{"total":30,"rows":[{"id":"2512.16378","title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","created":"2025-12-18","cited_by_count":7,"area":null},{"id":"2510.00628","title":"Hearing the Order: Investigating Position Bias in Large Audio-Language Models","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2604.25591","title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","created":"2026-04-28","cited_by_count":4,"area":null},{"id":"2603.06193","title":"Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2606.19157","title":"IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2603.09714","title":"MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2603.10035","title":"TriageSim: A Conversational Emergency Triage Simulation Framework from Structured Electronic Health Records","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2607.13477","title":"Auditing Protocol-Level Shortcuts in Large Audio Language Model Judges for Speech Evaluation","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2606.06211","title":"FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2609.16582","title":"CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2512.14876","title":"Isolated Sign Language Recognition with Segmentation and Pose Estimation","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2601.15118","title":"WavLink: Compact Audio-Text Embeddings with a Global Whisper Token","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2605.28642","title":"Parameter- and Bandwidth-Efficient Edge--cloud Many-to-Many Speech-to-Text Translation","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.14784","title":"LLM-Based Synthetic Ground Truth Generation for Audio-Based Emotion Classification via In-Context Learning","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.15984","title":"ROMPAR: Morphological Completion and Demographic Unlearning for Romanian-Accented Speech Recognition","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.21395","title":"Atomistic Language Models Understand and Generate Materials","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.26968","title":"RedVox: Safety and Fairness Gaps in Speech Models Across Languages","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.03207","title":"S-DiverSe: Spanish Diverse Speech","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.10387","title":"GigaChat Audio: Time-aware Large Audio Language Model","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.13717","title":"StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.16203","title":"INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.11724","title":"The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.11762","title":"Component-Aware Differential Privacy for Federated Multilingual Speech-LLMs","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.22260","title":"Causal Localization of the Refusal Direction in Audio Language Models","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.22771","title":"ParA-LLM: A Unified Approach to Paralinguistic and Acoustic Speech Understanding","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.23825","title":"Federated Multilingual Speech-LLMs: Architecture and Aggregation Strategy Benchmarking","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.27382","title":"When Entanglement Lower-Bounds Disparity: Auditing and Repairing Demographic Fairness in Audio Understanding Models","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.28713","title":"Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing?","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.36920","title":"Benchmarking Automatic Speech Recognition Tools for Iberian Languages","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.10145","title":"InterView-C: A Synchronized Multimodal Corpus of VR Avatar-Mediated Survey Interviews","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}