{"total":51,"rows":[{"id":"2503.01710","title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","created":"2025-03-03","cited_by_count":113,"area":null},{"id":"2409.20007","title":"DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data","created":"2024-09-30","cited_by_count":45,"area":null},{"id":"2406.07867","title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","created":"2024-06-12","cited_by_count":41,"area":null},{"id":"2412.06602","title":"Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2312.11947","title":"Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling","created":"2023-12-19","cited_by_count":17,"area":null},{"id":"2407.21491","title":"Generative Expressive Conversational Speech Synthesis","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2404.06690","title":"CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations","created":"2024-04-10","cited_by_count":15,"area":null},{"id":"2407.02751","title":"Emotion and Intent Joint Understanding in Multimodal Conversation: A Benchmarking Dataset","created":"2024-07-03","cited_by_count":15,"area":null},{"id":"2402.05706","title":"Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2210.15360","title":"FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis","created":"2022-10-27","cited_by_count":9,"area":null},{"id":"2310.02973","title":"UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2312.10358","title":"CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis","created":"2023-12-16","cited_by_count":8,"area":null},{"id":"2505.19978","title":"DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2408.11849","title":"Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation","created":"2024-08-13","cited_by_count":7,"area":null},{"id":"2509.21144","title":"UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice","created":"2025-09-25","cited_by_count":7,"area":null},{"id":"2305.02269","title":"M2-CTTS: End-to-End Multi-scale Multi-modal Conversational Text-to-Speech Synthesis","created":"2023-05-03","cited_by_count":6,"area":null},{"id":"2406.08820","title":"DisfluencySpeech -- Single-Speaker Conversational Speech Dataset with Paralanguage","created":"2024-06-13","cited_by_count":6,"area":null},{"id":"2409.18680","title":"Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2410.09524","title":"Emphasis Rendering for Conversational Text-to-Speech with Multi-modal Multi-scale Context Modeling","created":"2024-10-12","cited_by_count":6,"area":null},{"id":"2504.14482","title":"DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party Dialogue","created":"2025-04-20","cited_by_count":6,"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":"2412.18733","title":"Intra- and Inter-modal Context Interaction Modeling for Conversational Speech Synthesis","created":"2024-12-25","cited_by_count":5,"area":null},{"id":"2509.22220","title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2603.09853","title":"SCENEBench: An Audio Understanding Benchmark Grounded in Assistive and Industrial Use Cases","created":"2026-03-10","cited_by_count":3,"area":null},{"id":"2604.17358","title":"Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions","created":"2026-04-19","cited_by_count":3,"area":null},{"id":"2303.08329","title":"Cross-speaker Emotion Transfer by Manipulating Speech Style Latents","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2309.11724","title":"Emotion-Aware Prosodic Phrasing for Expressive Text-to-Speech","created":"2023-09-21","cited_by_count":2,"area":null},{"id":"2407.15828","title":"J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2503.08798","title":"Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2509.06074","title":"Multimodal Fine-grained Context Interaction Graph Modeling for Conversational Speech Synthesis","created":"2025-09-07","cited_by_count":2,"area":null},{"id":"2512.14687","title":"Spoken DialogSum: An Emotion-Rich Conversational Dataset for Spoken Dialogue Summarization","created":"2025-12-16","cited_by_count":2,"area":null},{"id":"2607.27756","title":"Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2503.23848","title":"SpeechDialogueFactory: Generating High-Quality Speech Dialogue Data to Accelerate Your Speech-LLM Development","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2506.11344","title":"Do We Still Need Audio? Rethinking Speaker Diarization with a Text-Based Approach Using Multiple Prediction Models","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2512.20296","title":"TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2602.24080","title":"Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2604.16767","title":"When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2607.15755","title":"AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2305.12200","title":"ComedicSpeech: Text To Speech For Stand-up Comedies in Low-Resource Scenarios","created":"2023-05-20","cited_by_count":0,"area":null},{"id":"2408.06827","title":"PRESENT: Zero-Shot Text-to-Prosody Control","created":"2024-08-13","cited_by_count":0,"area":null},{"id":"2508.08095","title":"Dual Information Speech Language Models for Emotional Conversations","created":"2025-08-11","cited_by_count":0,"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":"2605.17860","title":"PAREDA: A Multi-Accent Speech Dataset of Natural Language Processing Research Discussions","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.24430","title":"Let Me Look at You: Advanced Facial Expression Modeling for Conversational Speech Synthesis","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.14029","title":"S2Dialog: Multimodal Dialogue Retrieval with Semantic and Acoustic-Style Modeling","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.16203","title":"INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.22908","title":"Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.28630","title":"Enabling Proactive Spoken Turns via a Generalized Style-Aware Full-Duplex Framework","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.21683","title":"Listen Before You Speak: Response Planning from Listener Facial Reactions for Conversational Speech Generation","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.28806","title":"A Harness for Synthesizing Diverse Naturalistic Full-Duplex Conversations","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.33296","title":"BaatCheet: A Multilingual Corpus for Dialogue Translation in Indian Languages","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}