimodal 4.00%
- VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules.
Qwen3.5-Omni-Plus 93.1%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (9 entries).
- Pass Models scored 9 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
- Pass Importer We read the board on chimechallenge.github.io: 9 entries at the last read, none a model we track.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.