{"total":74,"rows":[{"id":"2603.18090","title":"MOSS-TTS Technical Report","created":"2026-03-18","cited_by_count":14,"area":null},{"id":"2605.23912","title":"Raon-Speech Technical Report","created":"2026-04-08","cited_by_count":7,"area":null},{"id":"2602.07803","title":"SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis","created":"2026-02-08","cited_by_count":3,"area":null},{"id":"2603.28086","title":"MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2604.10065","title":"ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models","created":"2026-04-11","cited_by_count":3,"area":null},{"id":"2609.08977","title":"Multimodal Duplex Interaction Agent","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2602.07106","title":"Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2603.09714","title":"MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2603.10035","title":"TriageSim: A Conversational Emergency Triage Simulation Framework from Structured Electronic Health Records","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2604.22225","title":"TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2605.17488","title":"Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2606.03168","title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","created":"2026-06-02","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":"2608.19515","title":"Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2608.24168","title":"FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2609.23407","title":"OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents","created":"2026-09-20","cited_by_count":2,"area":null},{"id":"2603.06444","title":"Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2604.10580","title":"Knowing What to Stress: A Discourse-Conditioned Text-to-Speech Benchmark","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2604.22436","title":"AgentSearchBench: A Benchmark for AI Agent Search in the Wild","created":"2026-04-24","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":"2605.06765","title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.00851","title":"Sympatheia: Emotionally Adaptive Voice Assistant with Continuous Affect Conditioning","created":"2026-05-30","cited_by_count":1,"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":"2606.21343","title":"An Evaluation Framework for Text-to-Speech Voice Reconstruction","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2606.22811","title":"Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis","created":"2026-06-22","cited_by_count":1,"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":"2606.29031","title":"How to Leverage Synthetic Speech for LLM-Based ASR Systems?","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2607.06461","title":"WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2609.08147","title":"ConversationalVoice: Full-Duplex Speech Data from Real Conversations through Source-Faithful Reconstruction and Conversation-Grounded Expansion","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.08936","title":"AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.16582","title":"CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2603.25727","title":"Back to Basics: Revisiting ASR in the Age of Voice Agents","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.24794","title":"V.O.I.C.E (Voice, Ownership, Identity, Control, Expression): Risk Taxonomy of Synthetic Voice Generation From Empirical Data","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.27258","title":"PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.28063","title":"Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.31173","title":"MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.04418","title":"CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.16969","title":"Probing Low Frame Rate Degradation in Neural Audio Codecs","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.17339","title":"SpeechDx: A Multi-Task Benchmark for Clinical Speech AI","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.20650","title":"EmoInstruct-TTS: Dual-Path Instruction-Guided Emotional Speech Synthesis","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.21365","title":"LambdaMark: Semantic Audio Watermarking for Robustness and Radioactivity","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.29473","title":"MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2606.31128","title":"UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.02633","title":"GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.02763","title":"LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answering","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.03418","title":"DETECT-3B-Omni is Agnostic of Content and Demographics","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.11706","title":"VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.05663","title":"Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.11650","title":"Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.12814","title":"FastThaiG2P: Lightning-fast Thai Grapheme-to-phoneme Conversion for Voice Agent Pipelines","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.19936","title":"Towards Quantifying Benchmark Optimization in ASR Models","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.20387","title":"Poly-InstructTTS: Learning In-the-Wild Expressive Speech Synthesis from Open-Ended Instructions","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.04250","title":"Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.09677","title":"X2-NativeCursor: Native-Token Text Progress Tracking for Incremental-Text Streaming Codec TTS","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.16614","title":"RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.19805","title":"Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.20124","title":"Multi-Dimensional Prosody Judgment For Live Streaming Speech Synthesis","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.20995","title":"Voice-Light: A Full-Duplex Cascaded Voice Agent with Causal Turn-Taking and Speculative Generation","created":"2026-09-17","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":"2609.28806","title":"A Harness for Synthesizing Diverse Naturalistic Full-Duplex Conversations","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.32050","title":"Tracing Decoder Artifacts for Compact Synthetic Speech Screening","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33311","title":"SocialHumanoid: Towards Expressive Humanoid Behavior via One-Step Co-Speech Motion Generation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35922","title":"Almost Human, Except When It Matters: VoxParity and the Decisions a Voice Should Change","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36624","title":"DualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.36974","title":"Repetition, Not Length: Isolating the Counting Failure in Neural Text-to-Speech","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37586","title":"Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39088","title":"SCIC: Scope- and Codebook-Aware Instruction Conditioning for Speaker-Adapted Expressive TTS","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.07506","title":"Jarvis: A Proactive Speech Agent for Multi-Party Conversations","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.07533","title":"SkillFormer: Skill-Decomposed Adaptation for Audio Language Models","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.10868","title":"Conversational Voice Aesthetic Model with Reinforcement Learning from Human Listeners","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.14299","title":"RUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Can","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14694","title":"VoTSpeech: Decoupling Voice Design from Speech Generation in Instruction-Following TTS","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.14776","title":"Training a Compact, Strong, and Realistic Text-to-Speech Model","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}