{"total":20,"rows":[{"id":"2502.05236","title":"Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance","created":"2025-02-07","cited_by_count":27,"area":"alignment"},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2409.12403","title":"Preference Alignment Improves Language Model-Based TTS","created":"2024-09-19","cited_by_count":21,"area":"alignment"},{"id":"2406.00654","title":"Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback","created":"2024-06-02","cited_by_count":20,"area":"alignment"},{"id":"2407.02243","title":"Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization","created":"2024-07-02","cited_by_count":11,"area":"alignment"},{"id":"2506.21463","title":"Aligning Spoken Dialogue Models from User Interactions","created":"2025-06-26","cited_by_count":11,"area":"alignment"},{"id":"2508.17229","title":"Multi-Metric Preference Alignment for Generative Speech Restoration","created":"2025-08-24","cited_by_count":7,"area":"alignment"},{"id":"2601.19063","title":"Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback","created":"2026-01-27","cited_by_count":5,"area":"alignment"},{"id":"2603.00610","title":"CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction","created":"2026-02-28","cited_by_count":5,"area":"alignment"},{"id":"2509.18531","title":"No Verifiable Reward for Prosody: Toward Preference-Guided Prosody Learning in TTS","created":"2025-09-23","cited_by_count":4,"area":"alignment"},{"id":"2605.23975","title":"Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs","created":"2026-05-13","cited_by_count":2,"area":"alignment"},{"id":"2609.13150","title":"The Limits of Reference-Free Speech Quality Metrics as Evaluators and Rewards on Modern Text-to-Speech","created":"2026-07-02","cited_by_count":2,"area":"alignment"},{"id":"2508.05011","title":"Towards Hallucination-Free Music: A Reinforcement Learning Preference Optimization Framework for Reliable Song Generation","created":"2025-08-07","cited_by_count":1,"area":"alignment"},{"id":"2509.21718","title":"Align2Speak: Improving TTS for Low Resource Languages via ASR-Guided Online Preference Optimization","created":"2025-09-26","cited_by_count":1,"area":"alignment"},{"id":"2510.14628","title":"RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis","created":"2025-10-16","cited_by_count":1,"area":"alignment"},{"id":"2606.21458","title":"Post-Training Speech Enhancement Language Models with Perceptual Rewards","created":"2026-06-19","cited_by_count":1,"area":"alignment"},{"id":"2506.08998","title":"On Monotonicity in AI Alignment","created":"2025-06-10","cited_by_count":0,"area":"alignment"},{"id":"2510.05799","title":"Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech","created":"2025-10-07","cited_by_count":0,"area":"alignment"},{"id":"2603.07093","title":"Facial Expression Generation Aligned with Human Preference for Natural Dyadic Interaction","created":"2026-03-07","cited_by_count":0,"area":"alignment"},{"id":"2609.27599","title":"EmphTTS: an emphasis-control TTS with reinforcement learning","created":"2026-09-23","cited_by_count":0,"area":"alignment"}],"next_cursor":null}