Plan accuracy alone cannot show whether a speech-delivery decision follows its source: a fixed prior may match the original label yet fail to respond appropriately when a cue changes. VoxReason provides a 100-case verifier benchmark that holds each utterance fixed, edits one designated source-label cue, and scores cite...
Streaming spoken agents may produce the correct final action after acting too early. Final-turn scores do not reveal whether each observed speech prefix supports an exposed action. We introduce the Partial Speech Action Contract for Turn Taking in Speech Language Models (PACT-SLM), a controlled test that assigns the fi...
Text-output scores alone do not show whether quantization preserves performance on speech tasks whose target labels cannot be recovered from the transcript. We evaluate fixed mixed 4/8-bit Qwen2-Audio-7B-Instruct allocations averaging 6 and 7 bits per parameter on 508 English-to-German FLEURS utterances and on 512 RAVD...
Meng-Zhe Geng, Jin-Xin Ji, Jun-Hao Xu· 0 citations
A decision record is built with a passive detector score and a score from a probe applied to a marked copy to retain inspectable component fields while producing one scalar score for retrospective diagnosis and is not the strongest detector in this comparison.
Meng-Zhe Geng, Yu-Jia Lu, Manuela Kunz et al.· 0 citations
A benchmark isolates whether planned delivery is warranted by the record before waveform evaluation or listener studies are used, and recommends a deterministic verifier for source-grounded speech planning.
Meng-Zhe Geng· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
