AnchorPrompt is an adaptation technique for large audio‑language models that keeps the base model frozen and learns a single block of prompt vectors inserted at the decoder input. By training these prompts through self‑distillation on diverse audio and text perturbations, the method improves answer consistency and reduces hallucinations across multiple benchmarks. The approach is perturbation‑agnostic at inference, enabling zero‑shot transfer to unseen distortions such as reverberation and choice permutations.
By Pooneh Mousavi, Amir Ivry, Mirco Ravanelli, Cem Subakan
arXiv:2509. 22363v4 Announce Type: replace Abstract: Large Audio Language Models (LALMs) integrate audio encoders with pretrained Large Language Models to perform complex multimodal reasoning tasks.
By Pooneh Mousavi, Lovenya Jain, Mirco Ravanelli, Cem Subakan
arXiv:2608. 09593v1 Announce Type: cross Abstract: Recent advances in speech synthesis and audio generation have made high-fidelity acoustic forgery low-cost and difficult to attribute, enabling a realistic attack scenario in which speech and background audio are independently manipulated over otherwise authentic video.
By Yanqiu Li, Yang Xiao, Jisheng Bai, Bin Chen, Hong Jia, Ting Dang
arXiv:2603. 10725v3 Announce Type: replace-cross Abstract: The modern generative audio models can be used by an adversary in an unlawful manner, specifically, to impersonate other people to gain access to private information.
By Artem Dvirniak, Evgeny Kushnir, Dmitrii Tarasov, Artem Iudin, Oleg Kiriukhin, Mikhail Pautov, Dmitrii Korzh, Oleg Y. Rogov
arXiv:2606. 10912v1 Announce Type: cross Abstract: Deepfake speech detectors often output a single score without explaining why an audio sample is flagged, where in the signal the evidence lies, or what cues drive the decision.
By Vojt\v{e}ch Stan\v{e}k, Veronika Jirmusov\'a, Anton Firc, Kamil Malinka, Jakub Re\v{s}, Martin Pere\v{s}\'ini
arXiv:2606. 16137v1 Announce Type: cross Abstract: Speech deepfake detection (SDD) systems require trustworthy explanations for reliable decision-making.
By Yupei Li, Qiyang Sun, Xiaoliang Wu, Chenxi Wang, Berrak Sisman, Bj\"orn W. Schuller
arXiv:2605. 16651v2 Announce Type: replace-cross Abstract: Explanation mechanisms are increasingly used to support transparency and trust in vision-language models (VLMs), particularly in settings where model decisions require human oversight.
By Narges Babadi, Hadis Karimipour
Video-HolmesV2 is a new benchmark that tests multimodal large language models on their ability to reason with spatio‑temporal audio‑visual evidence in long videos. It requires models to justify answers with precise evidence, uses a multi‑model cross‑verification pipeline and a spatio‑temporal evidence‑aware metric, and introduces an audio‑text guided token compression framework to reduce long‑context noise. In evaluations, even strong proprietary models score below 60% while the proposed approach outperforms comparable open‑source omni‑models.
By Zhaoyang Wei, Zipeng Wang, Yushe Cao, Chenhui Qiang, Shuaibing Cheng, Xuesong Yang, Sen Nie, Bowen Jiang, Wenchao Ding, Yanchao Hao, Zheng Wei, Xuehui Yu, Zhenjun Han
arXiv:2503. 17577v2 Announce Type: replace-cross Abstract: Deepfakes have emerged as a widespread and rapidly escalating concern in generative AI, spanning images, audio, and videos.
By Xiang Li, Pin-Yu Chen, Wenqi Wei
The paper introduces STAG, a post‑hoc framework that provides token‑level spectro‑temporal grounding for captions produced by audio‑based multimodal large language models (MLLMs). STAG estimates temporal support for each token via vocabulary projections of encoded audio, measures frequency‑band relevance through controlled spectral occlusion, and fuses these signals into a spectro‑temporal relevance map. Evaluations across ten explanation methods and four grounding benchmarks show that STAG achieves superior event‑localization performance on every dataset, and counterfactual deletion experiments confirm that removing the identified evidence selectively reduces model confidence and often eliminates the corresponding event from regenerated captions.
By Lucia Cascone, Valeria Fraenza, Michele Nappi, Fabio Narducci, Benedetto Simone
arXiv:2606. 14647v1 Announce Type: cross Abstract: Transformer-based automatic speech recognition (ASR) models such as Whisper are highly accurate, but their predictions remain difficult to interpret.
By Ravi Ranjan, Utkarsh Grover, Xiaomin Lin, Agoritsa Polyzou
arXiv:2608. 19936v1 Announce Type: cross Abstract: Public benchmarks are important measures of Automatic Speech Recognition (ASR) model capabilities.
By Theo Lebryk, David Ayllon, Alice Baird, Jakub Piotr C{\l}apa, Jens Madsen, Panagiotis Tzirakis