Qwen-Audio-Jev：面向音频决策的统一接口

View PDF HTML (experimental)

Abstract:Large audio language models (LALMs) have made substantial progress in audio understanding. However, in high-throughput applications requiring frequent selection, judgment, and scoring, autoregressive text generation introduces additional computational overhead and response latency. To address this limitation, we introduce Qwen-Audio-Jev by augmenting Qwen-Audio-3.1-ASR-Flash-Next with a dedicated Jev decision head. The model unifies selection, binary judgment, and scoring through three decision primitives: CHOICE, NOUL, and SCORE. Given audio, a natural-language question, and an explicit answer specification, it directly produces a task-conditioned probability distribution or a numerical score through typed decision readouts. Evaluation across 18 labeled configurations covers all three primitives: for CHOICE, Qwen-Audio-Jev achieves accuracies of 78.70% on MMAU-mini and 84.06% on MMSU; for NOUL, it achieves an equal error rate of 6.50% on the VoxCeleb1-O speaker verification benchmark; and for SCORE, the model achieves a normalized mean absolute error of 0.1062 on NISQA overall quality assessment, with Pearson and Spearman correlations of 0.8210 and 0.8074, respectively. Compared with the original Qwen-Audio-3.1-ASR-Flash-Next, Qwen-Audio-Jev achieves an approximately 20x inference speedup. It demonstrates its potential for efficient, high-throughput audio decision-making in applications such as large-scale audio screening, speaker verification, and automated quality assessment.

Subjects:	Sound (cs.SD); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.21614 [cs.SD]
	(or arXiv:2610.21614v1 [cs.SD] for this version)
	https://doi.org/10.48550/arXiv.2610.21614 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Qing Gu [view email]
[v1] Thu, 15 Oct 2026 09:59:07 UTC (129 KB)