Audio Understanding

Follow this topic Ask about this topic

Momentum

17 papers in the last four weeks, up 325% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 169

Jun 5, 2026cs.SD

Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition

Instruction-following audio language models (ALMs) can be augmented with explicit acoustic cues, yet it remains unclear whether such cues are used in a grounded way when the raw audio is already available. We study this question in speech emotion recognition (SER) by deriving six interpretable acoustic concept tokens from the standardised eGeMAPS paralinguistic feature set. These tokens summarise energy, pitch, dynamics, brightness, formants, and voice quality, and are appended to the textual prompt while the audio input is kept unchanged. Across the widely used FAU-Aibo and IEMOCAP benchmarks, aligned tokens improve unweighted average recall (UAR), whereas shuffled, conflicting, or corrupted tokens reduce performance relative to aligned tokens and shift confusions toward neutral. Importantly, predictions do not collapse under strong token perturbations, suggesting that the models are sensitive to the symbolic cue channel but remain partly anchored to the audio signal. We argue that token-only interventions provide a practical way to probe audio-grounded cue use, robustness, and interpretability in ALM-based affective computing.

Iosif Tsangko, Andreas Triantafyllopoulos, Björn W. Schuller

CHI – Chair of Health Informatics, TUM University Hospital, Munich, Germany · MCML – Munich Center for Machine Learning, Munich, Germany · MDSI – Munich Data Science Institute, Munich, Germany +1

Audio-Language Model Evaluation Audio Understanding Audio-Language Models Speech Emotion Recognition

Jun 5, 2026cs.CL

Continuous Audio Thinking for Large Audio Language Models

Large audio language models (LALMs) have shown impressive capabilities on diverse audio understanding tasks, ranging from speech transcription to music analysis. However, because LALMs are typically trained to produce text-aligned responses, their hidden states are progressively shaped for text generation rather than for preserving acoustic information. As a result, the diverse acoustic content that audio carries, such as phonetic detail, prosody, sound events, affect, and pitch, is lost along the way and difficult to leverage in the response. We introduce Continuous Audio Thinking (CoAT), a framework that equips audio language models with a continuous latent workspace for organizing acoustic information prior to response generation, grounded by distillation from audio experts. Within the thinking space, the model can utilize the rich acoustic information provided by expert distillation when generating its response. Furthermore, the proposed continuous thinking block can be processed in a single prefill, so CoAT does not require additional autoregressive decoding cost over the baseline. Across three LALMs, Qwen2-Audio, Qwen2.5-Omni-7B, and Audio Flamingo~3, performance gains on a broad benchmark suite spanning audio reasoning, audio understanding, music classification, speech emotion, and speech transcription demonstrate the effectiveness of CoAT. Further analysis confirms that the auxiliary supervision propagates from the thinking positions to the model's textual responses.

Gyojin Han, Dong-Jae Lee, Changho Choi +2

KAIST, South Korea

Audio Reasoning Audio Understanding Audio-Language Models Continuous Latent Reasoning Latent Reasoning

Jun 5, 2026eess.AS

Beyond Semantic Dominance: Cognitive Affective Reasoning and Empathetic Response Alignment in Audio Language Models

While Audio Language Models (ALMs) demonstrate strong semantic understanding, they struggle with complex affective interactions. Specifically, textual semantic dominance often overshadows acoustic nuances, and a lack of cognitive depth leads to generic, emotion-agnostic responses. We propose CogAudio-LLM\footnote{ \urlstyle{same} https://github.com/zxzhao0/CogAudio-LLM, a novel cognitive affective reasoning framework. To mitigate semantic dominance, we build LIME-440K, a ``lexically-identical, multi-emotion'' dataset designed to facilitate acoustic-semantic decoupling. We introduce EIPS, a 4-step Chain-of-Thought (CoT) mechanism incorporating psychological reasoning. For inference efficiency, multi-stage training explicitly establishes EIPS via supervised fine-tuning, then distills this logic into an implicit generation process. Finally, we design DR-SAPO (Dual-Route Soft Adaptive Policy Optimization) to dynamically balance the logical rigor of the CoT with the empathetic quality of the direct response.

Zhixian Zhao, Shuiyuan Wang, Wenjie Tian +3

CoT Reasoning Audio Understanding Audio-Language Models Emotion-Aware Dialogue Generation

Jun 5, 2026eess.AS

SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models

Large audio language models (LALMs) extend large language models with an audio encoder and large-scale audio data. However, the scarcity of high-quality annotated audio data remains a fundamental bottleneck for scaling. Through probing signal detectability analysis, we identify fine-grained spectrotemporal perceptual weaknesses in a foundation LALM. To address these challenges, we propose Spectrotemporal Counting (SpectCount), a data-efficient fine-tuning approach based on fully synthetic audio signals generated on-the-fly, without relying on real-world audio, annotations, or pretrained generative models. SpectCount not only resolves the observed weaknesses but also improves performance on diverse auditory benchmarks spanning sound, music, and speech, unseen during fine-tuning. These results suggest that weakness-targeted synthetic signals provide a data-efficient path toward enhanced auditory understanding capabilities in LALMs.

Seonuk Kim, Yonghyeon Jun, Ju Yeon Kang +3

Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea

LLM Fine-Tuning Audio Understanding Audio-Language Models

Jun 5, 2026eess.AS

SEAM: Shortcut-Aware Real-Time Detection of Scripted vs. Spontaneous Speech for Interview Guardrails

Scripted vs spontaneous speech detection is appealing for interview guardrails, but benchmark performance can be inflated by shortcuts tied to corpus identity, channel conditions, and recording artifacts rather than speaking style itself. We present SEAM, a shortcut-aware framework for real-time scriptedness detection that combines uniform preprocessing, seam-aware sampling, non-speech augmentation, and a compact DistilHuBERT backbone. With 8s windows, the model achieves 0.971 +- 0.004 ROC-AUC on an external interview-domain evaluation set. Removing the shortcut-prevention components improves internal held-out metrics but sharply reduces external performance, indicating shortcut learning. Post-training quantization reduces the model footprint to 41.8MB with little loss in external performance. The results demonstrate that robust real-time scriptedness detection depends not only on the backbone, but on shortcut-aware data design and evaluation. We release code and model checkpoints.

Vsevolod, Kovalev, Pranay Manocha

V. · Symbal AI, USA · Princeton University

Audio Understanding Shortcut Learning Audio Classification

Jun 4, 2026cs.SD

FIGMA: Towards FIne-Grained Music retrievAl

Retrieving music using natural language descriptions has improved with contrastive audio-text models such as CLAP, but current systems remain limited to coarse semantic queries. When descriptions specify fine-grained musical attributes such as tempo, key, chord progression, or rhythmic structure, existing models often fail to retrieve the correct audio. We show that this limitation stems from the contrastive learning objective itself: despite being trained on long captions, CLAP-based models effectively utilize only the first few tokens, discarding much of the information encoded in detailed prompts. Then, we propose FIGMA (FIne-Grained Music RetrievAl), a multi-view contrastive architecture that addresses this limitation by jointly optimizing global audio-text alignment and frame-level, token-wise alignment. This design enables FIGMA to capture both high-level semantic context and fine-grained musical attributes within a unified representation space. Moreover, we formalize the task of Fine-Grained Music Retrieval and construct Fine-Grained Music Caption dataset (FGMCaps), a large-scale dataset of 380K music-caption pairs for training along with a 10K test set, both annotated with tempo, key, chord progression, beat count, as well as genre and mood. Extensive experiments demonstrate that FIGMA consistently outperforms existing CLAP-based music retrieval models across multiple music retrieval benchmarks, including out-of-domain evaluations, with relative improvements of up to 73.3%.

Nishit Anand, Ashish Seth, Sreyan Ghosh +2

University of Maryland, College Park, USA

Audio Understanding Audio-Text Retrieval Music Information Retrieval Cross-Modal Feature Matching Multimodal Contrastive Learning

Jun 4, 2026eess.AS

USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding

Audio encoders are critical to modern audio applications as large language models (LLMs) increasingly rely on a single encoder for diverse inputs. While self-supervised learning (SSL) has yielded strong domain-specific encoders like speech or music experts, multi-domain approaches like USAD and SPEAR remain limited in coverage and evaluation. Recent studies also suggest supervised encoders align better with audio LLMs. We present USAD 2.0, a universal encoder integrating knowledge from both SSL and supervised foundation models. USAD 2.0 introduces domain-aware distillation to address teacher mismatch, extends coverage to the music domain, and adds second-stage supervised distillation for downstream use. We further scale the model to one billion parameters via depth scaling. Experiments show USAD 2.0 achieves strong or state-of-the-art performance across probing and LLM-based evaluations.

Heng-Jui Chang, Alexander H. Liu, Saurabhchand Bhati +4

MIT CSAIL, USA · Amazon, USA

Audio Representation Learning Audio Understanding Knowledge Distillation

Jun 4, 2026cs.SD

F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation

Continuous audio autoencoders reconstruct waveforms well but often produce latents with weak structure for understanding, while self-supervised audio encoders capture semantics but are not directly decodable. This mismatch complicates a single audio tokenizer that must support both understanding and generation. We adapt continuous autoencoder latents to this setting with two components: a noise-regularized autoencoder bottleneck and a latent-side representation encoder. The bottleneck uses channel normalization and stochastic perturbation instead of KL-based variational training, yielding scale-controlled continuous latents for reconstruction and autoregressive generation. The representation encoder is trained on frozen autoencoder latents with RQ-MTP and frozen-LLM supervision. The resulting tokenizer provides high-dimensional representations for understanding while preserving normalized continuous latents as generation targets

Dinghao Zhou, Xingchen Song, Di Wu +3

2WeNet Open Source Community · ∗Equal contribution · 1Nanjing University, China

Audio Representation Learning Autoencoders Audio Understanding Audio Tokenization Tokenizer Adaptation Audio Generation

Jun 4, 2026cs.AI

ProSarc: Prosody-Aware Sarcasm Recognition Framework via Temporal Prosodic Incongruity

We present ProSarc, an audio-only framework that detects sarcasm by modelling temporal prosodic incongruity, that is, the mismatch between local prosodic dynamics and the utterance-level emotional baseline. Dual encoding paths, a Global Emotion Encoder and a Temporal Prosody Encoder (BiLSTM + multi-head attention), feed a Prosodic Incongruity Analyzer that produces a scalar incongruity score for classification. Monte Carlo dropout provides uncertainty estimates, and an attention-based mechanism localises sarcastic onset without frame-level labels. ProSarc outperforms prior audio-only methods on MUStARD++ (F1=75.3) and generalises to spontaneous (PodSarc, F1=62.9) and cross-lingual speech (MuSaG, F1=65.6). Ten-run validation confirms the contribution of incongruity modelling (Wilcoxon p=0.002, Cohen's d=1.51). Human evaluation shows that model uncertainty tracks perceptual ambiguity and predicted onsets align with human-annotated temporal windows.

Prathamjyot Singh, Ashima Sood, Sahil Sharma +1

Department of Computer Science and Engineering, Thapar Institute of Engineering and Technology, Patiala, India · School of Computing, Engineering and Intelligent Systems, Ulster University, Londonderry, United Kingdom · School of Computing, Ulster University, Belfast, United Kingdom

Audio Understanding Speech Prosody

Jun 3, 2026cs.SD

Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models

Audio-language models (ALMs) often follow text that conflicts with audio, even when the audio evidence is clear. This raises a basic question: is the audio-supported answer unavailable, or is it represented but overridden by the conflicting text? We examine this question using a same-audio counterfactual that keeps the audio fixed, removes only the conflicting text, and measures the resulting shift in model preference. Across five ALMs and four conflict tasks, 64.1% of conflict samples show a sign flip: the same-audio branch prefers the audio-supported answer, whereas the joint branch prefers the text-supported answer. This pattern suggests that the relevant audio evidence is encoded but loses in arbitration. Activation patching further localizes the reversal to answer-position computation, and patching effects closely track output candidate-score differences (Spearman rho=0.93). Using this diagnostic, we propose Gated Audio Counterfactual Logit Correction (GACL), a training-free decoding rule that interpolates between joint and same-audio scores. Under a strict 5 pp faithfulness-drop budget, GACL improves nAUC by 17.8 points over the best contrastive baseline and transfers without retuning to vision-text arbitration (up to +40.5 pp).

Yichen Gao, Yiqun Zhang, Zijing Wang +7

Northeastern University, China · Shanghai Artificial Intelligence Laboratory, China

Audio-Language Model Evaluation Audio Understanding Audio-Language Models Contrastive Decoding Causal Interventions in Language Models

Jun 3, 2026cs.SD

Audio Interaction Model

Audio is an inherently interactive modality, yet today's Large Audio Language Models (LALMs) are offline, and streaming audio models each handle only a single task such as streaming ASR or voice chatting. It is time to unify them into one online LALM: a model that, through an always-on perceive-decide-respond loop, listens to sound, environment, and instructions in real time and reacts on the fly. We formalize this regime as the Audio Interaction Model, and realize it with Audio-Interaction, a unified streaming model that retains offline task execution while adding online general audio instruction following, from dialogue to full voice chatting, deciding when to respond from the semantics of the stream. To enable this, we propose SoundFlow, a framework that instantiates the perceive-decide-respond loop end to end, from data to training to deployment, through streaming-native data construction, comprehension-aware training, and asynchronous low-latency inference for stable real-time interaction. We further construct StreamAudio-2M, a 2.6M-item streaming corpus spanning 7 fundamental abilities and 28 sub-tasks, and Proactive-Sound-Bench for evaluating proactive audio intervention. Across 8 benchmarks, Audio-Interaction preserves competitive performance on mainstream audio tasks while unlocking capabilities inaccessible to offline LALMs, including real-time ASR, streaming audio instruction following, and proactive help.

Zhifei Xie, Zihang Liu, Ze An +8

1NTU · 2NUS · 3CUHK

Audio Understanding Audio-Language Models Full-Duplex Spoken Dialogue Systems

Jun 3, 2026cs.SD

Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification

Contrastive audio-language models such as CLAP enable zero-shot audio classification: a sound is labelled by matching its embedding to text prompt embeddings, with no labelled audio. This matching breaks down under acoustic noise, where accuracy and mAP fall by 12-30 percentage points at 0 dB SNR on standard benchmarks. We propose Drift Augmented Scoring (DAS), a small per-class bonus added to the cosine score. The bonus rewards a class when the noisy audio embedding drifts in the direction that the class's noise-conditioned text prompts predict. It is derived from text alone, computed once and cached, and adds a single inner product per class at inference, with no gradients and no test-time batch. On a LAION CLAP backbone, we compare DAS against the four variants of Acevedo et al.'s concurrent method on UrbanSound8K and the full FSD50K eval set, mixing each clip with urban acoustic scene noise across a range of SNRs. DAS improves the metric on every test condition: by +2.60 to +5.75 accuracy points on UrbanSound8K and +1.50 to +1.74 mAP points on FSD50K.

Tu Vo, Sheir Zaheer, Chan Y. Park

KC Machine Learning Lab

Few-Shot Audio Classification Audio Understanding Audio-Language Models Noise Robustness Audio Classification

Jun 2, 2026eess.AS

SpeakerCard-1M: An Evidence-Grounded Corpus for In-the-Wild Speaker Verification

Modern speaker verification (SV) systems rely on speaker embeddings that are effective but difficult to interpret or query in natural language. Most existing speech-text corpora target controllable synthesis or utterance-level captioning, offering limited speaker-level supervision for in-the-wild speaker recognition. This paper introduces SpeakerCard-1M, a bilingual speaker resource for evidence-grounded SV, derived from VoxCeleb1/2 and CN-Celeb1/2, where the ``-1M'' suffix refers to the 1.78M utterance-level captions contained in the release. We adopt a tool-first, LLM-last approach in which ten acoustic probes produce field-level evidence, the evidence is aggregated into speaker profiles under a schema that separates relatively stable traits from utterance-level states, and bilingual Speaker Cards are rendered by a constrained LLM that sees only the structured fields. The release includes 56.7k Speaker Card records over 10.2k speakers, 1.78M utterance-level captions, and speaker-ID-disjoint hard-negative triplets. We further define two SV-oriented cross-modal protocols, bidirectional Speaker-Text Retrieval (T2S-R / S2T-R) and Attribute-Conditioned Verification (AC-Verify), and compare a dual-encoder baseline against recent audio language models under a zero-shot forced-choice setting. Joint audio-text training costs only 0.31% absolute EER on VoxCeleb1-O relative to the audio-only baseline. Under a style-symmetric LLM-generated counterfactual protocol, eight recent audio language models (7B-30B+ parameters, both open- and closed-source) score 49-77% on pitch-level AC-Verify in a 2-way forced-choice setting, compared with 88.66% for our dual encoder.

Junyi Peng, Oldřich Plchot, Xiao Song +9

Brno University of Technology, Czechia · Peking University, China · Xiaomi, China +3

Audio-Language Model Evaluation Speaker Verification Audio Understanding

Jun 1, 2026cs.CV

AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs

Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language. However, their audio-visual intelligence (AVI) remains insufficiently evaluated due to the lack of systematic and comprehensive benchmarks. We introduce AVI-Bench, a cognitively inspired benchmark that evaluates Omni-MLLMs across three stages, perception, understanding, and reasoning, through cross-modal tasks requiring joint audio-visual interpretation. This design enables fine-grained diagnosis of model capabilities and failure modes. To further assess robustness beyond familiar domains, we propose AVI-Bench-PriSe, an extension that probes models' primitive audio-visual sensation using unfamiliar, low-semantic stimuli, testing generalization beyond common training distributions. Extensive experiments on both open-source and closed-source models reveal substantial limitations in current Omni-MLLMs. Based on these findings, we present a four-level AVI taxonomy. Overall, AVI-Bench provides a principled evaluation framework to guide the development of more robust and generalizable AVI. Project website: https://fudancvl.github.io/AVI-Bench/

Yaoting Wang, Ziyi Zhang, Wenming Tu +10

Institute of Big Data, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China · Huazhong University of Science and Technology · Shanghai Jiaotong University +5

Audio-Visual Understanding Multimodal Robustness Multimodal Large Language Models Audio Understanding Multimodal Model Evaluation Multimodal Understanding

Jun 1, 2026cs.SD

EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement

Audio tokenizers serve as the discrete interface between continuous audio and Audio Language Models (ALMs), but existing tokenizers often struggle to support both understanding and generation. Reconstruction-oriented codecs preserve acoustic fidelity but lack rich semantics, while semantic-aware tokenizers typically rely on separate semantic and acoustic streams, introducing redundancy or misalignment. We propose \textbf{EntangleCodec}, a unified discrete audio tokenizer that learns caption-aligned semantic-acoustic representations before quantization. By aligning audio with rich captions rather than ASR transcripts, EntangleCodec captures linguistic content, speaker identity, emotion, prosody, and acoustic scenes within a compact token stream. A flow-matching diffusion decoder further enables high-quality reconstruction across speech, music, and general audio. EntangleCodec achieves reconstruction quality competitive with specialized codecs, outperforms all codec-based baselines on audio understanding by up to \textbf{+7.4%} on MMAR, and supports both TTS and TTA generation in a unified framework. Furthermore, EntangleCodec-based audio language models demonstrate strong scaling behavior: even at \textit{0.6B} parameters, the model surpasses specialized continuous-representation LLMs with over \textit{13B} parameters across three benchmarks using \textbf{22

\times

} fewer parameters; scaling to \textit{8B} further establishes new state-of-the-art results on MMAR, highlighting that representation quality is as critical as model scale in audio language modeling. Code and model weights are available at https://github.com/luckyerr/EntangleCodec.

Hui Li, Yangfan Gao, Junlin Shang +4

Fudan University

Audio Representation Learning Neural Audio Codecs Audio Understanding Audio-Language Models Audio Tokenization Discrete Speech Representation Learning

Jun 1, 2026cs.SD

Echo: A Joint-Embedding Predictive Architecture for Speaker Diarization and Speech Recognition in a Shared Latent Space

We present Echo, a proof-of-concept audio system built around a single 25 M-parameter ViT encoder. The encoder is pretrained with a JEPA objective and then specialised by stages to carry speaker identity, phonetic content, and dynamic source routing in the same 512-dimensional latent space, with no per-task fine-tuning at deployment. Light heads handle diarization (ArcFace + VBx) and dynamic source separation (null-target K-set prediction). On synthetic VoxCeleb2 mixtures with unknown K, the canonical stack reaches 15.00% blind DER, 97.80% PIT separation accuracy with +9.52 dB latent SI-SDR, and a +53.50-point speaker/content factorisation gap on a held-out k-NN probe. The point of Echo is not a new SOTA on any single task but the joint coexistence of three tasks on one encoder at this footprint. We document the design stage by stage, report the dead-ends, and identify the structural wall on end-to-end ASR through the VQ bottleneck that still bounds the PoC.

Louis Mouchon

Independent Research

Audio Representation Learning Joint-Embedding Predictive Architecture Speech Processing Audio Understanding Automatic Speech Recognition Speaker Diarization+1

Jun 1, 2026cs.SD

MOSS-Audio Technical Report

MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware question answering, timestamped transcription, and audio-grounded reasoning. MOSS-Audio couples a dedicated audio encoder with a modality adapter and a large language model: the encoder produces 12.5 Hz temporal representations, the adapter projects them into the decoder space, and the decoder generates autoregressive text outputs. Two design choices are central to the system: DeepStack cross-layer feature injection, which exposes the decoder to acoustic information from multiple encoder depths, and time markers, which provide explicit temporal cues by inserting timestamp markers into the audio-token stream. At the data level, we design an event-preserving audio annotation pipeline that segments raw audio at coherent event boundaries, applies branch-specific annotation to speech, music, and general audio, and merges the results into unified captions for pretraining. The intermediate branch-specific captions are further retained to support the construction of task-oriented SFT data. The model is pretrained on large-scale audio-language data, with time-aware objectives incorporated to support temporal grounding, and then undergoes multi-stage post-training to enhance instruction following and audio-grounded reasoning. We release 4B and 8B variants in both Instruct and Thinking configurations. MOSS-Audio achieves strong performance across general audio understanding, speech captioning, ASR, and timestamped ASR, positioning it as a promising understanding foundation for future voice agents.

Chen Yang, Chufan Yu, Hanfu Chen +27

Audio Understanding Audio-Language Models Automatic Speech Recognition Temporal Audio Grounding Audio Captioning

May 31, 2026eess.AS

Context-aware child-directed speech detection from long-form recordings

Automatically distinguishing child-directed speech from adult-directed speech in long-form recordings is key to scalable analyses of children's language environments. Existing approaches process utterances in isolation and have been evaluated primarily on English. We address these gaps along three dimensions. First, we fine-tune and evaluate six-self supervised models on a multilingual dataset of 182 children, showing that in-domain pre-training on child-centered recordings substantially outperforms models trained on adult speech. Second, we demonstrate that incorporating surrounding context substantially improves classification, with an absolute gain of 13.8% in average F1-score. Third, we evaluate our model in a realistic end-to-end pipeline, from adult speech detection to addressee classification, showing that performance drops under automatic segmentation but still consistently outperforms a rule-based baseline.

Théo Charlot, Tarek Kunze, Kaveri K. Sheth +2

LSCP, DEC, ENS, EHESS, CNRS, PSL University, France · Laboratoire d’Informatique et Syst`emes, Universit´e Aix-Marseille, CNRS, France

Speech Processing Audio Understanding Self-Supervised Speech Representation Learning

May 31, 2026cs.CL

PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects

While End-to-End (E2E) Speech-Large Language Models (Speech-LLMs) are rapidly evolving, their evaluation methodologies remain limited to the era of simple transcription. Existing benchmarks suffer from three critical limitations: a pronounced bias towards high-resource languages, a focus on low-level recognition (ASR) rather than semantic reasoning, and a neglect of regional dialects. To bridge this gap, we introduce PolySpeech-100, a massive-scale benchmark designed to assess `native-level' speech comprehension across 110 linguistic variants. We employ a novel hybrid construction pipeline that augments gold-standard human recordings with instruction-driven synthetic speech, allowing us to cover 19 distinct Chinese dialects and over 80 low-resource languages. Extensive evaluation of 22 state-of-the-art models (including Gemini-3, GPT-Audio, and Qwen2.5-Omni) yields pivotal insights. First, we demonstrate that open-source E2E models outperform Cascade (ASR+LLM) systems on heavy dialects, proving that direct audio processing preserves critical paralinguistic cues and prosodic features (e.g., intonation, stress) that are often lost in standard transcription. Second, we reveal a significant performance gap: while commercial models maintain robustness, open-source models suffer catastrophic degradation on low-resource languages. Finally, counter-intuitively, we observe that under standard zero-shot settings, Chain-of-Thought prompting frequently degrades speech understanding performance for most evaluated models, revealing a potential modality alignment gap in current architectures. PolySpeech-100 establishes a rigorous standard for the next generation of inclusive, omni-capable Speech-LLMs. The data, demo, and code are publicly available at https://github.com/YoungSeng/PolySpeech-100.

Sicheng Yang, Shulan Ruan, Shiwei Wu +4

Shenzhen International Graduate School, Tsinghua University Shenzhen, China · Department of Electronic Engineering, Tsinghua University Beijing, China · JD AI Research Beijing, China

Audio-Language Model Evaluation Audio Understanding Speech Language Models Low-Resource Language Processing Multilingual ASR

May 29, 2026cs.CL

UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perception

Semantic speech tokenizers have become a widely used interface for Audio-LLMs, owing to their compact single-codebook design and strong linguistic alignment. However, their focus on linguistic abstraction induces acoustic blindness, limiting their applicability beyond speech-centric tasks. We propose UniAudio-Token, a framework that empowers semantic tokenizers with general audio perception without compromising speech ability. Instead of altering the semantic paradigm, UniAudio-Token mitigates its information loss through two key innovations: (1) Semantic-Acoustic Primitives (SAP) provide structured supervision by decomposing audio into linguistic content, vocal attributes, and auditory-scene primitives; and (2) Semantic-Acoustic Equilibrium (SAE) introduces a content-aware gating mechanism that adaptively restores fine-grained acoustic details from shallow layers. Extensive evaluations show that UniAudio-Token learns comprehensive universal representations while preserving high-fidelity speech generation. When integrated with downstream LLMs, it outperforms all single-codebook baseline tokenizers on both understanding and generation tasks, effectively serving as a unified audio interface. We publicly release all our code, including training and inference scripts, together with the model checkpoints at https://github.com/Tencent/Universal_Audio_Tokenizer.

Yuhan Song, Linhao Zhang, Aiwei Liu +6

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

Audio Representation Learning Audio Understanding Audio Tokenization Discrete Speech Representation Learning

May 28, 2026cs.SD

HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding

Unified speech foundation models require a holistic tokenization space that is both learnable by language models and decodable into high-quality waveforms. Existing speech tokenizers, however, often fail to satisfy these requirements simultaneously, leading to increased architectural complexity and more involved training designs. We propose HoliTok, a continuous Holistic speech Tokenization model designed for unified generation-understanding modeling. HoliTok encodes 48~~kHz speech into a compact 25~~Hz sequence of 128-dimensional latents. It is trained with a progressive strategy that jointly preserves signal-level fidelity, incorporates semantic information, and maintains strong latent learnability. Based on this tokenization, we build a unified AR+DiT model for speech synthesis and recognition, where the same latent sequence supports both generation-specific and unified generation-understanding tasks. Experiments show that HoliTok achieves competitive reconstruction fidelity, improves generative learnability for high-quality and controllable synthesis, and, among the evaluated representations, is the only one that operates robustly in our unified generation-understanding architecture without additional optimization tricks. These results suggest that HoliTok serves as an effective speech tokenizer and a foundational representation interface for unified spoken language modeling. The code is available at: https://github.com/bovod-sjtu/HoliTok.

Bohan Li, Shi Lian, Hankun Wang +6

X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, China · hi lab, Xiaohongshu Inc, China

Audio Representation Learning Speech Foundation Models Speech Processing Audio Understanding Audio Tokenization Controllable Speech Generation+1

May 28, 2026cs.SD

COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings

Contrastive Language-Audio Pretraining (CLAP) models are widely used for audio understanding and support modality-agnostic condition swapping in many zero-shot applications. However, their performance is heavily affected by the modality gap between audio and text embeddings. Existing explanations mainly attribute this gap to the cone effect, treating it as a shift between mean embeddings, yet correcting the mean alone yields only limited improvements. Alternative hypotheses, such as information imbalance and dimensionality collapse, have also been proposed, but they remain insufficiently verified and have not been thoroughly studied in the audio domain. Meanwhile, several works attempt to decompose multimodal contrastive embeddings into interpretable concepts, but none explicitly analyze the modality gap from the perspective of concept decomposition. In this work, we introduce COMET (Concept space Organization and Modality gap Explanation with PLS-SVD Transformation), a novel partial least squares singular value decomposition (PLS-SVD) framework for CLAP that unveils a broader perspective of the modality gap. Our framework reveals that only a small, interpretable subset of axes, which captures shared concepts, contributes substantially to similarity computation, and that the mean component represents only partially the modality gap. Building on this insight, we propose a simple spectral truncation method that mitigates the modality gap in a training-free manner. The method enables zero-shot audio captioning with condition swapping to approach fully supervised performance, without requiring large auxiliary memory banks or expensive computation. At the same time, it achieves substantial embedding dimensionality reduction while preserving strong performance on retrieval and audio captioning tasks.

Yonggang Zhu, Liting Gao, Aidong Men +1

School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China · Centre for Vision, Speech, and Signal Processing (CVSSP), University of Surrey, GU2 7XH Guildford, U.K.

Audio Understanding Audio-Language Models Multimodal Embedding Audio Captioning Multimodal Contrastive Learning

May 28, 2026cs.CL

MusTBench: Benchmarking and Advancing Temporal Grounding in Music LLMs

Recent Large Audio-Language Models (LALMs) have demonstrated promising abilities in understanding musical content. However, whether their responses are grounded in the correct temporal regions of the audio remains underexplored. This limitation is particularly critical for music understanding, where key information often occurs as temporally localized events, such as instrument entries and rhythmic transitions. To address this gap, we introduce MusTBench, a music-expert-validated benchmark designed to evaluate temporal grounding in LALMs through five temporally grounded question-answering tasks. To further improve temporal grounding in existing models, we propose MusT, a novel four-stage temporal optimization recipe spanning music encoder adaptation, LLM adaptation, LLM supervised fine-tuning, and RL-based optimization. Experiments on MusTBench show that existing LALMs struggle with precise temporal grounding, while MusT brings significant improvements over strong baselines. These results establish temporal grounding as a key missing capability in current LALMs and position MusTBench as a challenging benchmark for future research in temporally grounded music understanding.

Daeyong Kwon, Qiyu Wu, Shinobu Kuriya +6

1Seoul National University · 2Sony Group Corporation · 3Sony AI

Audio-Language Model Evaluation Audio Understanding Audio-Language Models Temporal Audio Grounding

May 28, 2026cs.SD

ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood

We present ChildVox, a novel benchmark for characterizing the diverse acoustic signals through which children communicate. Specifically, ChildVox follows the full developmental trajectory from birth through school age, covering physiological sounds, non-linguistic vocalizations, canonical syllables, and spoken language. ChildVox integrates more than 20 sub-tasks across 17 child-centered audio and speech datasets, enabling systematic cross-corpus and cross-domain comparison. We evaluate a representative range of audio and speech foundation models, including self-supervised, ASR-oriented, and large audio-language models, on tasks including physiological sound classification, vocalization and canonical syllables modeling, and speech quality assessment and recognition. Benchmark results show that ChildVox provides a suite of high-performance models in recognizing a wide range of acoustic signals from children, supporting downstream applications such as characterizing children's language levels and tracking speech production with age. Our benchmark models on public datasets are released at: https://github.com/tiantiaf0627/childvox-release.

Tiantian Feng, Anfeng Xu, Xuan Shi +10

University of Southern California · The Ohio State University · University of California, Los Angeles +3

Audio-Language Model Evaluation Speech Quality Assessment Speech Processing Audio Understanding Automatic Speech Recognition Child Language Acquisition+1

May 27, 2026eess.AS

Audio-Mind: An Auditable Agentic Framework for Audio Understanding

Audio agents extend large audio-language models (LALMs) by decomposing audio questions into tool calls, intermediate evidence, and iterative reasoning steps. However, as LALMs become stronger, the key challenge shifts from enabling tool use to determining when agentic evidence acquisition genuinely benefits audio understanding. We propose Audio-Mind, an auditable and pluggable framework for conditional evidence acquisition in audio understanding. Audio-Mind dynamically combines a strong frontend with planner-guided tool use, preserving frontend judgment when initial evidence is sufficient while acquiring bounded external evidence for questions with unresolved evidence gaps. Experiments on MMAR and MSU-Bench show that Audio-Mind outperforms prior audio-agent baselines, reaching 80.4% accuracy on MMAR and 82.8% accuracy on MSU-Bench. A matched-backbone comparison highlights why this design matters: under strong audio frontends, agentic decomposition can become an orchestration bottleneck when the workflow does not preserve the frontend's holistic audio-grounded judgment. Beyond accuracy, Audio-Mind produces higher-quality, auditable reasoning traces that expose uncertainty, tool evidence, and answer rationales, offering a potential basis for more reliable audio-QA annotation and error analysis.

Yucheng Wang, Jing Peng, Hanqi Li +6

School of Intelligence Science and Technology, Nanjing University, China · X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, China · School of Automation Science and Engineering, Xi’an Jiaotong University, China +1

Audio QA Audio Reasoning Audio Understanding Audio-Language Models LLM Agents

May 27, 2026cs.CL

KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evaluating SpeechLMs

Speech language models (SpeechLMs) have achieved substantial progress by extending large language models (LLMs) to the speech modality. However, SpeechLM evaluation remains heavily centered on English, limiting reliable assessment of multilingual speech capabilities. Straightforward benchmark transfer through ASR, translation, normalization, and TTS can corrupt language-specific instructions, answer constraints, and spoken forms; for audio understanding, transferring source-language audio also fails to preserve target-language speaker attributes, accents, and paralinguistic properties. To address these limitations, we propose two human-agent benchmark-construction frameworks: one transfers source-language SpokenQA benchmarks into target-language SpokenQA benchmarks, and the other converts target-language ASR corpora into audio understanding benchmarks using transcriptions and speaker metadata. Using these frameworks, we construct and publicly release three Korean speech benchmarks: KVoiceBench and KOpenAudioBench for Korean SpokenQA, and KMMAU for Korean audio understanding, comprising 12,345 samples in total. We evaluate eight recent SpeechLMs and find that English-Korean performance gaps vary substantially across models and task families, and that SpokenQA and audio understanding rankings diverge, revealing complementary weaknesses invisible to English-only evaluation.

Haechan Kim, Seungjun Chung, Inkyu Park +2

1KRAFTON · Department of Mathematical Sciences, Seoul National University

Audio-Language Model Evaluation Question Answering Audio Understanding

May 27, 2026cs.SD

VoiceGiraffe: A Benchmark for Extreme Long-Context Audio-Language Understanding

While large audio language models (LALMs) have achieved remarkable progress in audio processing at the second- or minute-level scale, understanding hour-level audio remains a fundamental bottleneck. Existing benchmarks predominantly rely on short clips or artificially concatenated segments, failing to faithfully assess LALM capacity for long-range information comprehension in real-world scenarios such as podcasts and lengthy speeches. To address this gap, we introduce VoiceGiraffe, a novel benchmark designed to rigorously evaluate LALMs across diverse real-world scenarios, modalities, and languages under long-context settings. It comprises 1500 curated triplets structured into a dual-level taxonomy of single-hop perception and multi-hop reasoning. We evaluate a broad suite of open-source and proprietary LALMs against human performance. Results underscore three fundamental findings. First, VoiceGiraffe remains highly challenging and far from saturation. Second, we show that no single inference paradigm universally dominates. The E2E inference benefits models with native long-context audio understanding, cascaded caption aggregation stabilizes small models overwhelmed by hour-scale audio, and reasoning-enhanced cascading with external LLM helps weaker models but can bottleneck stronger proprietary systems. Third, we reveal long-range memory persistence as a key bottleneck. LALMs are better at answering questions that require connecting salient causal cues than those requiring sustained tracking of sparse events across long audio, whereas humans show the opposite pattern. These findings position VoiceGiraffe as a challenging and diagnostic testbed for long-form audio understanding, highlighting the need for LALMs with persistent memory and robust long-range aggregation.

Jashin Ye, Dongxiao Wang, Yixuan Ye +10

Future Living Lab, Alibaba

Audio-Language Model Evaluation Audio Understanding Audio-Language Models Long-Context Modeling

May 27, 2026eess.AS

LoSATok: Low-dimensional Semantic-Acoustic Tokenizer for Cross-Domain Audio Understanding and Generation

Audio tokenizers are fundamental to unifying audio understanding and generation. Understanding requires high-level semantics, while generation demands semantic and acoustic details. Existing unified tokenizers jointly encode both in high-dimensional continuous latents, which increases the modeling burden of Diffusion Transformers (DiTs) for generation. We propose LoSATok, a low-dimensional audio tokenizer for cross-domain audio understanding and generation. Motivated by the observation that 1280-dimensional semantic encoder features are compressible, we introduce a Semantic Bottleneck that compresses them into 128 dimensions, regularized by the proposed time-relation loss for temporal feature consistency. We further design a dual-level semantic supervision method that leverages both high- and low-dimensional semantic signals, enabling the tokenizer to jointly capture semantics and acoustic details within a compact latent space. Experiments on speech, music, and general audio show that SemBo preserves strong low-dimensional semantic capacity and LoSATok retains competitive understanding performance compared with several semantic representations, while consistently improving DiT modeling performance on speech, music, and audio generation. These results demonstrate that LoSATok's low-dimensional representations can effectively support audio understanding and generation. Our code is provided at https://github.com/wxzyd123/LoSATok.

Zhisheng Zhang, Xiang Li, Yixuan Zhou +3

1Shenzhen International Graduate School, Tsinghua University, China · *Work conducted while interning at ModelBest. · 2ModelBest Inc., China

Audio Token Compression Audio Representation Learning Audio Understanding Audio Tokenization Audio Generation

May 26, 2026cs.SD

Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox

Audio large language models (Audio LLMs) demonstrate strong performance on speech understanding tasks, yet their ability to understand paralinguistic information remains limited. To systematically quantify this issue, we introduce VoxParadox, an adversarial benchmark with 2,000 verified examples, spanning 10 paralinguistic tasks, created with controlled speech synthesis to intentionally mismatch transcript claims and speaking style, enabling direct measurement of speech paralinguistic understanding. Evaluation of a diverse set of Audio LLMs reveals consistently low accuracy on acoustic ground truth and a strong tendency to follow language-implied (incorrect) answers. To understand the cause of this gap, we perform layer-wise probing and find that (i) paralinguistic cues can degrade in deeper encoder layers and at the encoder--LLM interface, and (ii) even when such cues are available in audio tokens, the language model frequently ignores them. To address these problems, we propose Prompt-Conditioned Layer Mixer (PCLM), which adaptively combines information from multiple audio layers based on the input prompt, and pair it with Direct Preference Optimization (DPO) to explicitly prefer acoustically supported options over language-implied alternatives. These methods substantially improve Audio LLM paralinguistic understanding, improving Audio Flamingo 3 from 17.40% to 65.20% on VoxParadox, and from 37.74% to 54.78% on MMSU paralinguistic subset. Our project page is available at https://voxparadox.github.io/.

Jiacheng Pang, Ashutosh Chaubey, Mohammad Soleymani

Institute for Creative Technologies, University of Southern California, Los Angeles, USA

Audio-Language Model Evaluation Speech Processing Audio Understanding Audio-Language Models

May 26, 2026cs.SD

MERIT: Learning Disentangled Music Representations for Audio Similarity

Current music similarity models typically compute a single, monolithic score, entangling distinct musical dimensions like melody, rhythm, and timbre. This limits user control and interpretability, making it impossible to execute nuanced queries. We introduce MERIT, a framework for learning disentangled, factor-specific music representations tailored to these three core dimensions. To overcome the lack of isolated musical variations in real-world audio, we use a novel training strategy that uses conditional audio generation and source-separated stems to strongly encourage single-factor variation in training data. Our evaluations demonstrate strong factor-wise disentanglement. Each head responds strongly to its intended perceptual dimension while remaining near chance on the others, a representational property that holds across both the synthetic training domain and independent real-world audio.

Abhinaba Roy, Junyi Liang, Dorien Herremans

Singapore University of Technology and Design

Disentangled Representation Learning Audio Representation Learning Audio Understanding Music Information Retrieval