Reproduce “Do Multi-Turn Conversational Capabilities Carry Over from Text to Speech? A Parallel Multilingual Benchmark” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jiaming Zhou, Pei Zhang, Shiwan Zhao, Zhijun Wang, Baosong Yang, Yong Qin
The authors introduce a multilingual benchmark asking whether transcript performance carries over to the same multi-turn conversations in speech. They compare matched transcript and audio conditions across six models and replace either preceding turns or the current turn with transcripts. Muse-Spark falls from 64.0% to 32.4% instance success, while Qwen3.8 remains near 60%; these results are benchmark-specific, not universal.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.