60
47
30
45
30
60
57
42
30
30
60
30
42
57
55
30
30
57
60
ECHO: A Matched-Contrast Benchmark for Context-Sensitive Turn-Taking in Full-Duplex Dialogue
ECHO benchmark pairs identical-overlap Chinese dialogue examples with contrasting contexts, revealing most full-duplex systems bias toward yielding the floor.
ECHO is a paired diagnostic benchmark for Chinese full-duplex turn-taking that matches examples with identical overlap transcripts but contrasting preceding multi-turn contexts, one requiring Yield and the other Keep. It also includes off-talk examples for diagnosing unnecessary yielding and introduces pair accuracy, which grants no credit to constant-action policies. Experiments across multiple full-duplex systems show most exhibit a pronounced Yield bias, performing substantially better on interruptions than backchannels. The benchmark and metadata will be publicly released.
40
42
30
30
30
47
42
60
30
42
30
45
55
42
30
30
42
57
60
42
60