Repository
MM-Speech/DuplexSurvey
[EMNLP 2026 Main] Speaking While Listening: a survey and empirical audit of full-duplex spoken dialogue systems — L0–L3 architectural hierarchy, T×I×R interaction ontology, and a five-state decision machine, with a curated list of models, datasets, and benchmarks.
★ 111
Stars
3 forks · 2 open issues
+3.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
22.5
Momentum / 100
see the breakdown below
5mo ago
Created
last push 19d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 3.0 | +3.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.81× the monthly pace |
| Freshness | 15 | 13.6 | last push 19d ago; decays to zero at 180 days |
| Scale | 15 | 5.9 | 111 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 22.5 | sum of the above |
Detail
| Topics | awesome-listemnlp2026full-duplexlarge-language-modelsspeech-language-modelspeech-to-speechspoken-dialogue-systemsurveyturn-taking |
| Matched on | LLM & Inference (large-language-models) |
| Short window | +3 stars over 7 days = 0.4/day |
| Long window | +9 stars over 17 days = 0.5/day |
| Lifetime average | 0.68 stars/day over 164 days |
| First seen here | 2026-10-19 |
| Last read | 2d ago |