The paper introduces MixAgent, an agentic pipeline for music post‑production that emulates audio engineers’ workflow to create interpretable and editable mixing plans guided by a reference song. It employs a grouping agent to cluster related tracks, a planning agent to select and order audio effects, and a detector‑critic pair to refine the mix by identifying needed corrections and proposing parameter adjustments. The authors also present MixCritic, a dataset of 45,657 repair critiques, and demonstrate that supervised fine‑tuning followed by preference optimization improves mix quality, achieving a 19% error reduction on MedleyDB and outperforming several large language models in human listening tests.
By Jaywon Koo, Junghyun Koo, Marco A. Martinez-Ramirez, Wei-Hsiang Liao, Seungheon Doh, Qiyu Wu, Vicente Ordonez, Yuki Mitsufuji
SpeechCritic learns a diagnostic speech judge from only about 300 human-labeled comparisons, calibrating a frontier audio-language model with non-binding hints that select acoustic measurements agreeing with human judgments. The approach improves dimension-level agreement by 6.3 points and reduces mismatch in Tie rates by 10.4 points, and training a 7B judge with SFT, OPD, and RL yields distinct behaviors, with RL producing more specific rationales. The method works across language pairs, demonstrating a path from limited human preferences to a diagnostic speech judge.
By Mingyue Huo, Shivam Mehta, Bhavin Jawade, Yinghong Lan, Haoqi Li
Audio-language models (ALMs) are increasingly used as judges for speech-to-speech systems, but a judge that receives audio may not actually use paralinguistic evidence. We introduce counterfactual audits for paralinguistic response evaluation.
Large Audio-Language Models (LALMs) have been widely used as judge models for the automatic evaluation of generated speech. However, prior approaches predominantly focus on holistic naturalness, leaving fine-grained paralinguistic distinctions underexplored.
arXiv:2607. 13408v1 Announce Type: cross Abstract: Recent text-to-audio models generate high-quality audio, but often fail to follow instructions involving multiple sound events and temporal order.
By Chun-Yi Kuan, Siwon Kim, Byeonggeun Kim, Suyoun Kim, Bo-Ru Lu, Qinming Tang, Ankur Gandhe, Hung-yi Lee, Chieh-Chi Kao, Chao Wang
arXiv:2606. 27536v1 Announce Type: cross Abstract: Speech emotion recognition (SER) often relies on hard consensus labels that collapse annotator disagreement.
By Zahra Omidi, John H. L. Hansen
arXiv:2609.33212v2 Announce Type: replace
Abstract: Speaker verification systems achieve high accuracy but provide little account of the acoustic evidence behind their judgments. Making these systems...
By Massa Baali, Sarthak Bisht, Ziyue Qiu, Joseph Konan, Rita Singh, Bhiksha Raj
The paper investigates what open audio‑language models actually attend to when judging generated music. By designing four probes—removing audio, swapping clips, changing clip order, and rewording instructions—the authors test whether the models respond to the music, the text prompt, or the question framing. Across five judges and thousands of clips, the results show that most models rely on the prompt alone, only a few follow the audio for prompt alignment, and instruction wording can shift correlations as much as changing the model itself.
By Mateusz Modrzejewski, Tomasz Radzikowski
DEAF (Diagnostic Evaluation of Acoustic Faithfulness) is a benchmark comprising over 2,700 conflict stimuli that test Audio Multimodal Large Language Models (Audio MLLMs) across three acoustic dimensions: emotional prosody, background sounds, and speaker identity. The benchmark uses a controlled multi-level evaluation framework that gradually increases textual influence, from semantic conflicts to misleading prompts, to separate content-driven bias from prompt-induced sycophancy. Diagnostic metrics are introduced to measure how much models rely on textual cues versus acoustic signals, and an evaluation of seven Audio MLLMs shows that while models respond to acoustic variations, their predictions are largely driven by textual inputs, highlighting a gap between benchmark performance and true acoustic understanding.
By Jiaqi Xiong, Yunjia Qi, Qi Cao, Yu Zheng, Yutong Zhang, Ziteng Wang, Ruofan Liao, Weisheng Xu, Sichen Liu
AVERT is a method for spoken dialogue state tracking that improves upon a per-turn text editor by incorporating an audio-conditioned verifier to score candidate slot values. It addresses three types of recoverable errors—inconsistent values across turns, omitted slots, and values unsupported by audio—using three specialized operators: vote, add, and swap, each limited to relevant slots. On the SpokenWOZ dataset, AVERT achieves a joint goal accuracy of 40.13, surpassing both a base speech-LLM (33.04) and a text editor (38.34) without retraining, and matching the performance of a larger end‑to‑end system that processes the full spoken history.
By Chunggi Lee, Hanspeter Pfister
The paper introduces ContraTalk, a benchmark that tests whether dialogue models truly use acoustic cues or rely on transcript shortcuts. It formalizes cross‑modal disagreement, creates conflict and consistent QA examples, and proposes an Audio Twin representation to expose acoustic evidence to models. Experiments show that while text‑only LLMs perform well on consistent cases, they falter on conflict cases, and AudioLLMs only partially mitigate this issue.
By Yen-Ju Lu, Yuzhe Wang, Yaohan Guan, Xiluo He, Jiarui Hai, Mingrui Liang, Kaavya Chaparala, Thomas Thebaud, Laureano Moro-Velazquez, Najim Dehak, Jesus Villalba
arXiv:2608. 19515v1 Announce Type: new Abstract: Prosodic cues can convey task-relevant information that alters the trajectory and outcome of a task-oriented dialogue, even when the words themselves remain unchanged.
By Xinyi Liu, Hooshang Nayyeri, Dilek Hakkani-Tur, Emine Yilmaz, JK Kim, Yifei Zhang, Charith Peris, Hari Thadakamalla