音频问答 on 语音/音频论文速递 https://nanless.github.io/audio-paper-digest-blog/tags/%E9%9F%B3%E9%A2%91%E9%97%AE%E7%AD%94/ Recent content in 音频问答 on 语音/音频论文速递 Hugo zh-cn Wed, 29 Apr 2026 00:00:00 +0000 Advancing Speech Summarization in Multi-Modal LLMs with Reinforcement Learning https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-advancing-speech-summarization-in-multi-modal/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-advancing-speech-summarization-in-multi-modal/ 音频问答 | 7.0/10 AQUA-Bench: Beyond finding answers to knowing when there are None in Audio Question Answering https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-aqua-bench-beyond-finding-answers-to-knowing-when/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-aqua-bench-beyond-finding-answers-to-knowing-when/ 音频问答 | 7.0/10 AUDIOGENIE-Reasoner: A Training-Free Multi-Agent Framework for Coarse-to-Fine Audio Deep Reasoning https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-audiogenie-reasoner-a-training-free-multi-agent/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-audiogenie-reasoner-a-training-free-multi-agent/ 音频问答 | 7.0/10 Benchmarking Humans And Machines On Complex Multilingual Speech Understanding Tasks https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-benchmarking-humans-and-machines-on-complex/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-benchmarking-humans-and-machines-on-complex/ 音频问答 | 7.5/10 DSpAST: Disentangled Representations for Spatial Audio Reasoning with Large Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-dspast-disentangled-representations-for-spatial/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-dspast-disentangled-representations-for-spatial/ 音频问答 | 8.0/10 Efficient Audio-Visual Inference Via Token Clustering And Modality Fusion https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-efficient-audio-visual-inference-via-token/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-efficient-audio-visual-inference-via-token/ 音频问答 | 7.5/10 Enhancing Audio Question-Answering Performance Through Log-Likelihood Guided Reward Functions https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-enhancing-audio-question-answering-performance/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-enhancing-audio-question-answering-performance/ 音频问答 | 8.5/10 FastAV: Efficient Token Pruning for Audio-Visual Large Language Model Inference https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fastav-efficient-token-pruning-for-audio-visual/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fastav-efficient-token-pruning-for-audio-visual/ 音频问答 | 7.0/10 ICASSP 2026 - 音频问答 论文列表 https://nanless.github.io/audio-paper-digest-blog/posts/icassp2026-task-137/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/icassp2026-task-137/ 共 15 篇 ICASSP 2026 音频问答 方向论文 Improving Audio Question Answering with Variational Inference https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-improving-audio-question-answering-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-improving-audio-question-answering-with/ 音频问答 | 7.5/10 Keeping Models Listening: Segment- and time-aware attention rescaling at decoding time https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-keeping-models-listening-segment-and-time-aware/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-keeping-models-listening-segment-and-time-aware/ 音频问答 | 7.5/10 Mitigating Language Prior-Induced Hallucinations via Bi-Level Contrastive Decoding https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mitigating-language-prior-induced-hallucinations/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mitigating-language-prior-induced-hallucinations/ 多模态模型 | 7.5/10 Segmentwise Pruning in Audio-Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-segmentwise-pruning-in-audio-language-models/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-segmentwise-pruning-in-audio-language-models/ 音频问答 | 7.0/10 SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sightsound-r1-cross-modal-reasoning-distillation/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sightsound-r1-cross-modal-reasoning-distillation/ 音频问答 | 7.5/10 TAU: A Benchmark for Cultural Sound Understanding Beyond Semantics https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tau-a-benchmark-for-cultural-sound-understanding/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tau-a-benchmark-for-cultural-sound-understanding/ 音频问答 | 7.5/10 Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-Wise Distillation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-teaching-audio-models-to-reason-a-unified/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-teaching-audio-models-to-reason-a-unified/ 音频问答 | 7.0/10 Test-Time Scaling for Auditory Cognition in Audio Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-test-time-scaling-for-auditory-cognition-in-audio/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-test-time-scaling-for-auditory-cognition-in-audio/ 音频问答 | 7.0/10 TinyMU: A Compact Audio-Language Model for Music Understanding https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tinymu-a-compact-audio-language-model-for-music/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tinymu-a-compact-audio-language-model-for-music/ 音乐理解 | 7.5/10 Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-walking-through-uncertainty-an-empirical-study-of/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-walking-through-uncertainty-an-empirical-study-of/ 音频问答 | 7.5/10 All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-all-that-glitters-is-not-audio-rethinking-text/ Tue, 28 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-all-that-glitters-is-not-audio-rethinking-text/ 音频问答 | 6.5/10 Listening with Time: Precise Temporal Awareness for Long-Form Audio Understanding https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-listening-with-time-precise-temporal-awareness/ Tue, 28 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-listening-with-time-precise-temporal-awareness/ 音频场景理解 | 8.0/10 AUDITA: A New Dataset to Audit Humans vs. AI Skill at Audio QA https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-audita-a-new-dataset-to-audit-humans-vs-ai-skill/ Fri, 24 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-audita-a-new-dataset-to-audit-humans-vs-ai-skill/ 音频问答 | 6.5/10 Audio-Cogito: Towards Deep Audio Reasoning in Large Audio Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-audio-cogito-towards-deep-audio-reasoning-in/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-audio-cogito-towards-deep-audio-reasoning-in/ 本文旨在解决大型音频语言模型（LALMs）在复杂音频推理任务中能力不足、推理过程不透明的问题。**核心贡献**是提出了一个名为 **Audio-Cogito** 的完全开源解决方案，其核心是一个四阶段的自动化数据构建管道 **Cogito-Pipe**，用于生成高质量、多样化的音频推理链（CoT）数 Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-audio-deepthinker-progressive-reasoning-aware/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-audio-deepthinker-progressive-reasoning-aware/ 这篇论文旨在解决大型音频语言模型（LALMs）缺乏显式、高质量推理能力的问题。现有方法要么受限于监督数据的质量，要么使用粗糙的奖励，导致生成的思维链形式良好但缺乏声学依据。作者提出了**Audio-DeepThinker**框架，其核心贡献有三：1）设计了一种**混合推理相似度奖励**，结合LLM评 Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-temporal-contrastive-decoding-a-training-free/ Mon, 20 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-temporal-contrastive-decoding-a-training-free/ 统一的大型音频-语言模型（LALMs）在自回归解码时存在“时间平滑偏差”：短暂、瞬态的声学线索（如电话铃声、乐器拨弦）容易被语言先验和时间上平滑的上下文所淹没，导致生成结果缺乏音频特异性。本文提出 Temporal Contrastive Decoding (TCD)，一种完全免训练、仅在推理时生效