{"total":16,"rows":[{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2505.15670","title":"SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model","created":"2025-05-21","cited_by_count":34,"area":null},{"id":"2508.05835","title":"NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference","created":"2025-08-07","cited_by_count":15,"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":"2507.02176","title":"Analyzing and Improving Speaker Similarity Assessment for Speech Synthesis","created":"2025-07-02","cited_by_count":3,"area":null},{"id":"2603.13518","title":"VoXtream2: Full-stream TTS with dynamic speaking rate control","created":"2026-03-13","cited_by_count":3,"area":null},{"id":"2608.23791","title":"EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesis","created":"2026-08-24","cited_by_count":3,"area":null},{"id":"2606.18485","title":"MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2608.28970","title":"Diagnose, Then Refine: A Closed-Loop TTS System with AudioLLM-Guided Correction","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2509.19592","title":"Frame-Stacked Local Transformers For Efficient Multi-Codebook Speech Generation","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2510.13293","title":"Cross-modal Consistency Guidance for Robust Emotion Control in Auto-Regressive TTS Models","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2511.14779","title":"The Impact of Prosodic Segmentation on Speech Synthesis of Spontaneous Speech","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2606.18323","title":"Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecs","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2609.25411","title":"Learnable Classifier-Free Guidance Null Embeddings for Enhanced Controllable Speech Synthesis","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.30416","title":"All In Good Time: Causality-Aware Framework for LLM-Based Simultaneous Speech-to-Speech Translation","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.38182","title":"EmAvatar: Multimodal Empathetic Response Generation via Conflict Resolution and Expressive Guidance","created":"2026-08-04","cited_by_count":0,"area":null}],"next_cursor":null}