{"total":34,"items":[{"citing_arxiv_id":"2607.01733","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving","primary_cat":"cs.CL","submitted_at":"2026-07-02T05:42:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"JSTIP interleaves speech and text sequences during pretraining on 38k hours of ASR data to improve entity accuracy over ASR-only and simple joint-training baselines while matching performance from domain text.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26968","ref_index":126,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RedVox: Safety and Fairness Gaps in Speech Models Across Languages","primary_cat":"cs.CL","submitted_at":"2026-06-25T12:40:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"RedVox benchmark shows speech model safety and fairness vulnerabilities persist under non-adversarial conditions, worsen in non-English languages, and increase with spoken inputs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.25391","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models","primary_cat":"cs.SD","submitted_at":"2026-06-24T04:42:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Introduces CASU benchmark with four tasks to evaluate context-aware auditory scene understanding in LALMs via semi-synthetic audio compositions of speech, events, and environments.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21408","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Vaani Benchmark V1.0: An Inclusive Multimodal Benchmark Dataset for Hindi","primary_cat":"eess.AS","submitted_at":"2026-06-19T13:20:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Vaani Benchmark V1.0 is a multimodal Hindi ASR dataset from 104 districts featuring spontaneous speech recordings in real-world conditions and three independent transcriptions per segment for robust multi-reference evaluation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19157","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages","primary_cat":"eess.AS","submitted_at":"2026-06-17T14:59:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"IndicContextEval is a new 56-hour multilingual benchmark and 7-level prompting framework for evaluating context utilization in AudioLLMs across 8 Indic languages.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18134","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Grounding Spoken LLMs in Multi-Speaker Audio via Diarization Conditioning","primary_cat":"eess.AS","submitted_at":"2026-06-16T16:34:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Dixtral uses diarization conditioning on a Whisper-based encoder within Voxtral to outperform baselines on multi-speaker transcription and match or exceed on QA tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.13464","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversations","primary_cat":"cs.CL","submitted_at":"2026-06-11T15:18:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces ontology memory-augmented ASR correction that organizes prior interaction history into retrievable nodes and reports gains over direct correction in 9 of 10 backbone-setting pairs on a new long-context dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.14784","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LLM-Based Synthetic Ground Truth Generation for Audio-Based Emotion Classification via In-Context Learning","primary_cat":"cs.SD","submitted_at":"2026-06-10T11:08:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Proposes an LLM agentic workflow with retrieval-based in-context learning to generate synthetic ground truth for audio emotion classification in multi-user VR environments.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09335","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Factors affecting ASR performance: A study using state of the art ASR models in Indic Languages","primary_cat":"eess.AS","submitted_at":"2026-06-08T11:03:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Empirical analysis of speaker and acoustic factors correlated with ASR word error rates across five Indic languages using zero-shot evaluation on multiple open-source models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08194","ref_index":69,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large Audio-Language Models","primary_cat":"cs.CL","submitted_at":"2026-06-06T14:24:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"GlobeAudio is a new multilingual multicultural benchmark for naturalistic evaluation of large audio-language models, showing performance gaps especially for open-source models and low-resource languages.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06211","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition","primary_cat":"cs.CL","submitted_at":"2026-06-04T14:20:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"FiLM speaker conditioning allows a SpeechLLM to adapt to pathological speakers competitively with fine-tuning while keeping general performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06177","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Ouvia: A User-centered Framework for Measuring Usability of Speech Translation in Real-World Communication Scenarios","primary_cat":"cs.CL","submitted_at":"2026-06-04T13:52:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Ouvia is a user-centered evaluation framework for speech translation usability in real-world scenarios, showing limited usability rates and the superiority of QA-based metrics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06037","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SpeechJBB: Probing Safety Alignment and Comprehension in Large Audio Language Models under Code-Switched Speech","primary_cat":"cs.SD","submitted_at":"2026-06-04T11:31:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SpeechJBB benchmark shows substantially high jailbreak success rates for LALMs on code-switched harmful audio, highest for non-English cases, with pseudo-word insertion further lowering refusal rates.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03241","ref_index":58,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Benchmarking Speech-to-Speech Translation Models","primary_cat":"cs.CL","submitted_at":"2026-06-02T07:01:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"COMPASS is a new reproducible benchmarking framework for S2ST that deploys 46 metrics on 1248 configurations, shows single-metric rankings mislead, reduces to 10 metrics per direction, and finds domain-specific metrics better match human judgments than standalone MOS predictors.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01483","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MURMUR: An Efficient Inference System for Long-Form ASR","primary_cat":"cs.LG","submitted_at":"2026-05-31T22:54:57+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Murmur matches single-pass long-context ASR accuracy on AMI-IHM while cutting latency 4.2x by tuning chunk size and using intra-chunk attention sparsity via KV eviction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00168","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RealityTest: How People Probe AI Identity and Whether Models Disclose It","primary_cat":"cs.CL","submitted_at":"2026-05-29T12:40:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"RealityTest is a human-grounded multilingual multimodal benchmark showing that only 31% of people ask AI identity directly and that suppression instructions plus question phrasing dominate disclosure behavior over model choice.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20414","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PlanRAG-Audio: Planning and Retrieval Augmented Generation for Long-form Audio Understanding","primary_cat":"eess.AS","submitted_at":"2026-05-19T19:10:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"PlanRAG-Audio introduces planning-based retrieval-augmented generation to improve accuracy and stability of long-form audio understanding in LALMs by decoupling model input from raw audio duration.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17370","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CBT-Audio: Evaluating Audio Language Models for Patient-Side Distress Intensity Estimation in CBT Session Recordings","primary_cat":"cs.AI","submitted_at":"2026-05-17T10:27:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CBT-Audio dataset shows that adding audio input improves distress intensity estimation over transcripts alone for 8 of 10 audio language models, with clearest gains when verbal content and vocal delivery diverge.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.25591","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","primary_cat":"eess.AS","submitted_at":"2026-04-28T12:56:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Semantic-level and verification-based uncertainty methods outperform token-level baselines for audio reasoning in ALLMs, but their relative performance on hallucination and unanswerable-question benchmarks is model- and task-dependent.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024, pp. 19 186-19 199. [9] S. Ghosh, A. Goel, J. Kim, S. Kumar, Z. Kong, S.-g. Lee, C.-H. H. Yang, R. Duraiswami, D. Manocha, R. Valleet al., \"Audio flamingo 3: Advancing audio intelligence with fully open large audio language models,\" inThe Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. [10] A. H. Liu, A. Ehrenberg, A. Lo, C. Denoix, C. Barreau, G. Lample, J.-M. Delignon, K. R. Chandu, P. von Platen, P. R. Muddireddyet al., \"V oxtral,\"arXiv preprint arXiv:2507.13264, 2025. [11] J. Xu, Z. Guo, J. He, H. Hu, T. He, S. Bai, K. Chen, J. Wang, Y . Fan, K. Danget al., \"Qwen2. 5-omni technical report,\"arXiv preprint arXiv:2503.20215, 2025. [12] C."},{"citing_arxiv_id":"2604.24401","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation","primary_cat":"cs.SD","submitted_at":"2026-04-27T12:25:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Audio-language models retain 60-72% of benchmark scores without audio, and most audio-dependent items can be solved from short fragments rather than full clips.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19565","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps","primary_cat":"cs.CL","submitted_at":"2026-04-21T15:18:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Four attention metrics enable logistic regression classifiers that detect hallucinations in SpeechLLMs with up to +0.23 PR-AUC gains over baselines on ASR and translation tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18105","ref_index":13,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR","primary_cat":"eess.AS","submitted_at":"2026-04-20T11:21:06+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A 2.3B-parameter LLM-based ASR system achieves competitive recognition accuracy and reduced hallucination through a multi-stage training paradigm with asynchronous encoder updates, ASR-specialized RL, and phoneme-level RAG for hotword customization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14604","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection","primary_cat":"cs.CR","submitted_at":"2026-04-16T04:22:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AudioHijack generates imperceptible adversarial audio via gradient estimation, attention supervision, and reverberation blending to hijack 13 LALMs with 79-96% success on unseen contexts and real commercial agents.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[10], enabling them to autonomously invoke external ser- vices, operate applications, and issue actionable commands. However, the very capabilities that grant LALMs mul- timodal perception and advanced autonomy also introduce new avenues for misuse or adversarial manipulation. Re- cent research has revealed that LALMs are susceptible to audio jailbreak attacks [11] that craft audio inputs to trigger harmful responses. These attacks either vocalize well-crafted jailbreak prompts or deliver harmful speech into the audio channel. The former exploits the misalignment of the LLM backbone [12], [13], while the latter relies on signal aug- mentation [14], [15] or adversarial perturbations [16]-[18] to increase escape from safeguards."},{"citing_arxiv_id":"2604.14493","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Pushing the Limits of On-Device Streaming ASR: A Compact, High-Accuracy English Model for Low-Latency Inference","primary_cat":"cs.AI","submitted_at":"2026-04-16T00:04:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A quantized int4 version of Nemotron ASR runs faster than real-time on CPU at 8.20% WER and 0.67 GB size, setting a new efficiency point for on-device streaming speech recognition.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08003","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs","primary_cat":"eess.AS","submitted_at":"2026-04-09T09:07:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A multi-stage training method for LLM-based ASR uses new entropy allocation metrics to achieve competitive benchmark performance with 2.3B parameters while mitigating hallucinations via better encoder-LLM decoupling.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"For a Gaussian random vectorZ∈R k with covarianceΣ Z, its differential entropy is given by h(Z) = 1 2 log (2πe)k det ΣZ \u0001 .(17) This shows that, under a Gaussian assumption, entropy is fully determined by the covariance structure through its log- determinant. Proposition B.1(Gaussian mutual information in log-det form).Let A∈R dA and B∈R dB be jointly Gaussian random variables with joint covariance Σ[A,B] = \u0014ΣAA ΣAB ΣBA ΣBB \u0015 .(18) Then their mutual information admits the closed-form expression I(A;B) = 1 2 log det ΣAA det ΣBB det Σ[A,B] .(19) Proof.By definition, I(A;B) =h(A) +h(B)−h(A, B).(20) Since(A, B)is jointly Gaussian, its marginals are also Gaussian. Therefore, h(A) = 1 2 log (2πe)dA det ΣAA \u0001 ,(21) h(B) = 1 2 log (2πe)dB det ΣBB \u0001 ,(22) h(A, B) = 1 2 log (2πe)dA+dB det Σ[A,B]"},{"citing_arxiv_id":"2604.03995","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning","primary_cat":"cs.CV","submitted_at":"2026-04-05T06:32:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Coordinated multi-modal typographic attacks on MLLMs achieve 83.43% success rate versus 34.93% for single-modality attacks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.25551","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Voxtral TTS","primary_cat":"cs.AI","submitted_at":"2026-03-26T15:23:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Voxtral TTS produces expressive multilingual speech from 3-second reference audio with a hybrid autoregressive-plus-flow-matching architecture and a new VQ-FSQ tokenizer, achieving 68.4% win rate over ElevenLabs in human evaluations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.11298","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Voxtral Realtime","primary_cat":"cs.AI","submitted_at":"2026-02-11T19:17:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Voxtral Realtime is an end-to-end trained streaming ASR model that achieves Whisper-level transcription quality at 480ms delay after scaling pretraining across 13 languages.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.09270","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus","primary_cat":"cs.CL","submitted_at":"2026-01-14T08:05:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MCGA is a new 119-hour multi-task audio corpus for classical Chinese literary genres that shows current MLLMs face substantial challenges on its test set.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.16378","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","primary_cat":"cs.CL","submitted_at":"2025-12-18T10:21:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Cascaded systems remain the most reliable for speech translation overall, but recent SpeechLLMs match or outperform them in many conditions while standalone speech models lag.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.01512","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages","primary_cat":"cs.CL","submitted_at":"2025-12-01T10:39:12+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MCAT scales MLLMs to many-to-many speech translation across 70 languages via curriculum learning and a 30-token speech adapter, surpassing prior SOTA on FLEURS while improving speed.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.00626","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"When Silence Matters: The Impact of Irrelevant Audio on Text Reasoning in Large Audio-Language Models","primary_cat":"cs.SD","submitted_at":"2025-10-01T07:59:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Irrelevant audio including silence reduces accuracy and increases volatility in text reasoning for large audio-language models, with effects worsening at longer durations, higher amplitudes, and higher temperatures.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.14804","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages","primary_cat":"cs.SD","submitted_at":"2025-09-18T09:59:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Introduces XLSR-Thai encoder, U-Align alignment, and Thai-SUP data pipeline to enable multitask speech understanding SLLMs for Thai.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.08031","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AU-Harness: An Open-Source Toolkit for Holistic Evaluation of Audio LLMs","primary_cat":"cs.SD","submitted_at":"2025-09-09T15:30:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AU-Harness introduces an efficient unified evaluation framework for audio LLMs featuring batch optimizations, multi-turn dialogue support, and standardized protocols for fair comparisons.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}