DasanCallDial Benchmark

What is DasanCallDial?

Dialogue-level ASR error correction benchmark dataset with 1,974 dialogues and 115,460 utterances from Korean call center interactions.

Released

2026-09-09

Evaluates

General AI, Speech & Audio, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.09889

DasanCallDial paper

• Paper https://arxiv.org/abs/2609.09889

Which sources cite DasanCallDial?

• DasanCallDial

Related General AI, Speech & Audio, cs.CL benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench
• ActiveVision