{"total":83,"rows":[{"id":"2507.15375","title":"STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models","created":"2025-07-21","cited_by_count":26,"area":"lr"},{"id":"2506.00885","title":"CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching","created":"2025-06-01","cited_by_count":11,"area":"diffusion"},{"id":"2506.02863","title":"CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2606.11167","title":"Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models","created":"2026-06-09","cited_by_count":10,"area":null},{"id":"2502.04519","title":"GenVC: Self-Supervised Zero-Shot Voice Conversion","created":"2025-02-06","cited_by_count":8,"area":null},{"id":"2506.19441","title":"TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems","created":"2025-06-24","cited_by_count":8,"area":null},{"id":"2605.23912","title":"Raon-Speech Technical Report","created":"2026-04-08","cited_by_count":7,"area":null},{"id":"2504.09839","title":"SafeSpeech: Robust and Universal Voice Protection Against Malicious Speech Synthesis","created":"2025-04-14","cited_by_count":6,"area":null},{"id":"2509.14946","title":"SynParaSpeech: Automated Synthesis of Paralinguistic Datasets for Speech Generation and Understanding","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2505.21724","title":"OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2605.15104","title":"From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents","created":"2026-05-14","cited_by_count":5,"area":"agents"},{"id":"2505.11200","title":"Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2602.13891","title":"GSRM: Generative Speech Reward Model for Speech RLHF","created":"2026-02-14","cited_by_count":4,"area":"alignment"},{"id":"2604.06138","title":"Generating Synthetic Doctor-Patient Conversations for Long-form Audio Summarization","created":"2026-04-07","cited_by_count":4,"area":null},{"id":"2501.13372","title":"Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement","created":"2025-01-23","cited_by_count":3,"area":null},{"id":"2606.25369","title":"Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis","created":"2026-06-24","cited_by_count":3,"area":"synth"},{"id":"2502.11094","title":"SyncSpeech: Efficient and Low-Latency Text-to-Speech based on Temporal Masked Transformer","created":"2025-02-16","cited_by_count":2,"area":null},{"id":"2503.23108","title":"SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System","created":"2025-03-29","cited_by_count":2,"area":null},{"id":"2504.20447","title":"APG-MOS: Auditory Perception Guided-MOS Predictor for Synthetic Speech","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2505.12226","title":"Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesis","created":"2025-05-18","cited_by_count":2,"area":"diffusion"},{"id":"2509.11084","title":"Length-Aware Rotary Position Embedding for Text-Speech Alignment","created":"2025-09-14","cited_by_count":2,"area":null},{"id":"2509.22727","title":"DiaMoE-TTS: A Unified IPA-Based Dialect TTS Framework with Mixture-of-Experts and Parameter-Efficient Zero-Shot Adaptation","created":"2025-09-25","cited_by_count":2,"area":"moe"},{"id":"2602.23266","title":"Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2603.05887","title":"Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec","created":"2026-03-06","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":"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":"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":"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":"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":"2505.04382","title":"Discrete Optimal Transport and Voice Conversion","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2505.19119","title":"CloneShield: A Framework for Universal Perturbation Against Zero-Shot Voice Cloning","created":"2025-05-25","cited_by_count":1,"area":null},{"id":"2508.09389","title":"ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2508.09767","title":"UtterTune: LoRA-Based Target-Language Pronunciation Edit and Control in Multilingual Text-to-Speech","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2509.17143","title":"MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances","created":"2025-09-21","cited_by_count":1,"area":null},{"id":"2510.05191","title":"Provable Speech Attributes Conversion via Latent Independence","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2601.18456","title":"Geneses: Unified Generative Speech Enhancement and Separation","created":"2026-01-26","cited_by_count":1,"area":"diffusion"},{"id":"2604.11552","title":"MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.17000","title":"Anonymization, Not Elimination: Utility-Preserved Speech Anonymization","created":"2026-04-18","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":"2606.09553","title":"OpenBibleTTS: Large-Scale Speech Resources and TTS Models for Low-Resource Languages","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2609.12872","title":"DuplexDrama: A Synthesized Dialogue Dataset with Scenarios, Full-Duplex Behaviors, Expressive Speech, and Sound Events","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2505.13771","title":"Score-Based Training for Energy-Based TTS Models","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2507.13563","title":"Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2509.14959","title":"Discrete optimal transport is a strong audio adversarial attack","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2509.18470","title":"Discrete-Time Diffusion-Like Models for Speech Synthesis","created":"2025-09-22","cited_by_count":0,"area":"diffusion"},{"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":"2509.24457","title":"Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditions","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2510.06201","title":"TokenChain: A Discrete Speech Chain via Semantic Token Modeling","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2512.04827","title":"Contract-Driven QoE Auditing for Speech and Singing Services: From MOS Regression to Service Graphs","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2601.08450","title":"Decoding Order Matters in Autoregressive Speech Synthesis","created":"2026-01-13","cited_by_count":0,"area":"diffusion"},{"id":"2601.16618","title":"PROST-LLM: Progressively Enhancing the Speech-to-Speech Translation Capability in LLMs","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2601.20185","title":"Improving X-Codec-2.0 for Multi-Lingual Speech: 25 Hz Latent Rate and 24 kHz Sampling","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.22417","title":"Absorbing Discrete Diffusion for Speech Enhancement","created":"2026-02-25","cited_by_count":0,"area":"diffusion"},{"id":"2603.09215","title":"SPAR-K: Scheduled Periodic Alternating Early Exit for Spoken Language Models","created":"2026-03-10","cited_by_count":0,"area":"inference"},{"id":"2603.10904","title":"When Fine-Tuning Fails and when it Generalises: Role of Data Diversity and Mixed Training in LLM-based TTS","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.14032","title":"Beyond Two-stage Diffusion TTS: Joint Structure and Content Refinement via Jump Diffusion","created":"2026-03-14","cited_by_count":0,"area":"diffusion"},{"id":"2603.25551","title":"Voxtral TTS","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2606.11681","title":"UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction","created":"2026-06-10","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":"2606.19951","title":"Investigating Human-Model Discrepancies in Speech Quality Assessment via Acoustic and Prosodic Perturbations","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.20137","title":"PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.31729","title":"Is Natural Always Appropriate? Investigating Naturalness and Appropriateness Across Different Domains for TTS Evaluation","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.03928","title":"TokAN: Accent Normalization Using Self-Supervised Speech Tokens","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.08256","title":"Best-of-$N$ TTS Evaluation is Confounded by ASR Family Alignment","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.09930","title":"Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.21176","title":"DAMOS: Learning Distortion-Aware Speech Quality Assessment through Explicit Distortion Localization","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.30325","title":"Sequential Trajectories and Simultaneous Blending: Multi-Emotion Modeling for Instruction-Following TTS","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.02623","title":"Scalable Direction-Following TTS via Voice Impression-Guided Pseudo Triplet Construction","created":"2026-09-02","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":"2609.13045","title":"Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning","created":"2026-09-11","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":"2609.22697","title":"COT-TTS: Audio Context-Aware Text-to-Speech with Chain-of-Thought Reasoning","created":"2026-09-19","cited_by_count":0,"area":"lr"},{"id":"2609.24651","title":"Corrective Forcing: Unified Post-Training for Diffusions and Flows in Generative Speech Enhancement","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.27086","title":"NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task","created":"2026-09-22","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":"2609.33443","title":"Context Spanning: A Communication Framework for Full-Duplex Speech Models and External LLM Backends","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33774","title":"Tokens Change, Structure Endures: Spectral Watermarking for Generated Speech","created":"2026-09-27","cited_by_count":0,"area":"safety"},{"id":"2609.34648","title":"SEmoEdit: Probing and Harnessing the Editability of Pre-trained Speech Flows","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2610.04488","title":"Can LLM Agents Automate Reinforcement Learning for Text-to-Speech?","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.06057","title":"A Comprehensive Objective Evaluation of Modern Text-to-Speech for Turkish Using Speech Quality Assessment Models","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.06817","title":"Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.17461","title":"Distilling Text LMs into Speech-to-Speech LMs by Matching Internal Text Predictions","created":"2026-10-12","cited_by_count":0,"area":"distill"},{"id":"2610.19388","title":"ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}