{"total":22,"rows":[{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2502.15602","title":"KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generation","created":"2025-02-21","cited_by_count":24,"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":"2506.17611","title":"OpusLM: A Family of Open Unified Speech Language Models","created":"2025-06-21","cited_by_count":9,"area":null},{"id":"2506.19441","title":"TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems","created":"2025-06-24","cited_by_count":8,"area":null},{"id":"2502.12489","title":"A Comprehensive Survey on Generative AI for Video-to-Music Generation","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2602.05220","title":"Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2505.15772","title":"MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2506.18714","title":"Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancement","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2601.12205","title":"Do Neural Codecs Generalize? A Controlled Study Across Unseen Languages and Non-Speech Tasks","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2604.26347","title":"The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2509.08031","title":"AU-Harness: An Open-Source Toolkit for Holistic Evaluation of Audio LLMs","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2509.24457","title":"Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditions","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2602.06180","title":"STACodec: Semantic Token Assignment for Balancing Acoustic Fidelity and Semantic Information in Audio Codecs","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.13952","title":"LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2606.06740","title":"Multilingual Multi-Speaker Unit Vocoders: A Systematic Analysis of Discrete Speech Representations","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.19951","title":"Investigating Human-Model Discrepancies in Speech Quality Assessment via Acoustic and Prosodic Perturbations","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.20137","title":"PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2609.17509","title":"LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.23951","title":"HaikuS2S: A Cascaded System For Responding In Verse","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.26306","title":"CHiME-9 ECHI: A Machine Learning Challenge for Enhancing Conversations to Address Hearing Impairment","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.29448","title":"YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}