{"total":17,"rows":[{"id":"2505.23009","title":"EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge","created":"2025-05-29","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":"2506.05984","title":"Audio-Aware Large Language Models as Judges for Speaking Styles","created":"2025-06-06","cited_by_count":17,"area":null},{"id":"2601.14728","title":"AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering","created":"2026-01-21","cited_by_count":8,"area":null},{"id":"2603.22677","title":"MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation","created":"2026-03-24","cited_by_count":6,"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":"2605.04505","title":"JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions","created":"2026-05-06","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":"2606.25990","title":"SpeechEQ: Benchmarking Emotional Intelligence Quotient in Socially Aware Voice Conversational Models","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.07985","title":"A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2601.04029","title":"SpeakerSleuth: Can Large Audio-Language Models Judge Speaker Consistency across Multi-turn Dialogues?","created":"2026-01-07","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":"2604.13804","title":"Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2606.13507","title":"Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.18645","title":"Augmenting Dysarthric Speech Severity Assessment with MOS Supervision","created":"2026-06-17","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":"2609.30483","title":"AcoustiClaim: A Numeric Claim Benchmark with Instrument Ground Truth","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}