{"total":21,"rows":[{"id":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"area":null},{"id":"2507.12705","title":"AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation","created":"2025-07-17","cited_by_count":21,"area":null},{"id":"2601.23255","title":"Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Models","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2505.19103","title":"WHISTRESS: Enriching Transcriptions with Sentence Stress Detection","created":"2025-05-25","cited_by_count":7,"area":null},{"id":"2505.22765","title":"StressTest: Can YOUR Speech LM Handle the Stress?","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2406.11065","title":"Can LLMs Understand the Implication of Emphasized Sentences in Dialogue?","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2505.15667","title":"Segmentation-Variant Codebooks for Preservation of Paralinguistic and Prosodic Information","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2507.20091","title":"ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models","created":"2025-07-27","cited_by_count":4,"area":null},{"id":"2406.06251","title":"Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning","created":"2024-06-10","cited_by_count":1,"area":null},{"id":"2508.11224","title":"Benchmarking Prosody Encoding in Discrete Speech Tokens","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2604.10580","title":"Knowing What to Stress: A Discourse-Conditioned Text-to-Speech Benchmark","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2606.25529","title":"STEB: A Speech-to-Speech Translation Expressiveness Benchmark for Evaluating Beyond Translation Fidelity","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2508.11566","title":"Emphasis Sensitivity in Speech Representations","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2510.08606","title":"Centering Emotion Hotspots: Multimodal Local-Global Fusion and Cross-Modal Alignment for Emotion Recognition in Conversations","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2606.15266","title":"Evaluating and Preserving Lexical Stress in English-to-Chinese Speech-to-Speech Translation","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2606.24648","title":"ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.27717","title":"Do Speech Emphasis Models Generalize across Languages and Emotions?","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.02214","title":"Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.15910","title":"Iterative Self-Learning for Expressive Text-to-Speech Synthesis","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2610.07626","title":"A Novel Sentence Stress Detection Framework Leveraging Auxiliary Word-Stress Modeling and Loss Optimization","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}