Audio QA

Training general-purpose Audio Large Language Models (ALLMs) across diverse datasets is essential for holistic audio understanding, yet it faces significant challenges due to dataset heterogeneity, which often leads to conflicting gradients and slow convergence. Despite its impact, how to explicitly manage this heterogeneity during training remains underexplored, with current practices relying primarily on uniform mixture. In this work, we analyze multi-dataset AudioQA training from a convergence perspective and propose Grouped Sequential Training (GST). GST strategically organizes datasets into affinity-aware groups and introduces them via a progressive scheduling protocol, effectively balancing the stability of parallel training with the efficiency of sequential optimization. To ensure scalability, we develop gradient-based affinity metrics that capture inter-dataset relationships without the prohibitive cost of empirical transferability estimation. Extensive evaluations on 14 AudioQA datasets spanning speech, music, and environmental sounds demonstrate that GST achieves 30--40% faster convergence than standard parallel training while maintaining or even surpassing the performance of mix-all training. Our results provide both theoretical insights and a practical, model-agnostic framework for efficient large-scale ALLM optimization.

Medical audio data is difficult to collect due to privacy regulations and high annotation costs arising from domain expertise. Thus, existing benchmarks tend to underrepresent complex medical audio scenarios. To address this challenge, we present MedMosaic, a medical audio question-answering dataset designed to benchmark language and audio reasoning models under realistic clinical constraints. MedMosaic features a diverse range of medical audio types, including condition-related physiological sounds, carefully constructed synthetic voices to mimic speech with artifacts as well as real short and long length clinical conversations to model varying context lengths. The dataset also features a total of 46,701 question-answer pairs, spanning categories such as multiple-choice, sequential multi-turn, and open-ended question-answers, enabling systematic evaluation of multi-hop reasoning and answer generation capabilities. Benchmarking 13 audio and multimodal reasoning models reveals that reasoning remains challenging for all evaluated systems, with substantial performance variation across question types. In particular, even state-of-the-art model like Gemini-2.5-pro can only achieve 68.1% accuracy approximately. These findings underscore persistent limitations in medical reasoning and highlight the need for more robust, domain-specific multimodal reasoning models. A sample of benchmark data is available here: https://shorturl.at/Lyp33

Large Audio-Language Models show consistent performance gains across speech and audio benchmarks, yet high scores may not reflect true auditory perception. If a model can answer questions without processing the acoustic signal, the benchmark fails as a measure of auditory understanding. We present a diagnostic framework using two axes: text prior, which measures answerability from text and general knowledge alone, and audio reliance, which assesses actual dependency on the acoustic signal. Evaluating eight LALMs across three benchmarks, we find that models retain 60-72% of their full audio scores even without any audio input. Moreover, among items that require audio, only 3.0-4.2% need the complete audio clip; the majority can be resolved using localized fragments. These findings challenge the assumption that benchmark performance equals robust audio understanding, and we conclude with practical guidelines for improving evaluation reliability and benchmark design.

Existing audio question answering benchmarks largely emphasize sound event classification or caption-grounded queries, often enabling models to succeed through shortcut strategies, short-duration cues, lexical priors, dataset-specific biases, or even bypassing audio via metadata and captions rather than genuine reasoning Thus, we present AUDITA (Audio Understanding from Diverse Internet Trivia Authors), a large-scale, real-world benchmark to rigorously evaluate audio reasoning beyond surface-level acoustic recognition. AUDITA comprises carefully curated, human-authored trivia questions grounded in real-world audio, designed to stress robust auditory reasoning through challenging distractors and long-range temporal dependencies, using probing queries that cannot be answered from isolated text or sound cues alone. Human average accuracy of 32.13% shows both the challenge of the task while demonstrating meaningful comprehension of the audio. In stark contrast, state of-the-art audio question answering models perform poorly, with average accuracy below 8.86%. Beyond raw accuracy, we apply Item Response Theory (IRT) to estimate latent proficiency, question difficulty, and expose systematic deficiencies of the models and data.

Recent Large Audio Language Models have demonstrated impressive capabilities in audio understanding. However, they often suffer from perceptual errors, while reliable audio reasoning is unattainable without first grounding the model's perception in structured auditory scenes. Inspired by Auditory Scene Analysis, we first introduce a Perception-Aware Question Answering (PAQA) dataset. PAQA implements a hierarchical decoupling strategy that separates speech from environmental sound and distinguishes multiple speakers, providing explicit perceptual reasoning for training. Building on this, we propose HyPeR, a two-stage Hybrid Perception-Reasoning framework. In Stage I, we finetune the model on PAQA to perceive acoustic attributes in complex audio. In Stage II, we leverage GRPO to refine the model's internal deliberation. We also introduce PAUSE tokens to facilitate latent computation during acoustically ambiguous phases and design perceptual consistency reward to align reasoning rationales with raw audio. Experiments across benchmarks demonstrate that HyPeR achieves absolute improvements over the base model, with performance comparable to large-scale models, stressing the effectiveness of hybrid perception-grounded reasoning for robust and multi-speaker audio understanding.

Recent work on music question answering (Music-QA) has primarily focused on single-track understanding, where models answer questions about an individual audio clip using its tags, captions, or metadata. However, listeners often describe music in comparative terms, and existing benchmarks do not systematically evaluate reasoning across multiple tracks. Building on the Jamendo-QA dataset, we introduce Jamendo-MT-QA, a dataset and benchmark for multi-track comparative question answering. From Creative Commons-licensed tracks on Jamendo, we construct 36,519 comparative QA items over 12,173 track pairs, with each pair yielding three question types: yes/no, short-answer, and sentence-level questions. We describe an LLM-assisted pipeline for generating and filtering comparative questions, and benchmark representative audio-language models using both automatic metrics and LLM-as-a-Judge evaluation.

Large Audio Language Models (LALMs) still struggle in complex acoustic scenes because they often fail to preserve task-relevant acoustic evidence before reasoning begins. We identify this error pattern as the evidence bottleneck: state-of-the-art systems show larger deficits in acoustic evidence extraction than in downstream reasoning, suggesting that upstream perception is often the limiting factor. To address this problem, we propose EvA (Evidence-First Audio), a dual-path architecture that enhances acoustic evidence preservation through hierarchical aggregation and non-compressive, time-aligned fusion. We also build EvA-Perception, a large-scale training set with about 54K event-ordered captions and 500K evidence-grounded QA pairs. Under a unified zero-shot protocol, EvA achieves the best open-source Perception results on MMAU, MMAR, and MMSU, with the largest gains on perception-heavy splits. Human evaluation on open-ended captioning further shows improved fine-grained acoustic coverage and caption quality. These results support the evidence-first hypothesis: stronger audio understanding depends on preserving acoustic evidence before reasoning. Project can be found at https://satsuki2486441738.github.io/EvA/.

Large audio language models (LALMs) can answer questions about speech, music, and environmental sounds, yet their internal reasoning is largely opaque and difficult to validate. We describe TalTech's solution to the Agent Track of the Interspeech 2026 Audio Reasoning Challenge, in which systems are evaluated on reasoning process quality, specifically the factual accuracy, logical soundness, and completeness of their reasoning chains. Our multi-source ensemble pipeline uses two LALMs that generate independent observations, while a separate text-only reasoning model cross-checks these against outputs from 25 acoustic tools organized into reliability tiers. By grounding every inference step in explicit, reliability-tagged evidence, the system produces dense, verifiable reasoning chains. Our system ranked first in the challenge, outperforming all competing systems by a wide margin in challenge's reasoning quality metric.

Conversational generative AI is increasingly explored in healthcare, where models must integrate heterogeneous patient signals and support diverse interaction styles while producing clinically meaningful outputs. In respiratory care, non-invasive audio recordings captured with sensing devices offer a scalable route to screening and longitudinal monitoring, but heterogeneity is particularly acute: recordings vary across devices, environments, and acquisition protocols, and queries may vary in intent, answer format, and prediction objective. Existing biomedical audio-language question answering systems for respiratory assessment are starting to emerge, but they are typically built as single-path models, processing all inputs through the same acoustic and language pathway despite variation in recording conditions and query types. They are also usually evaluated in relatively limited settings, leaving open their robustness under realistic distribution shifts, including changes in acquisition domains, modality, and clinical task. To address this gap, we introduce RAMoEA-QA, the first RA QA model designed to support input-dependent specialization across heterogeneous recordings and query types within a unified hierarchical two-stage framework. We study this design in a unified RA QA setting spanning clinical and self-recorded, multi-device acquisition settings, question formats, and both discrete and continuous targets. Across in-domain and controlled-shift evaluations, RAMoEA-QA improves over matched monolithic baselines and routing controls, reaching 0.72 in in-domain test accuracy (vs. 0.61 and 0.67 for single-path baselines) on discriminative tasks, while also achieving the best regression performance and stronger average transfer under dataset, modality, and task shifts, including gains of up to 23 percentage points in accuracy on the COPD modality-shift setting.

Answering natural-language questions over multi-hour audio requires reliable event recognition, temporal grounding, and efficient retrieval. We present LA-RAG (Long Audio Retrieval-Augmented Generation), a structured framework that converts audio into timestamped event records, stores them in an event database, and answers questions using intent-aware retrieval and LLM-based generation. LA-RAG supports two deployment settings: offline grounding mode, in which long recordings are pre-indexed for low-latency querying, and inference-time grounding mode, which performs query-conditioned grounding over shorter, open-ended clips. We evaluate LA-RAG on controlled 24-hour Home-IoT and Industrial-IoT benchmarks and on CASTELLA-QA, derived from real-world audio recordings. The results demonstrate effective long-audio question answering with low query-time latency after grounding and indexing. They also reveal a substantial gap between event detection and temporal localization in current large audio-language models, while showing that explicit timestamped grounding consistently improves temporal reasoning. These findings establish structured grounding and retrieval as a practical complement to generative audio-language models for deployment-oriented long-audio understanding.

As conversational multimodal AI tools are increasingly adopted to process patient data for health assessment, robust benchmarks are needed to measure progress and expose failure modes under realistic conditions. Despite the importance of respiratory audio for mobile health screening, respiratory audio question answering remains underexplored, with existing studies evaluated narrowly and lacking real-world heterogeneity across modalities, devices, and question types. We hence introduce the Respiratory-Audio Question-Answering (RA-QA) benchmark, including a standardized data generation pipeline, a comprehensive multimodal QA collection, and a unified evaluation protocol. RA-QA harmonizes public RA datasets into a collection of 9 million format-diverse QA pairs covering diagnostic and contextual attributes. We benchmark general audio-language models as well as domain-specific architectures, establishing reproducible reference points and showing how current approaches fail under heterogeneity.

Reliable assessment of the abilities of large audio language models (LALMs) is essential to advancing the state of the art. As benchmarks rapidly evolve to incorporate complex reasoning and subjective tasks, they increasingly necessitate open-ended responses from LALMs. We present Open-ended Response Correctness Assessment (ORCA) -- a reliable and lightweight model-based approach for answer correctness and disagreement modeling. We employ a three-stage annotation pipeline combining human judgment, structured feedback, and human-AI correction, yielding 9,663 annotations across 3,699 question-answer pairs from 15 LALMs on three audio understanding and reasoning benchmarks (achieving a Krippendorff's alpha of 0.82). Our experiments employing curriculum learning show that ORCA models achieve a Spearman correlation of 0.91 with average human correctness ratings on seen benchmarks and generalize to unseen benchmarks with a score of 0.85, outperforming several LLM judge baselines including Gemini 2.5 Flash. Furthermore, we demonstrate that ORCA's predicted variance correlates strongly with human disagreement, allowing it to effectively identify problematic benchmark items.

Large Audio-Language Models (LALMs) excel in Audio QA but often suffer from hallucinations ungrounded in the audio. To our knowledge, we are the first to propose applying vector steering to the audio domain to mitigate this. Unlike text-based steering, our silence-anchored contrastive approach steers the model away from hallucinations by contrasting active audio against a silent baseline. Probing internal states reveals a strong correlation between specific layer representations and output correctness. Leveraging this, we introduce Layer-Weighted Vector Steering (LWVS), a training-free intervention that increases steering strength at influential layers. On the Audio Hallucination QA dataset, LWVS significantly outperforms baselines, boosting Recall on the Gemma model by 15.6% (53.4% to 69.0%). Crucially, MMAU benchmark tests confirm LWVS preserves and even enhances general audio understanding, achieving an 8% relative accuracy increase on the Qwen model (54.8% to 59.2%).

Recent advances in large audio language models (LALMs) have primarily been assessed using a multiple-choice question answering (MCQA) framework. However, subtle changes, such as shifting the order of choices, result in substantially different results. Existing MCQA frameworks do not account for this variability and report a single accuracy number per benchmark or category. We dive into the MCQA evaluation framework and conduct a systematic study spanning three benchmarks (MMAU, MMAR and MMSU) and four models: Audio Flamingo 2, Audio Flamingo 3, Qwen2.5-Omni-7B-Instruct, and Kimi-Audio-7B-Instruct. Our findings indicate that models are sensitive not only to the ordering of choices, but also to the paraphrasing of the question and the choices. Finally, we propose a simpler evaluation protocol and metric that account for subtle variations and provide a more detailed evaluation report of LALMs within the MCQA framework.

Masked token prediction has emerged as a powerful pre-training objective across language, vision, and speech, offering the potential to unify these diverse modalities through a single pre-training task. However, its application for general audio understanding remains underexplored, with BEATs being the only notable example. BEATs has seen limited modifications due to the absence of open-source pre-training code. Furthermore, BEATs was trained only on AudioSet, restricting its broader downstream applicability. To address these gaps, we present OpenBEATs, an open-source framework that extends BEATs via multi-domain audio pre-training. We conduct comprehensive evaluations across six types of tasks, twenty five datasets, and three audio domains, including audio reasoning tasks such as audio question answering, entailment, and captioning. OpenBEATs achieves state-of-the-art performance on six bioacoustics datasets, two environmental sound datasets and five reasoning datasets, performing better than models exceeding a billion parameters at one-fourth their parameter size. These results demonstrate the effectiveness of multi-domain datasets and masked token prediction task to learn general-purpose audio representations. To promote further research and reproducibility, we release all pre-training and evaluation code, pretrained and fine-tuned checkpoints, and training logs at https://github.com/Shikhar-S/OpenBEATs