Audio-Language Models

Ask about this topic

Overview

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

CardsList

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

May 5, 2026

MiniMind-O Technical Report: An Open Small-Scale Speech-Native Omni Model

MiniMind-O is an open 0.1B-scale omni model built on the MiniMind language model. It accepts text, speech, and image inputs, and returns both text and streaming speech. The release includes model code, checkpoints, and the main Parquet training datasets for text-to-audio, image-to-text, and audio-to-audio training, making the complete interaction loop directly inspectable. The model uses a full MiniMind backbone as the Thinker and an independent four-layer Talker made from MiniMind blocks. Frozen SenseVoice-Small and SigLIP2 encoders provide speech and image features, which are mapped by lightweight MLP projectors and injected at modality-placeholder positions. The Talker reads a middle-layer Thinker state together with an autoregressive eight-layer Mimi-code buffer. Speaker control is handled by a dedicated speaker token, right-aligned reference codec prompts, and precomputed CAM++ speaker embeddings, so voice conditioning remains part of the audio-code context rather than a separate TTS module. With a 768-dimensional Talker, the dense and MoE variants reach average CERs of 0.0897 and 0.0900 in Thinker--Talker consistency evaluation, with overall voice-cloning similarities of 0.5995 and 0.5937. Beyond reporting a working system, the paper identifies three scale-critical design choices for small omni models: middle-layer semantic bridging, a released multimodal sequence format, and a parameter-efficient eight-codebook interface.

Jingyao Gong

Independent Researcher

Speech Foundation ModelsUnified Multimodal ModelsSmall Language ModelsAudio-Language ModelsMultimodal Foundation ModelsAudio Generation+2
AskPDF
May 5, 2026

ReasonAudio: A Benchmark for Evaluating Reasoning Beyond Matching in Text-Audio Retrieval

As multimodal content continues to expand at a rapid pace, audio retrieval has emerged as a key enabling technology for media search, content organization, and intelligent assistants. However, most existing benchmarks concentrate on semantic matching and fail to capture the fact that real-world queries often demand advanced reasoning abilities, including negation understanding, temporal ordering, concurrent event recognition, and duration discrimination. To address this gap, we introduce ReasonAudio, the first reasoning-intensive benchmark for Text-Audio Retrieval, comprising 1,000 queries and 10,000 composite audio clips across five fundamental reasoning tasks: Negation, Order, Overlap, Duration, and Mix. Despite their intuitive nature for humans and straightforward construction, these tasks pose significant challenges to current models. Our evaluation of ten state-of-the-art models reveals the following findings: All models struggle with reasoning-intensive audio retrieval, performing particularly poorly on Negation and Duration while showing relatively better results on Overlap and Order. Moreover, Multimodal Large Language Model-based embedding models fail to inherit the reasoning capabilities of their backbones through contrastive fine-tuning, suggesting that current training paradigms are insufficient to preserve reasoning capacity in retrieval settings

Honglei Zhang, Yuting Chen, Chenpeng Hu +2

School of Software, Nanjing University Nanjing, China · School of Software, Northwestern Polytechnical University Xi’an, China · College of Computing and Data Science, Nanyang Technological University Singapore, Singapore

Audio ReasoningAudio UnderstandingAudio-Language ModelsMultimodal ReasoningCross-Modal RetrievalAudio-Text Retrieval+1
AskPDF
May 4, 2026

When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognition

Automatic speech recognition (ASR) systems remain brittle on dysarthric and other atypical speech. Recent audio-language models raise the possibility of improving performance by conditioning on additional clinical context at inference time, but it is unclear whether these models can make use of such information. We introduce a benchmark built on the Speech Accessibility Project (SAP) dataset that tests whether diagnosis labels, clinician-derived speech ratings, and progressively richer clinical descriptions improve transcription accuracy for dysarthric speech. Across matched comparisons on nine models, we find that current models do not meaningfully use this context: diagnosis-informed and clinically detailed prompts yield negligible improvements and often degrade word error rate. We complement the prompting analysis with context-dependent fine-tuning, showing that LoRA adaptation with a mixture of clinical prompt formats achieves a WER of 0.066, a 52% relative reduction over the frozen baseline, while preserving performance when context is unavailable. Subgroup analyses reveal significant gains for Down syndrome and mild-severity speakers. These results clarify where current models fall short and provide a testbed for measuring progress toward more inclusive ASR.

Pehuén Moure, Niclas Pokel, Bilal Bounajma +4

Institute of Neuroinformatics, University of Zurich and ETH Zurich, Switzerland · Department of Mathematics, ETH Zurich, Switzerland · Department of Computational Linguistics, University of Zurich, Switzerland

Audio-Language Model EvaluationASR EvaluationAudio-Language ModelsAutomatic Speech RecognitionDysarthric Speech Recognition
AskPDF
May 1, 2026

GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models

In this paper, we propose GaMMA, a state-of-the-art (SoTA) large multimodal model (LMM) designed to achieve comprehensive musical content understanding. GaMMA inherits the streamlined encoder-decoder design of LLaVA, enabling effective cross-modal learning between music and language. By incorporating audio encoders in a mixture-of-experts manner, GaMMA effectively unifies both time-series and non-time-series music understanding tasks within one set of parameters. Our approach combines carefully curated datasets at scale with a progressive training pipeline, effectively pushing the boundaries of music understanding via pretraining, supervised fine-tuning (SFT), and reinforcement learning (RL). To comprehensively assess both temporal and non-temporal capability of music LMMs, we introduce MusicBench, the largest music-oriented benchmark, comprising 3,739 human-curated multiple-choice questions covering diverse aspects of musical understanding. Extensive experiments demonstrate that GaMMA establishes new SoTA in the music domain, achieving 79.1% accuracy on MuchoMusic, 79.3% on MusicBench-Temporal, and 81.3% on MusicBench-Global, consistently outperforming previous methods.

Zuyao You, Zhesong Yu, Mingyu Liu +3

1Fudan University · 2ByteDance

Music UnderstandingMultimodal PretrainingMultimodal Large Language ModelsAudio UnderstandingAudio-Language ModelsMusic Information Retrieval+2
AskPDF
Apr 28, 2026

Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models

Recent audio-aware large language models (ALLMs) have demonstrated strong capabilities across diverse audio understanding and reasoning tasks, but they still frequently produce hallucinated or overly confident outputs. While uncertainty estimation has been extensively studied in text-only LLMs, it remains largely unexplored for ALLMs, where audio-conditioned generation introduces additional challenges such as perceptual ambiguity and cross-modal grounding. In this work, we present the first systematic empirical study of uncertainty estimation in ALLMs. We benchmark five representative methods, including predictive entropy, length-normalized entropy, semantic entropy, discrete semantic entropy, and P(True), across multiple models and diverse evaluation settings spanning general audio understanding, reasoning, hallucination detection, and unanswerable question answering. Our results reveal two key findings. First, semantic-level and verification-based methods consistently outperform token-level baselines on general audio reasoning benchmarks. Second, on trustworthiness-oriented benchmarks, the relative effectiveness of uncertainty methods becomes notably more model- and benchmark-dependent, indicating that conclusions drawn from general reasoning settings do not straightforwardly transfer to hallucination and unanswerable-question scenarios. We further explore uncertainty-based adaptive inference as a potential downstream application. We hope this study provides a foundation for future research on reliable, uncertainty-aware audio-language systems.

Chun-Yi Kuan, Wei-Ping Huang, Hung-yi Lee

Graduate Institute of Communication Engineering, National Taiwan University, Taiwan · Artificial Intelligence Center of Research Excellence (AI-CoRE), National Taiwan University, Taiwan

Semantic EntropyAudio UnderstandingAudio-Language ModelsLLM Uncertainty Estimation
AskPDF
Apr 27, 2026

Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

We introduce Nemotron 3 Nano Omni, the latest model in the Nemotron multimodal series and the first to natively support audio inputs alongside text, images, and video. Nemotron 3 Nano Omni delivers consistent accuracy improvements over its predecessor, Nemotron Nano V2 VL, across all modalities, enabled by advances in architecture, training data and recipes. In particular, Nemotron 3 delivers leading results in real-world document understanding, long audio-video comprehension, and agentic computer use. Built on the highly efficient Nemotron 3 Nano 30B-A3B backbone, Nemotron 3 Nano Omni further incorporates innovative multimodal token-reduction techniques to deliver substantially lower inference latency and higher throughput than other models of similar size. We are releasing model checkpoints in BF16, FP8, and FP4 formats, along with portions of the training data and codebase to facilitate further research and development.

NVIDIA, :, Amala Sanjay Deshmukh +216

Efficient Multimodal InferenceMultimodal Large Language ModelsAudio UnderstandingAudio-Language ModelsMultimodal Foundation ModelsMultimodal Understanding
AskPDF
Apr 27, 2026

All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation

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.

Leonardo Haw-Yang Foo, Chih-Kai Yang, Chen-An Li +2

National Taiwan University · NTU Artificial Intelligence Center of Research Excellence (NTU AI-CoRE)

Audio-Language Model EvaluationModality Reliance in Multimodal ModelsAudio QAAudio UnderstandingAudio-Language ModelsBenchmark Validity+2
AskPDF
Apr 26, 2026

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models

Recent large audio language models (LALMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet incur high inference costs. Token compression is an effective method that directly reduces redundant tokens in the sequence. Existing compression methods usually assume that all attention heads in LALMs contribute equally to various audio tasks and calculate token importance by averaging scores across all heads. However, our analysis demonstrates that attention heads exhibit distinct behaviors across diverse audio domains. We further reveal that only a sparse subset of attention heads actively responds to audio, with completely different performance when handling semantic and acoustic tasks. In light of this observation, we propose HeadRouter, a head-importance-aware token pruning method that perceives the varying importance of attention heads in different audio tasks to maximize the retention of crucial tokens. HeadRouter is training-free and can be applied to various LALMs. Extensive experiments on the AudioMarathon and MMAU-Pro benchmarks demonstrate that HeadRouter achieves state-of-the-art compression performance, exceeding the baseline model even when retaining 70% of the audio tokens and achieving 101.8% and 103.0% of the vanilla average on Qwen2.5-Omni-3B and Qwen2.5-Omni-7B, respectively.

Peize He, Yaodi Luo, Xiaoqian Liu +7

1EPIC Lab, Shanghai Jiao Tong University · 2DAIL Tech · 3Northeastern University +2

Audio Token CompressionSelf-AttentionAudio UnderstandingAudio-Language ModelsToken PruningMultimodal Token Compression+3
AskPDF
Apr 25, 2026

Au-M-ol: A Unified Model for Medical Audio and Language Understanding

In this work, we present Au-M-ol, a novel multimodal architecture that extends Large Language Models (LLMs) with audio processing. It is designed to improve performance on clinically relevant tasks such as Automatic Speech Recognition (ASR). Au-M-ol has three main components: (1) an audio encoder that extracts rich acoustic features from medical speech, (2) an adaptation layer that maps audio features into the LLM input space, and (3) a pretrained LLM that performs transcription and clinical language understanding. This design allows the model to interpret spoken medical content directly, improving both accuracy and robustness. In experiments, Au-M-ol reduces Word Error Rate (WER) by 56% compared to state-of-the-art baselines on medical transcription tasks. The model also performs well in challenging conditions, including noisy environments, domain-specific terminology, and speaker variability. These results suggest that Au-M-ol is a strong candidate for real-world clinical applications, where reliable and context-aware audio understanding is essential.

Meizhu Liu, Nistha Mitra, Paul Li +3

Oracle AI Science · Neuramill

Medical Speech RecognitionSpeech ProcessingAudio UnderstandingAudio-Language ModelsAutomatic Speech RecognitionMedical LLMs
AskPDF
Apr 23, 2026

Listen and Chant Before You Read: The Ladder of Beauty in LM Pre-Training

We show that pre-training a Transformer on music before language significantly accelerates language acquisition. Using piano performances (MAESTRO dataset), a developmental pipeline -- music →\to poetry →\to prose -- yields a 17.5%17.5\% perplexity improvement over random initialization (p<0.001p < 0.001, 5 seeds), with music and poetry improving orthogonal model components (internal computation and embeddings, respectively). Convergence tests confirm that this is not a transient head start: at d ⁣= ⁣64d\!=\!64, multi-seed validation (5 seeds) shows a persistent 5.5% gap at plateau (p=0.017p = 0.017), with the pipeline converging faster and to a lower loss in every run. Real music matches the transfer ceiling of synthetic patterns with one-third the data, and scaling experiments reveal that optimal pre-training data volume shifts with model capacity (−3%→+3%→+6%-3\% \to +3\% \to +6\% advantage of larger datasets from d ⁣= ⁣16d\!=\!16 to d ⁣= ⁣64d\!=\!64). Across the scales we study (d ⁣∈ ⁣{16,32,64}d\!\in\!\{16,32,64\}, up to ∼400{\sim}400K parameters), these results suggest a capacity-dependent data curation principle and indicate that structured human creative outputs can provide an efficient pre-training substrate for small language models; stronger conclusions at modern pre-training scale will require substantially larger experiments.

Yoshinori Nomura

Mirage Mountain Technologies Inc.

Language Model PretrainingAudio-Language ModelsCurriculum Learning
AskPDF
Apr 22, 2026

SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation

Paralinguistic cues are essential for natural human-computer interaction, yet their evaluation in Large Audio-Language Models (LALMs) remains limited by coarse feature coverage and the inherent subjectivity of assessment. To address these challenges, we introduce SpeechParaling-Bench, a comprehensive benchmark for paralinguistic-aware speech generation. It expands existing coverage from fewer than 50 to over 100 fine-grained features, supported by more than 1,000 English-Chinese parallel speech queries, and is organized into three progressively challenging tasks: fine-grained control, intra-utterance variation, and context-aware adaptation. To enable reliable evaluation, we further develop a pairwise comparison pipeline, in which candidate responses are evaluated against a fixed baseline by an LALM-based judge. By framing evaluation as relative preference rather than absolute scoring, this approach mitigates subjectivity and yields more stable and scalable assessments without costly human annotation. Extensive experiments reveal substantial limitations in current LALMs. Even leading proprietary models struggle with comprehensive static control and dynamic modulation of paralinguistic features, while failure to correctly interpret paralinguistic cues accounts for 43.3% of errors in situational dialogue. These findings underscore the need for more robust paralinguistic modeling toward human-aligned voice assistants.

Ruohan Liu, Shukang Yin, Tao Wang +6

1Nanjing University · 2Xiaomi

Audio-Language Model EvaluationLLM EvaluationSpeech Generation EvaluationPairwise Preference EvaluationAudio-Language ModelsGenerative AI Evaluation
AskPDF
Apr 21, 2026

HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models

Large Audio-Language Models (LALMs) have recently achieved strong performance across various audio-centric tasks. However, hallucination, where models generate responses that are semantically incorrect or acoustically unsupported, remains largely underexplored in the audio domain. Existing hallucination benchmarks mainly focus on text or vision, while the few audio-oriented studies are limited in scale, modality coverage, and diagnostic depth. We therefore introduce HalluAudio, the first large-scale benchmark for evaluating hallucinations across speech, environmental sound, and music. HalluAudio comprises over 5K human-verified QA pairs and spans diverse task types, including binary judgments, multi-choice reasoning, attribute verification, and open-ended QA. To systematically induce hallucinations, we design adversarial prompts and mixed-audio conditions. Beyond accuracy, our evaluation protocol measures hallucination rate, yes/no bias, error-type analysis, and refusal rate, enabling a fine-grained analysis of LALM failure modes. We benchmark a broad range of open-source and proprietary models, providing the first large-scale comparison across speech, sound, and music. Our results reveal significant deficiencies in acoustic grounding, temporal reasoning, and music attribute understanding, underscoring the need for reliable and robust LALMs.

Feiyu Zhao, Yiming Chen, Wenhuan Lu +3

College of Intelligence and Computing, Tianjin University, China · ASUS Intelligent Cloud Services, Singapore

Audio-Language Model EvaluationAudio-Language Model Hallucination DetectionHallucination in Language ModelsAudio UnderstandingAudio-Language ModelsMultimodal Hallucination
AskPDF
Apr 20, 2026

Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval

Audio-text retrieval systems based on Contrastive Language-Audio Pretraining (CLAP) achieve strong performance on traditional benchmarks; however, these benchmarks rely on caption-style queries that differ substantially from real-world search behavior, limiting their assessment of practical retrieval robustness. We present Omni-Embed-Audio (OEA), a retrieval-oriented encoder leveraging multimodal LLMs with native audio understanding. To systematically evaluate robustness beyond caption-style queries, we introduce User-Intent Queries (UIQs) - five formulations reflecting natural search behaviors: questions, commands, keyword tags, paraphrases, and exclusion-based negative queries. For negative queries, we develop a hard negative mining pipeline and propose discrimination metrics (HNSR, TFR) assessing models' ability to suppress acoustically similar distractors. Experiments on AudioCaps, Clotho, and MECAT show that OEA achieves comparable text-to-audio retrieval performance to state-of-the-art M2D-CLAP, while demonstrating clear advantages in two critical areas: (1) dominant text-to-text retrieval (+22% relative improvement), and (2) substantially superior hard negative discrimination (+4.3%p HNSR@10, +34.7% relative TFR@10), revealing that LLM backbones provide superior semantic understanding of complex queries.

HaeJun Yoo, Yongseop Shin, Insung Lee +2

Sogang University

Audio-Language Model EvaluationMultimodal IRAudio UnderstandingAudio-Language ModelsRetrieval RobustnessAudio-Text Retrieval+1
AskPDF
Apr 20, 2026

Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models

Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning processes. Existing methods for enhancing audio reasoning rely either on supervised chain-of-thought (CoT) fine-tuning, which is limited by training data quality, or on reinforcement learning (RL) with coarse rewards that do not directly evaluate reasoning quality. As a result, the generated reasoning chains often appear well-structured yet lack specific acoustic grounding. We propose Audio-DeepThinker, a framework built on two core ideas. First, we introduce a hybrid reasoning similarity reward that directly supervises the quality of generated reasoning chains by combining an LLM evaluator assessing logical path alignment, key step coverage, and analytical depth with an embedding similarity component enforcing semantic alignment with reference reasoning chains. Second, we propose a progressive two-stage curriculum that enables high-quality CoT reasoning to emerge through pure RL exploration, without any supervised reasoning fine-tuning, from an instruction-tuned model that possesses no prior chain-of-thought capability. Stage 1 trains on foundational audio QA with the hybrid reward to foster basic reasoning patterns, while Stage 2 shifts to acoustically challenging boundary cases with an LLM-only reward for greater reasoning diversity. Audio-DeepThinker achieves state-of-the-art results on MMAR (74.0%), MMAU-test-mini (78.5%), and MMSU (77.26%), winning 1st Place in the Interspeech 2026 Audio Reasoning Challenge (Single Model Track). Interpretability analyses further reveal that RL training primarily reshapes upper-layer MoE gating mechanisms and that reasoning tokens crystallize progressively in the upper transformer layers, offering mechanistic insights into how audio reasoning emerges through exploration.

Xiang He, Chenxing Li, Jinting Wang +5

Tencent AI Lab, Beijing, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China

RL for Language Model ReasoningAudio ReasoningAudio UnderstandingAudio-Language ModelsMultimodal CoT Reasoning
AskPDF
Apr 20, 2026

Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment

The rapid proliferation of large audio models (LAMs) demands efficient approaches for model comparison, yet comprehensive benchmarks are costly. To fill this gap, we investigate whether minimal subsets can reliably evaluate LAMs while reducing costs and data redundancy. Analyzing 10 subset selection methods with 18 audio models across 40 tasks covering major LAM evaluation dimensions, we show that subsets of just 50 examples (0.3% of data) can achieve over 0.93 Pearson correlation with full benchmark scores. To understand how well these scores align with what practitioners ultimately care about, user satisfaction, we collect 776 human preference ratings from realistic voice assistant conversations, finding that both subsets and full benchmark achieve only 0.85 correlation with human. To better predict preferences, we trained regression models on these selected subsets, achieving 0.98 correlation -- outperforming regression models trained on both random subsets and the full benchmark. This demonstrates that in regression modeling, well-curated subsets outpredict the full benchmark, showing quality over quantity. We open-source these regression-weighted subsets as the HUMANS benchmark, an efficient proxy for LAM evaluation that captures both benchmark performance and user preferences.

Woody Haosheng Gan, William Held, Diyi Yang

University of Southern California · Stanford University · OpenAthena

Audio-Language Model EvaluationHuman Preference ModelingAudio-Language Models
AskPDF
Apr 19, 2026

VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech

Large Audio-Language Models (LALMs) are increasingly integrated into daily applications, yet their generative biases remain underexplored. Existing speech fairness benchmarks rely on synthetic speech and Multiple-Choice Questions (MCQs), both offering a fragmented view of fairness. We propose VIBE, a framework that evaluates generative bias through open-ended tasks such as personalized recommendations, using human-recorded speech. Unlike MCQs, our method allows stereotypical associations to manifest organically without predefined options, making it easily extensible to new tasks. Evaluating 12 state-of-the-art LALMs reveals systematic biases in realistic scenarios. Both gender and accent cues trigger statistically significant distributional shifts, and bias magnitude is strongly task-dependent.

Yi-Cheng Lin, Yusuke Hirota, Sung-Feng Huang +1

Graduate Institute of Communication Engineering National Taiwan University Taipei, Taiwan · NVIDIA Research NVIDIA Taipei, Taiwan · AI Center of Research Excellence National Taiwan University Taipei, Taiwan

Audio-Language Model EvaluationGender Bias in Language ModelsLanguage Model Generation EvaluationSocial Bias in Language ModelsAudio-Language ModelsLanguage Model Bias Evaluation
AskPDF
Apr 17, 2026

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs

Fine-tuning on benign data is known to degrade safety alignment in text and vision LLMs, but whether distinct input properties drive this vulnerability differently remains unclear. Audio introduces a richer problem where benign samples can neighbor harmful content through what is said or how it sounds. We present the first systematic study of benign fine-tuning safety in Audio LLMs, evaluating three state-of-the-art models with a proximity-based framework that decomposes embedding-space distance into semantic, acoustic, and mixed axes. We find that the dominant vulnerability axis is architecture-conditioned, determined by how each model's encoder and projector transform audio into the backbone LLM's input space. Across three models, benign fine-tuning elevates Jailbreak Success Rate (JSR) from single digits to as high as 87%, with the most damaging axis shifting from semantic to acoustic proximity depending on encoder design. Mechanistically, fine-tuning selectively suppresses late-layer refusal circuits while frozen encoders preserve upstream representations: the model still detects harmful content but stops refusing, a recognition-refusal dissociation. Two practical defenses, filtering training data to maximize distance from harmful embeddings and a textual system prompt at inference, reduce JSR to near-zero without architectural modification. These findings show that safety evaluation should account for modality and architecture, while highlighting Audio LLMs as a useful testbed for understanding alignment fragility.

Jaechul Roh, Virat Shejwalkar, Amir Houmansadr

University of Massachusetts Amherst

Language Model Safety EvaluationLLM Fine-TuningLLM Safety AlignmentAudio-Language ModelsLLM Safety
AskPDF
Apr 17, 2026

NaijaS2ST: A Multi-Accent Benchmark for Speech-to-Speech Translation in Low-Resource Nigerian Languages

Speech translation for low-resource languages remains fundamentally limited by the scarcity of high-quality, diverse parallel speech data, a challenge that is especially pronounced in African linguistic contexts. To address this, we introduce NaijaS2ST, a parallel speech translation dataset spanning Igbo, Hausa, Yorùbá, and Nigerian Pidgin paired with English. The dataset comprises approximately 50 hours of speech per language and captures substantial variation in speakers and accents, reflecting realistic multilingual and multi-accent conditions. With NaijaS2ST, we conduct a comprehensive benchmark of cascaded, end-to-end (E2E), and AudioLLM-based approaches across bidirectional translation settings. Our results show that audio LLMs with few-shot examples are more effective for speech-to-text translation than cascaded and end-to-end methods trained on fine-tuned data. However, for speech-to-speech translation, the cascaded and audio LLM paradigms yield comparable performance, indicating that there is still considerable room for improvement in developing targeted, task-specific models for this setting. By providing both a high-quality dataset and a systematic benchmark, we hope that NaijaS2ST will serve as a strong foundation for advancing research in low-resource, multilingual speech translation.

Marie Maltais, Yejin Jeon, Min Ma +7

Mila - Quebec AI Institute · McGill University, Canada · Google DeepMind +6

Speech TranslationAudio-Language Models
AskPDF
Apr 17, 2026

Joint-Centric Dual Contrastive Alignment with Structure-Preserving and Information-Balanced Regularization

We propose HILBERT (HIerarchical Long-sequence Balanced Embedding with Reciprocal contrastive Training), a cross-attentive multimodal framework for learning document-level audio-text representations from long, segmented sequences in low-resource data settings. HILBERT leverages frozen pre-trained speech and language encoders to extract segment-level features, which are aggregated via cross-modal attention and self-attentive pooling to form modality-specific document representations and a joint cross-attentive embedding. To align modalities while preserving modality-specific structure under severe audio-text dimensional imbalance, we introduce a reciprocal dual contrastive objective that simultaneously aligns audio-to-joint and text-to-joint representations, rather than directly contrasting audio and text alone. Two auxiliary regularizers further stabilize long-sequence fusion: a Centered Kernel Alignment (CKA) loss that preserves structural consistency between each modality and the joint embedding, and a mutual information balancing loss that prevents dominance of a single modality by equalizing information flow from audio and text into the joint space. For downstream prediction, HILBERT employs a Mixture-of-Experts (MoE) classifier over concatenated audio, text, and joint representations to accommodate heterogeneous label regimes. Extensive evaluation across multiple audio-text backbone combinations demonstrates that HILBERT learns semantically meaningful long-sequence representations and achieves superior performance on highly imbalanced multi-class settings.

Habibeh Naderi, Behrouz Haji Soleimani, Stan Matwin

Dalhousie University, Halifax NS, Canada

Cross-Modal LearningModality ImbalanceCross-Modal AlignmentAudio UnderstandingAudio-Language ModelsMultimodal Classification+3
AskPDF
Apr 17, 2026

TinyMU: A Compact Audio-Language Model for Music Understanding

Music understanding and reasoning are central challenges in the Music Information Research field, with applications ranging from retrieval and recommendation to music agents and virtual assistants. Recent Large Audio-Language Models (LALMs) have shown remarkable progress in answering music-related questions by following user instructions. However, their massive scale, often billions of parameters, results in expensive training, slow inference, and limited deployability on edge devices. In this work, we present TinyMU, a lightweight (229M) Music-Language Model (MLM) that achieves performance comparable to much larger LALMs while remaining efficient and compact. To train TinyMU, we introduce MusicSkills-3.5M, a carefully curated, music-grounded question-answering dataset with 3.5M samples. Spanning multiple-choice, binary, and open-ended formats, this dataset provides fine-grained supervision across diverse musical concepts. For its architecture, TinyMU leverages MATPAC++, the SOTA self-supervised audio encoder for fine-grained feature extraction. Paired with a lightweight linear projector, it efficiently aligns audio embeddings with the language model. Through extensive evaluation, we show that TinyMU performs strongly in both basic music understanding and complex reasoning. Notably, on the MuChoMusic benchmark, it achieves 82% of SOTA LALM's performance despite being 35x smaller, highlighting the potential of small MLMs under constrained computational budgets.

Xiquan Li, Aurian Quelennec, Slim Essid

LTCI, T´el´ecom Paris, Institut Polytechnique de Paris · Shanghai Jiao Tong University

Music UnderstandingSmall Language ModelsAudio UnderstandingAudio-Language ModelsMusic Information Retrieval
AskPDF
Apr 16, 2026

Listen, Pause, and Reason: Toward Perception-Grounded Hybrid Reasoning for Audio Understanding

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.

Jieyi Wang, Yazhe Niu, Dexuan Xu +1

Shanghai AI Laboratory · Peking University · CUHK MMLab +1

Audio QAAudio ReasoningAudio UnderstandingAudio-Language Models
AskPDF
Apr 16, 2026

Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection

Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond text and introduces vulnerabilities in the continuous, high-dimensional audio channel. While prior work studied audio jailbreaks, the security risks of malicious audio injection and downstream behavior manipulation remain underexamined. In this work, we reveal a previously overlooked threat, auditory prompt injection, under realistic constraints of audio data-only access and strong perceptual stealth. To systematically analyze this threat, we propose AudioHijack, a general framework that generates context-agnostic and imperceptible adversarial audio to hijack LALMs. AudioHijack employs sampling-based gradient estimation for end-to-end optimization across diverse models, bypassing non-differentiable audio tokenization. Through attention supervision and multi-context training, it steers model attention toward adversarial audio and generalizes to unseen user contexts. We also design a convolutional blending method that modulates perturbations into natural reverberation, making them highly imperceptible to users. Extensive experiments on 13 state-of-the-art LALMs show consistent hijacking across 6 misbehavior categories, achieving average success rates of 79%-96% on unseen user contexts with high acoustic fidelity. Real-world studies demonstrate that commercial voice agents from Mistral AI and Microsoft Azure can be induced to execute unauthorized actions on behalf of users. These findings expose critical vulnerabilities in LALMs and highlight the urgent need for dedicated defense.

Meng Chen, Kun Wang, Li Lu +2

The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security · National University of Singapore +1

Audio-Language ModelsLLM Security
AskPDF
Apr 16, 2026

Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models

Large audio-language models (LALMs) generalize across speech, sound, and music, but unified decoders can exhibit a temporal smoothing bias: transient acoustic cues may be underutilized in favor of temporally smooth context that is better supported by language priors, leading to less specific audio-grounded outputs. We propose Temporal Contrastive Decoding (TCD), a training-free decoding method for unified LALMs that mitigates this effect at inference time. TCD constructs a temporally blurred slow-path view by smoothing the input waveform and re-encoding it, then contrasts next-token logits from the original and slow-path views. The contrastive signal is applied as a token-level logit update restricted to a small candidate set. A self-normalized stability score sets the blur window and update scale, and a step-wise gate based on uncertainty and audio reliance activates the update only when needed. Experiments on MMAU and AIR-Bench show consistent improvements on strong unified LALMs. We further conduct ablations and an architectural applicability study to analyze the contributions of key components and how TCD behaves across large audio-language model designs.

Yanda Li, Yuhan Liu, Zirui Song +3

Mohamed bin Zayed University of Artificial Intelligence, UAE · Beijing Jiaotong University, China

Audio UnderstandingAudio-Language ModelsContrastive Decoding
AskPDF
Apr 15, 2026

Towards Fine-grained Temporal Perception: Post-Training Large Audio-Language Models with Audio-Side Time Prompt

Large Audio-Language Models (LALMs) enable general audio understanding and demonstrate remarkable performance across various audio tasks. However, these models still face challenges in temporal perception (e.g., inferring event onset and offset), leading to limited utility in fine-grained scenarios. To address this issue, we propose Audio-Side Time Prompt and leverage Reinforcement Learning (RL) to develop the TimePro-RL framework for fine-grained temporal perception. Specifically, we encode timestamps as embeddings and interleave them within the audio feature sequence as temporal coordinates to prompt the model. Furthermore, we introduce RL following Supervised Fine-Tuning (SFT) to directly optimize temporal alignment performance. Experiments demonstrate that TimePro-RL achieves significant performance gains across a range of audio temporal tasks, such as audio grounding, sound event detection, and dense audio captioning, validating its robust effectiveness.

Yanfeng Shi, Pengfei Cai, Jun Liu +5

National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China · ICT Cluster, Singapore Institute of Technology, Singapore

Audio-Language ModelsTemporal Audio GroundingAudio UnderstandingSound Event Detection
AskPDF
Apr 14, 2026

SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding

Large Audio-Language Models (ALMs) have recently demonstrated remarkable capabilities in holistic audio understanding, yet they remain unreliable for temporal grounding, i.e., the task of pinpointing exactly when an event occurs within long-form audio. This limitation stems from two factors: training data dominated by clip-level supervision lacking precise timestamps, and benchmarks that fail to simulate real-world scenarios where short events are obscured by dense background sounds. In this paper, we introduce SpotSound, an audio language model designed for grounding audio events. SpotSound incorporates a novel training objective, specifically designed to suppress hallucinated timestamps for events absent from the input. Additionally, we present SpotSound-Bench, a challenging temporal grounding benchmark where target events occupy less than ~10% of each clip, creating a rigorous 'needle-in-a-haystack' evaluation. Experiments demonstrate that SpotSound achieves state-of-the-art results on temporal grounding benchmarks while maintaining robust performance across general downstream audio-language tasks. Code, models and benchmark are released on https://loiesun.github.io/spotsound/

Luoyi Sun, Xiao Zhou, Zeqian Li +3

Zhejiang University Hangzhou, Zhejiang, China · SAI, Shanghai Jiao Tong University Shanghai, China

Temporal Audio GroundingAudio-Language ModelsAudio-Language Model EvaluationHallucination Mitigation
AskPDF
Apr 14, 2026

Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMs

Recent Audio Large Language Models (AudioLLMs) exhibit a striking performance inversion: while excelling at complex reasoning tasks, they consistently underperform on fine-grained acoustic perception. We attribute this gap to a fundamental limitation of ASR-centric training, which provides precise linguistic targets but implicitly teaches models to suppress paralinguistic cues and acoustic events as noise. To address this, we propose Unified Audio Schema (UAS), a holistic and structured supervision framework that organizes audio information into three explicit components -- Transcription, Paralinguistics, and Non-linguistic Events -- within a unified JSON format. This design achieves comprehensive acoustic coverage without sacrificing the tight audio-text alignment that enables reasoning. We validate the effectiveness of this supervision strategy by applying it to both discrete and continuous AudioLLM architectures. Extensive experiments on MMSU, MMAR, and MMAU demonstrate that UAS-Audio yields consistent improvements, boosting fine-grained perception by 10.9% on MMSU over the same-size state-of-the-art models while preserving robust reasoning capabilities. Our code and model are publicly available at https://github.com/Tencent/Unified_Audio_Schema.

Linhao Zhang, Yuhan Song, Aiwei Liu +6

Basic Model Technology Center, WeChat AI, Tencent Inc. · State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University

Audio UnderstandingAudio-Language Models
AskPDF
Apr 13, 2026

Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music

We present Audio Flamingo Next (AF-Next), the next-generation and most capable large audio-language model in the Audio Flamingo series, designed to advance understanding and reasoning over speech, environmental sounds and music. Compared to Audio Flamingo 3, AF-Next introduces: (i) a stronger foundational audio-language model that significantly improves accuracy across diverse audio understanding tasks; (ii) scalable strategies for constructing large-scale audio understanding and reasoning data beyond existing academic benchmarks; (iii) support for long and complex audio inputs up to 30 minutes; and (iv) Temporal Audio Chain-of-Thought, a new reasoning paradigm that explicitly grounds intermediate reasoning steps to timestamps in long audio, enabling fine-grained temporal alignment and improved interpretability. To enable these capabilities, we first conduct a systematic analysis of Audio Flamingo 3 to identify key gaps in audio understanding and reasoning. We then curate and scale new large-scale datasets totaling over 1 million hours to address these limitations and expand the existing AudioSkills-XL, LongAudio-XL, AF-Think and AF-Chat datasets. AF-Next is trained using a curriculum-based strategy spanning pre-training, mid-training and post-training stages. Extensive experiments across 20 audio understanding and reasoning benchmarks, including challenging long-audio tasks, show that AF-Next outperforms similarly sized open models by large margins and remains highly competitive with and sometimes surpasses, much larger open-weight and closed models. Beyond benchmark performance, AF-Next exhibits strong real-world utility and transfers well to unseen tasks, highlighting its robustness and generalization ability. In addition to all data, code and methods, we open-source 3 variants of AF-Next, including AF-Next-Instruct, AF-Next-Think and AF-Next-Captioner.

Sreyan Ghosh, Arushi Goel, Kaousheik Jayakumar +15

NVIDIA, USA · University of Maryland, USA

Audio UnderstandingAudio-Language ModelsAudio ReasoningTemporal Audio Grounding
AskPDF
Apr 12, 2026

Whisper-AuT: Domain-Adapted Audio Encoder for Efficient Audio-LLM Training

Audio-native large language models (audio-LLMs) commonly use Whisper as their audio encoder. However, Whisper was trained exclusively on speech data, producing weak representations for music and environmental sound. This forces downstream audio-LLMs to compensate through extensive training on large-scale non-speech data. We present Whisper-AuT, a domain-adapted audio encoder obtained by fine-tuning Whisper-large-v3 on a curated mixture of speech (80%), environmental sound (10%), and music (10%) totaling approximately 20M samples. The full encoder-decoder is trained end-to-end with a seq2seq captioning objective; the decoder is then discarded and only the encoder is retained. Linear probe evaluations show that Whisper-AuT achieves +23.0% on ESC-50 (environmental sound), +5.0% on GTZAN (music genre), and +0.7% on Speech Commands (keyword spotting) compared to the original Whisperlarge-v3 encoder. Whisper-AuT is designed as a drop-in replacement for Whisper in audio-LLM architectures, with the goal of reducing downstream training cost by providing stronger initial audio representations for non-speech domains.

Jielin Qiu, Ming Zhu, Wenting Zhao +11

Salesforce AI Research

Audio Representation LearningDomain AdaptationAudio-Language Models
AskPDF
Apr 10, 2026

GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking

Audio Large Language Models (ALLMs) enable spoken interaction but introduce new jailbreak vulnerabilities. Existing perturbation-based jailbreaks do not explicitly control which frequency bands carry the perturbation. Although such perturbations can elicit unsafe responses, repeatedly applying a universal perturbation across diverse inputs may also degrade utility on normal tasks, leaving a conspicuous behavioral footprint that may expose the attack to users or automated monitoring systems and thereby compromise its stealthiness. To determine whether full-band perturbation is necessary, we vary coverage from partial-band to full-band. Jailbreak Success Rate (JSR) varies non-monotonically, while utility degradation grows with coverage. This mismatch shows that selected bands can yield stronger attacks with less utility degradation than full-band perturbations. Based on this observation, we propose GRM, a utility-aware, frequency-selective jailbreak framework that ranks Mel bands by the ratio between jailbreak contribution and transcript sensitivity, confines a universal perturbation to selected bands, and regularizes deviations from the intended request semantics. Experiments on four ALLMs show that GRM achieves an average JSR of 88.46% while substantially reducing utility degradation across benign transcription and response tasks relative to baselines. Our code is available at this repository. Warning: This paper contains potentially sensitive content.

Yunqiang Wang, Hengyuan Na, Di Wu +2

Sun Yat-Sen University Guangzhou Yunshan Research Institute of Artificial Intelligence Security Guangzhou, China · Sun Yat-Sen University Guangzhou, China

LLM Jailbreak AttacksAdversarial PerturbationsAudio-Language Models
AskPDF
Apr 10, 2026

Noise-Aware In-Context Learning for Hallucination Mitigation in ALLMs

Auditory large language models (ALLMs) have demonstrated strong general capabilities in audio understanding and reasoning tasks. However, their reliability is still undermined by hallucination issues. Existing hallucination evaluation methods are formulated as binary classification tasks, which are insufficient to characterize the more complex hallucination patterns that arise in generative tasks. Moreover, current hallucination mitigation strategies rely on fine-tuning, resulting in high computational costs. To address the above limitations, we propose a plug-and-play Noise-Aware In-Context Learning (NAICL) method. Specifically, we construct a noise prior library, retrieve noise examples relevant to the input audio, and incorporate them as contextual priors, thereby guiding the model to reduce speculative associations when acoustic evidence is insufficient and to adopt a more conservative generation strategy. In addition, we establish a hallucination benchmark for audio caption tasks including the construction of the Clotho-1K multi-event benchmark dataset, the definition of four types of auditory hallucinations, and the introduction of metrics such as hallucination type distribution to support fine-grained analysis. Experimental results show that all evaluated ALLMs exhibit same hallucination behaviors. Moreover, the proposed NAICL method reduces the overall hallucination rate from 26.53% to 16.98%.

Qixuan Huang, Khalid Zaman, Masashi Unoki

Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology 1-1 Asahidai, Nomi, Ishikawa 923–1292 Japan

Audio-Language ModelsAudio-Language Model Hallucination DetectionIn-Context LearningAudio Captioning
AskPDF