Audio-Language Models

Follow this topic Ask about this topic

Audio-language models learn to connect speech, music, and environmental sounds with language so they can answer questions, describe events, retrieve audio, and generate speech or music. Common approaches align audio and text with contrastive dual encoders, or connect audio encoders to language models through projectors, discrete tokens, or continuous representations; training often combines large-scale pretraining with instruction tuning and preference or reinforcement learning. Benchmarks increasingly test temporal grounding, overlapping sounds, multilingual speech, and conversational or clinical settings, alongside standard captioning and question-answering tasks. A central challenge is ensuring answers actually depend on acoustic evidence rather than text priors, while improving robustness, faithful reasoning, and efficiency.

Latest papers

303 papers55 papers in the last four weeks, up 22% on the four weeks before. 0.3% of all new papers.

Mar 9, 2026

Disentangling Reasoning in Large Audio-Language Models for Ambiguous Emotion Prediction

Speech emotion recognition plays an important role in various applications. However, most existing approaches predict a single emotion label, oversimplifying the inherently ambiguous nature of human emotional expression. Recent large audio-language models show promise in generating richer outputs, but their reasoning ability for ambiguous emotional understanding remains limited. In this work, we reformulate ambiguous emotion recognition as a distributional reasoning problem and present the first systematic study of ambiguity-aware reasoning in LALMs. Our framework comprises two complementary components: an ambiguity-aware objective that aligns predictions with human perceptual distributions, and a structured ambiguity-aware chain-of-thought supervision that guides reasoning over emotional cues. Experiments on IEMOCAP and CREMA-D demonstrate consistent improvements across SFT, DPO, and GRPO training strategies.

Xiaofeng Yu, Jiaheng Dong, Jean Honorio +3

University of Auckland, New Zealand · The University of Melbourne, Australia · University of Birmingham, United Kingdom

Speech Emotion Recognition Emotion Recognition Audio-Language Models CoT Reasoning Label Distribution Learning

Mar 9, 2026

Patient-Level Multimodal Question Answering from Multi-Site Auscultation Recordings

Auscultation is a vital diagnostic tool, yet its utility is often limited by subjective interpretation. While general-purpose Audio-Language Models (ALMs) excel in general domains, they struggle with the nuances of physiological signals. We propose a framework that aligns multi-site auscultation recordings directly with a frozen Large Language Model (LLM) embedding space via gated cross-attention. By leveraging the LLM's latent world knowledge, our approach moves beyond isolated classification toward holistic, patient-level assessment. On the CaReSound benchmark, our model achieves a state-of-the-art 0.865 F1-macro and 0.952 BERTScore. We demonstrate that lightweight, domain-specific encoders rival large-scale ALMs and that multi-site aggregation provides spatial redundancy that mitigates temporal truncation. This alignment of medical acoustics with text foundations offers a scalable path for bridging signal processing and clinical assessment.

Fan Wu, Tsai-Ning Wang, Nicolas Zumarraga +8

Agentic Systems Lab, ETH Zurich Switzerland · Eindhoven University of Technology Netherlands · Centre for Digital Health Interventions, ETH Zurich +2

Audio-Text Alignment Clinical QA Audio-Language Models Respiratory Sound Classification

Mar 6, 2026

Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio Steering

Multimodal large language models can exhibit text dominance, over-relying on linguistic priors instead of grounding predictions in non-text inputs. One example is large audio-language models (LALMs) where decisive audio evidence can be under-utilized even when it contains important information. To address this issue we use mechanistic interpretability to identify a small set of audio-specialist attention heads whose audio attention yields a ``listening'' signal. We show that this signal increases when audio evidence affects the model's output, providing an indicator of audio engagement under standard prompting. Leveraging this localization, we construct an audio--silence steering direction and apply an inference-time activation intervention to the final representation, amplifying the model's audio effect. To demonstrate the utility of this intervention, we show on MMAU that this improves accuracy by up to +8.0 percentage points on two Qwen-based LALMs, without any parameter updates.

Neta Glazer, Lenny Aharon, Ethan Fetaya

Bar-Ilan University, Ramat Gan, Israel · Columbia University, New York, NY, USA

Audio-Language Models Audio-Language Model Evaluation Causal Interventions in Language Models

Mar 6, 2026

RAMoEA-QA: Hierarchical Specialization for Robust Respiratory Audio Question Answering

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.

Gaia A. Bertolino, Yuwei Zhang, Tong Xia +2

University of Cambridge, United Kingdom · Tsinghua University, China · University of Calabria, Italy

Audio QA Medical QA Audio-Language Models Domain Generalization Mixture of Experts

Mar 5, 2026

PolyBench: A Benchmark for Compositional Reasoning in Polyphonic Audio

Large Audio Language Models (LALMs) are increasingly capable of reasoning over audio, yet existing benchmarks offer limited coverage of reasoning in polyphonic audio, where multiple sound events co-occur and induce compositional structure. To address this gap, we introduce PolyBench, a benchmark designed to evaluate compositional reasoning in polyphonic audio, comprising five evaluation subsets that cover counting, classification, detection, concurrency, and duration estimation, all of which require reasoning over multiple concurrent events and their relations. Our evaluation of state-of-the-art LALMs reveals consistent performance degradation in polyphonic settings, indicating a fundamental bottleneck in current LALMs.

Yuanjian Chen, Yang Xiao, Han Yin +3

Harbin University of Science and Technology, China · The University of Melbourne, Australia · KAIST, South Korea +1

Audio Reasoning Audio-Language Model Evaluation Compositional Reasoning Audio-Language Models

Mar 5, 2026

TW-Sound580K: A Regional Audio-Text Dataset with Verification-Guided Curation for Localized Audio-Language Modeling

Large Audio-Language Models (LALMs) typically struggle with localized dialectal prosody due to the scarcity of specialized corpora. We present TW-Sound580K, a Taiwanese audio-text instruction dataset developed through a Verify-Generate-Critique (VGC) protocol. This pipeline leverages Dual-ASR validation to filter 522K raw clips, subsequently expanding them into 580,000 high-fidelity instruction pairs using a teacher model. The dataset's utility is demonstrated through Tai-LALM, which fine-tunes a DeSTA 2.5-Audio-initialized backbone and incorporates a dynamic Dual-ASR Arbitration strategy to optimize transcription selection during inference. On the TAU Benchmark, Tai-LALM reaches 49.1% accuracy, marking a 6.5% absolute improvement over the zero-shot baseline (42.6% with ASR text conditioning). This confirms that integrating regional corpora with rigorous curation and dynamic arbitration significantly enhances LALM performance on localized speech.

Hao-Hui Xie, Ho-Lam Chung, Yi-Cheng Lin +4

National Taiwan University · Shanghai Jiao Tong University

Audio-Language Models Speech Processing

Mar 5, 2026

Focus Then Listen: An Empirical Study of Plug-and-Play Audio Enhancer for Noise-Robust Large Audio Language Models

Large audio language models (LALMs) are a class of foundation models for audio understanding. Existing LALMs tend to degrade significantly in real-world noisy acoustic conditions where speech and non-speech sounds interfere. While noise-aware fine-tuning can improve robustness, it requires task-specific noisy data and expensive retraining, limiting scalability. To address this issue, we propose Focus-Then-Listen (FTL), a plug-and-play audio enhancer that improves LALMs' noise robustness. Specifically, FTL first separates the input waveform into speech and non-speech, and a modality router is applied to predict the target audio modality (e.g., speech) based on the user's instruction. Finally, a modality-aware fusion block generates a task-adaptive enhanced signal for improved downstream perception and reasoning. Experiments across multiple LALMs and tasks show that FTL improves performance across different noise levels without fine-tuning on LALMs.

Han Yin, Yang Xiao, Younghoo Kwon +2

School of Electrical Engineering, KAIST, Daejeon, Republic of Korea · University of Melbourne, Australia

Audio Understanding Audio-Language Models Speech Enhancement Noise Robustness Audio Source Separation

Mar 4, 2026

A Sensitivity Analysis of Multi-Event Audio Grounding in Audio LLMs

Audio LLMs have shown a strong ability to understand audio samples, yet their reliability in complex acoustic scenes remains under-explored. Unlike prior work limited to small scale or less controlled query construction, we present a large-scale evaluation of event grounding and false alarms as auditory scene complexity increases. Using 71K AudioCapsV2 clips, we extract normalized (source, attribute) events and build two query types: present-event queries for ground-truth detection and absent-event queries to probe hallucinations, using similarity-filtered negative sampling in an audio-aligned text embedding space. We evaluate four SOTA Audio LLMs with 12 prompt variants over 500K yes/no queries per model. Across models, increasing event count consistently lowers true-positive rate and raises false-positive rate, while prompts induce a strong trade-off between the two. Our confidence analysis shows that models become more uncertain on multi-event audio, revealing room for improvement.

Taehan Lee, Jaehan Jung, Hyukjun Lee

Sogang University, South Korea

Audio-Language Model Evaluation Audio-Language Models Audio-Language Model Hallucination Detection

Feb 28, 2026

When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning

Test-Time Scaling has shown notable efficacy in addressing complex problems through scaling inference compute. However, within Large Audio-Language Models (LALMs), an unintuitive phenomenon exists: post-training models for structured reasoning trajectories results in marginal or even negative gains compared to post-training for direct answering. To investigate it, we introduce CAFE, an evaluation framework designed to precisely quantify audio reasoning errors. Evaluation results reveal LALMs struggle with perception during reasoning and encounter a critical bottleneck: reasoning performance suffers from audio perception decay as reasoning length extends. To address it, we propose MPAR

^2

, a paradigm that encourages dynamic perceptual reasoning and decomposes complex questions into perception-rich sub-problems. Leveraging reinforcement learning, MPAR

^2

improves perception performance on CAFE from 31.74% to 63.51% and effectively mitigates perception decay, concurrently enhancing reasoning capabilities to achieve a significant 74.59% accuracy on the MMAU benchmark. Further analysis demonstrates that MPAR

^2

reinforces LALMs to attend to audio input and dynamically adapts reasoning budget to match task complexity.

Ruixiang Mao, Xiangnan Ma, Dan Chen +12

Northeastern University,China · NiuTrans Research.

Audio Reasoning Audio Understanding Audio-Language Models

Feb 27, 2026

StethoLM: Audio Language Model for Cardiopulmonary Analysis Across Clinical Tasks

Listening to heart and lung sounds - auscultation - is one of the first and most fundamental steps in a clinical examination. Despite being fast and non-invasive, it demands years of experience to interpret subtle audio cues. Recent deep learning methods have made progress in automating cardiopulmonary sound analysis, yet most are restricted to simple classification and offer little clinical interpretability or decision support. We present StethoLM, the first audio-language model specialized for cardiopulmonary auscultation, capable of performing instruction-driven clinical tasks across the full spectrum of auscultation analysis. StethoLM integrates audio encoding with a medical language model backbone and is trained on StethoBench, a comprehensive benchmark comprising 77,027 instruction-response pairs synthesized from 16,125 labeled cardiopulmonary recordings spanning seven clinical task categories: binary classification, detection, reporting, reasoning, differential diagnosis, comparison, and location-based analysis. Through multi-stage training that combines supervised fine-tuning and direct preference optimization, StethoLM achieves substantial gains in performance and robustness on out-of-distribution data. Our work establishes a foundation for instruction-following AI systems in clinical auscultation.

Yishan Wang, Tsai-Ning Wang, Mathias Funk +1

Eindhoven University of Technology

Audio-Language Models Respiratory Sound Classification

Feb 25, 2026

Evaluation of Audio Language Models for Fairness, Safety, and Security

Audio large language models (ALLMs) have recently advanced spoken interaction by integrating speech processing with large language models. However, existing evaluations of fairness, safety, and security (FSS) remain fragmented, largely because ALLMs differ fundamentally in how acoustic information is represented and where semantic reasoning occurs. Differences that are rarely made explicit. As a result, evaluations often conflate structurally distinct systems, obscuring the relationship between model design and observed FSS behavior. In this work, we introduce a structural taxonomy (system-level and representational) of ALLMs that categorizes systems along two axes: the form of audio input representation (e.g., discrete vs. continuous) and the locus of semantic reasoning (e.g., cascaded, multimodal, or audio-native). Building on the taxonomy, we propose a unified evaluation framework that assesses semantic invariance under paralinguistic variation, refusal and toxicity behavior under unsafe prompts, and robustness to adversarial audio perturbations. We apply this framework to two representative systems and observe systematic differences in refusal rates, attack success, and toxicity between audio and text inputs. Our findings demonstrate that FSS behavior is tightly coupled to how acoustic information is integrated into semantic reasoning, underscoring the need for structure-aware evaluation of audio language models.

Ranya Aloufi, Srishti Gupta, Soumya Shaw +2

Audio-Language Model Evaluation Audio-Language Models LLM Security Adversarial Robustness of Language Models

Feb 25, 2026

SGPA: Spectrogram-Guided Phonetic Alignment for Feasible Shapley Value Explanations in Multimodal Large Language Models

Explaining the behavior of end-to-end audio language models via Shapley value attribution is intractable under native tokenization: a typical utterance yields over

150

encoder frames, inflating the coalition space by roughly

10^{42}

relative to text; individual audio frames lack standalone meaning; and token boundaries that bisect phonetic transitions introduce masking artifacts. We introduce Spectrogram-Guided Phonetic Alignment (SGPA), a four-stage pipeline that combines Connectionist Temporal Classification forced alignment with spectral boundary refinement to produce acoustically stable, word-aligned audio segments. Controlled diagnostics on LFM2-Audio-1.5B with VoiceBench show that SGPA yields a 43

\times

reduction in model evaluations. Statistical testing confirms that SGPA significantly alters attribution concentration while preserving the global cumulative profile, establishing it as a feasibility-enabling layer for audio explainability.

Paweł Pozorski, Jakub Muszyński, Maria Ganzha

Warsaw University of Technology, Warsaw, Poland

Shapley Value Attribution Audio-Language Models

Feb 20, 2026

Re-purposing Multimodal Large Language Models for Audio-Text Retrieval

Audio-text retrieval is crucial for bridging acoustic signals and natural language. While contrastive dual-encoder architectures like CLAP have shown promise, they are fundamentally limited by the capacity of small-scale encoders. Specifically, the text encoders struggle to understand complex queries that require reasoning or world knowledge. In this paper, we propose AuroLA, a novel contrastive language-audio pre-trained model that re-purposes Multimodal Large Language Models (MLLMs) as a unified backbone for audio-text retrieval. Specifically, we make the following contributions: (i) we construct a scalable data pipeline that curates diverse audio from multiple sources and generates multi-granular captions, ranging from long descriptions to structured tags, via automated annotation; (ii) we adapt an MLLM for retrieval by prompting it to summarise the audio/text input and using the hidden state of a special token as audio/text embeddings. (iii) extensive experiments demonstrate that AuroLA consistently outperforms state-of-the-art dual-encoder models, including the recent PE-AV. This validates the effectiveness of MLLM as a unified backbone for audio-text retrieval.

Jilan Xu, Carl Thomé, Danijela Horak +2

Visual Geometry Group, University of Oxford · Epidemic Sound · School of Artificial Intelligence, Shanghai Jiao Tong University

Multimodal Large Language Models Audio Understanding Audio-Language Models Audio-Text Retrieval Multimodal Contrastive Learning

Feb 19, 2026

AudioChat: Unified Audio Storytelling, Editing, and Understanding with Transfusion Forcing

Despite recent breakthroughs, audio foundation models struggle in processing complex multi-source acoustic scenes. We refer to this challenging domain as audio stories, which can have multiple speakers and background/foreground sound effects. Compared to traditional audio processing tasks, audio stories introduce new layers of semantic, temporal, and physical complexity. To address this challenge, we propose AudioChat, a framework for developing audio foundation models that can generate, edit, and understand audio stories. AudioChat introduces a new paradigm in which LLM-based toolcalling agents simulate interactions between users and the system, and these simulated dialogues are used as training data. We also introduce a novel Audio Transfusion Forcing objective to train the AudioChat model, allowing it to simultaneously decompose high-level instructions via structured chain-of-thought reasoning and perform interactive multi-turn audio understanding/generation. To evaluate generation and editing performance, we develop three new metrics that directly measure task performance instead of relying upon distribution-based scoring. We highly encourage readers to visit our demo to better understand the capabilities of AudioChat: https://wanchichen.github.io/audiochat/.

William Chen, Prem Seetharaman, Rithesh Kumar +4

Adobe Research · Language Technologies Institute, Carnegie Mellon University · OpenAI

Audio-Language Models Audio Understanding Audio Editing

Feb 18, 2026

Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens

Current audio language models are predominantly text-first, either extending pre-trained text LLM backbones or relying on semantic-only audio tokens, limiting general audio modeling. This paper presents a systematic empirical study of native audio foundation models that apply next-token prediction to audio at scale, jointly modeling semantic content, acoustic details, and text to support both general audio generation and cross-modal capabilities. We provide comprehensive empirical insights for building such models: (1) We systematically investigate design choices -- data sources, text mixture ratios, and token composition -- establishing a validated training recipe. (2) We conduct the first scaling law study for discrete audio models via IsoFLOP analysis on 64 models spanning

3{\times}10^{18}

to

3{\times}10^{20}

FLOPs, finding that optimal data grows 1.6

\times

faster than optimal model size. (3) We apply these lessons to train SODA (Scaling Open Discrete Audio), a suite of models from 135M to 4B parameters on 500B tokens, comparing against our scaling predictions and existing models. SODA serves as a flexible backbone for diverse audio/text tasks -- we demonstrate this by fine-tuning for voice-preserving speech-to-speech translation, using the same unified architecture.

Potsawee Manakul, Woody Haosheng Gan, Martijn Bartelds +3

Stanford University · SCB 10X · University of Southern California +2

Audio-Language Models Audio Generation

Feb 18, 2026

Spatial Audio Question Answering and Reasoning on Dynamic Source Movements

Spatial audio understanding aims to enable machines to interpret complex auditory scenes, particularly when sound sources move over time. In this work, we study Spatial Audio Question Answering (Spatial AQA) with a focus on movement reasoning, where a model must infer object motion, position, and directional changes directly from stereo audio. First, we introduce a movement-centric spatial audio augmentation framework that synthesizes diverse motion patterns from isolated mono audio events, enabling controlled and scalable training data generation. Second, we propose an end-to-end multimodal finetuning approach with a thinking mode, which allows audio-language models to produce explicit intermediate reasoning steps before predicting an answer. Third, we investigate the impact of query-conditioned source separation as a preprocessing stage and compare three inference regimes: no masking, an audio grounding model (AGM), and ground-truth masks. Our results show that reasoning amplifies the benefits of source separation, with thinking mode showing significant improvement of +5.1% when a single event is present in the question. These findings highlight the interplay between movement modeling, reasoning, and separation quality, offering new insights for advancing spatial audio understanding.

Arvind Krishna Sridhar, Yinyi Guo, Erik Visser

Qualcomm Technologies Inc. San Diego, CA

Spatial Audio Audio Reasoning Audio-Language Models Data Augmentation

Feb 16, 2026

Event-Grounded Question Answering over Long Audio via Structured Retrieval

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.

Kartik Hegde, Arvind Krishna Sridhar, Naveen Vakada +2

Qualcomm Technologies, Inc., India · Qualcomm Technologies, Inc., USA

Multimodal RAG Audio QA Audio Understanding Audio-Language Models Temporal Audio Grounding Temporal QA

Feb 16, 2026

Hello-Chat: Towards Realistic Social Audio Interactions

Recent advancements in Large Audio Language Models (LALMs) have demonstrated exceptional performance in speech recognition and translation. However, existing models often suffer from a disconnect between perception and expression, resulting in a robotic "read-speech" style that lacks the spontaneity and emotional resonance of real human interaction. In this report, we introduce Hello-Chat, an end-to-end audio language model designed for realistic social scenarios. By leveraging a massive dataset of real-life conversations and employing a modality-interleaved training strategy, Hello-Chat achieves a breakthrough in anthropomorphic generation. Experimental results show that our model not only reaches state-of-the-art (SOTA) performance on specific audio understanding tasks but also significantly outperforms existing baselines in prosodic naturalness and emotional alignment, paving the way for the next generation of empathetic AI agents.

Yueran Hou, Peilei Jia, Zihan Sun +5

Expressive Speech Synthesis Audio-Language Models Spoken Dialogue Systems Emotion-Aware Dialogue Generation Text-to-Speech

Feb 10, 2026

Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization

Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timestamps as sequences of text tokens, which discards the frame-level representations in favor of autoregressive decoding. However, generating timestamps as tokens is slow and not parallelizable, and tends to hallucinate when producing timestamps outside the training distribution. We propose internal frame-level reuse, a method that trains audio LMs to reuse their own internal audio representations for temporal localization directly, bypassing token generation altogether. We introduce a lightweight prediction head trained via different frame-level objectives: a binary frame classifier and a novel inhomogeneous Poisson process (IHP) loss that models temporal event intensity. Across word localization, speaker diarization, and event localization tasks, our approach can achieve a >50x inference speedup over token-based generation and demonstrates robust length generalization, maintaining high accuracy on out-of-distribution audio durations where token-based models collapse completely. We find that reusing audio frame-level representations yields localization accuracies comparable to (and often better than) finetuned token-based baselines.

Joseph An, Phillip Keung, Jiaqi Wang +2

University of Washington · Allen Institute for Artificial Intelligence

Temporal Audio Grounding Audio-Language Models Speaker Diarization

Feb 5, 2026

Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions

Current audio foundation models typically rely on rigid, task-specific supervision, addressing isolated factors of audio rather than the whole. In contrast, human intelligence processes audio holistically, seamlessly bridging physical signals with abstract cognitive concepts to execute complex tasks. Grounded in this philosophy, we introduce Bagpiper, an 8B audio foundation model that interprets physical audio via rich captions, i.e., comprehensive natural language descriptions that encapsulate the critical cognitive concepts inherent in the signal (e.g., transcription, audio events). By pre-training on a massive corpus of 600B tokens, the model establishes a robust bidirectional mapping between raw audio and this high-level conceptual space. During fine-tuning, Bagpiper adopts a caption-then-process workflow, simulating an intermediate cognitive reasoning step to solve diverse tasks without task-specific priors. Experimentally, Bagpiper outperforms Qwen-2.5-Omni on MMAU and AIRBench for audio understanding and surpasses CosyVoice3 and TangoFlux in generation quality, capable of synthesizing arbitrary compositions of speech, music, and sound effects. To the best of our knowledge, Bagpiper is among the first works that achieve unified understanding generation for general audio. Model, data, and code are available at Bagpiper Home Page.

Jinchuan Tian, Haoran Wang, Bo-Hao Su +14

1Language Technologies Institute, Carnegie Mellon University · 2LY Corporation · 3NVIDIA Research

Audio Understanding Audio-Language Models Audio Captioning Audio Generation

Feb 4, 2026

RA-QA: A Benchmarking System for Respiratory Audio Question Answering Under Real-World Heterogeneity

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.

Gaia A. Bertolino, Yuwei Zhang, Tong Xia +2

University of Cambridge · Cambridge, United Kingdom · Tsinghua University +3

Audio-Language Model Evaluation Audio QA Healthcare Audio Understanding Multimodal QA Audio-Language Models+2

Jan 18, 2026

Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic SpeechLLMs

Audio large language models (LLMs) enable unified speech understanding and generation, but adapting them to linguistically complex and dialect-rich settings such as Arabic-English remains challenging. We present a controlled study of multi-task instruction tuning for an Arabic-centric audio LLM across generative tasks, including automatic speech recognition (ASR) and speech and text summarization, as well as discriminative tasks, including dialect identification (DID) and speech emotion recognition (SER), in a resource-constrained setting. To support end-to-end Arabic speech summarization, we introduce AraMega-SSum, the first Arabic speech summarization dataset designed for training and benchmarking Arabic-centric audio LLMs. We compare four training strategies: (i) Uniform Mixing (UM), (ii) Task-Progressive Curriculum (TPC), (iii) Aligner-Based Diverse Sampling (ADS) for training-time batch construction, and (iv) a two-stage TPC->ADS strategy. Our results reveal a clear efficiency-robustness trade-off. TPC achieves the strongest performance on generative tasks, including ASR and summarization. ADS improves paralinguistic tasks but reduces generative stability when used alone. The two-stage TPC->ADS strategy provides the best overall balance, achieving the strongest DID and SER performance while outperforming large proprietary models such as Gemini-2.5-Pro on discriminative tasks. We will publicly release AraMega-SSum together with all experimental resources to support future research in Arabic speech understanding.

Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury

Qatar Computing Research Institute, Qatar

Spoken Language Understanding Speech Processing Audio Understanding Text Summarization Audio-Language Models Instruction Tuning+1

Jan 15, 2026

HeartMuLa: A Family of Open Sourced Music Foundation Models

We present a family of open-source Music Foundation Models designed to advance large-scale music understanding and generation across diverse tasks and modalities. Our framework consists of four major components: (1) HeartCLAP, an audio-text alignment model; (2) HeartTranscriptor, a robust lyric recognition model optimized for real-world music scenarios; and (3) HeartCodec, a low-frame-rate (12.5 Hz) yet high-fidelity music codec tokenizer that captures long-range musical structure while preserving fine-grained acoustic details and enabling efficient autoregressive modeling; (4) HeartMuLa, an LLM-based song generation model capable of synthesizing high-fidelity music under rich, user-controllable conditions (e.g., textual style descriptions, lyrics, and reference audio). In addition, it provides two specialized modes: (i) fine-grained musical attribute control, which allows users to specify the style of different song sections (e.g., intro, verse, chorus) using natural language prompts; and (ii) short, engaging music generation, which is suitable as background music for short videos. Lastly, HeartMuLa improves significantly when scaled to 7B parameters. For the first time, we show that a Suno-level, commercial-grade system can be reproduced using academic-scale data and GPU resources. We expect these foundation models to serve as strong baselines for future research and to facilitate practical applications in multimodal content production.

Dongchao Yang, Yuxin Xie, Yuguo Yin +26

Text-to-Music Generation Neural Audio Codecs Controllable Music Generation Audio Understanding Audio-Language Models Multimodal Foundation Models

Nov 28, 2025

ORCA: Open-ended Response Correctness Assessment for Audio Question Answering

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.

Šimon Sedláček, Sara Barahona, Bolaji Yusuf +9

AUDIAS, Universidad Autónoma de Madrid, Spain · University of Buenos Aires, Argentina · Tufts University, USA +1

Audio-Language Model Evaluation LLM Evaluation Audio QA LLM-as-a-Judge Audio Understanding Audio-Language Models+1

Nov 20, 2025

Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation

Audio-language pretraining (ALP) holds promise for learning general-purpose audio representation, yet remains underexplored. Crucially, there is no consensus on whether audio-language models can build effective general-purpose audio encoders, nor a systematic understanding of how pretraining objectives behave across diverse tasks and scales. We identify three key barriers: limited scale of audio-text corpora, limited coverage of audio attributes in existing caption corpora, and lack of systematic exploration and evaluation. To fill this gap, we present the first principled empirical study of ALP. We first introduce CaptionStew, a 10.7M caption dataset aggregating open-source audio-text corpora across multiple domains and captioning focuses. We then conduct the first comprehensive evaluation comparing contrastive and captioning objectives for learning audio representation across speech, music, and environmental sound tasks. Our results not only demonstrate that ALP yields competitive, transferable representations, but reveal critical trade-offs: contrastive learning offers superior data efficiency, while captioning exhibits better scalability. Furthermore, we find that the benefits of supervised initialization often diminish at larger scales, challenging common practices. By grounding these claims in empirical evidence, we establish a viable pathway toward general-purpose audio representation learning, guiding future research.

Wei-Cheng Tseng, Xuanru Zhou, Mingyue Huo +3

University of Texas at Austin · Tencent AI Lab Seattle · Zhejiang University +1

Audio-Language Model Evaluation Audio Representation Learning Audio Understanding Audio-Language Models Audio Captioning Multimodal Contrastive Learning

Oct 14, 2025

Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering

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%).

Tsung-En Lin, Kuan-Yi Lee, Hung-Yi Lee

National Taiwan University, Taipei, Taiwan · ASUS Open Cloud Infrastructure Software Center, Taipei, Taiwan

Audio QA Hallucination in Language Models Audio Understanding Audio-Language Models Hallucination Mitigation Activation Steering

Oct 13, 2025

VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents

Recent advances in large audio language models (LALMs) have greatly enhanced multimodal conversational systems. However, existing benchmarks remain limited -- they are mainly English-centric, rely on synthetic speech, and lack comprehensive, discriminative evaluation across multiple dimensions. To address these gaps, we present Voice Chat Bot Bench (VCB Bench) -- a high-quality Chinese benchmark built entirely on real human speech. VCB Bench evaluates LALMs from three complementary perspectives: instruction following (including speech-level control beyond text commands), knowledge understanding (general knowledge, reasoning, and daily dialogue), and robustness (stability under perturbations in content, environment, and speaker traits). Experiments on representative LALMs reveal notable performance gaps and highlight future directions for improvement. VCB Bench provides a reproducible and fine-grained evaluation framework, offering standardized methodology and practical insights for advancing Chinese voice conversational models.

Jiliang Hu, Wenfu Wang, Zuchao Li +6

School of Artificial Intelligence, Wuhan University, Wuhan, China · Tencent AI Lab, Beijing, China

Audio-Language Model Evaluation Voice Agent Evaluation Audio-Language Models Speech Language Models Language Model Robustness

Oct 6, 2025

Robustness assessment of large audio language models in multiple-choice evaluation

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.

Fernando López, Santosh Kesiraju, Jordi Luque

Scientific Research, Telef´onica Innovaci´on Digital, Spain · Brno University of Technology, Czech Republic

Audio-Language Model Evaluation Audio QA Multiple-Choice Question Answering Audio-Language Models Language Model Robustness

Oct 1, 2025

Hearing the Order: Investigating Position Bias in Large Audio-Language Models

Large audio-language models (LALMs) are often used in tasks that involve reasoning over ordered options. An open question is whether their predictions are influenced by the order of answer choices, which would indicate a form of position bias and undermine their reliability. In this paper, we identify and analyze this problem in LALMs. We demonstrate that no model is immune to this bias through extensive experiments on six LALMs across three widely used benchmarks and their spoken counterparts. Shuffling the order of answer options can cause performance fluctuations of up to 24% and even change model rankings, raising concerns about the reliability of current evaluation practices. We also study permutation-based strategies and show that they can mitigate bias in most cases. Our work represents the first systematic investigation of this issue in LALMs, and we hope it raises awareness and motivates further research in this direction.

Yu-Xiang Lin, Chen-An Li, Sheng-Lun Wei +3

National Taiwan University

Audio-Language Model Evaluation Audio-Language Models Position Bias Input Order Sensitivity in Language Models

Sep 18, 2025

Aligning Audio Captions with Human Preferences

Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human preferences in real-world scenarios. To address this, we propose a preference-aligned audio captioning framework based on Reinforcement Learning from Human Feedback (RLHF). To capture nuanced preferences, we train a Contrastive Language-Audio Pretraining (CLAP) based reward model using human-labeled pairwise preference data. This reward model is integrated into an RL framework to fine-tune any baseline captioning system without ground-truth annotations. Extensive human evaluations across multiple datasets show that our method produces captions preferred over baseline models, particularly when baselines fail to provide correct and natural captions. Furthermore, our framework achieves performance comparable to supervised approaches with ground-truth data, demonstrating effective alignment with human preferences and scalability in real-world use.

Kartik Hegde, Rehana Mahfuz, Yinyi Guo +1

Qualcomm Technologies, Inc., India · Qualcomm Technologies, Inc., USA

Reward Modeling Audio-Language Models Audio Captioning Preference Alignment RL from Human Feedback