{"total":37,"rows":[{"id":"2601.15621","title":"Qwen3-TTS Technical Report","created":"2026-01-22","cited_by_count":118,"area":null},{"id":"2506.21619","title":"IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech","created":"2025-06-23","cited_by_count":90,"area":null},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83,"area":null},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61,"area":null},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2502.05512","title":"IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System","created":"2025-02-08","cited_by_count":28,"area":null},{"id":"2503.01879","title":"Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2412.08237","title":"TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch","created":"2024-12-11","cited_by_count":10,"area":null},{"id":"2603.08823","title":"Fish Audio S2 Technical Report","created":"2026-03-09","cited_by_count":9,"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":"2509.04667","title":"DarkStream: real-time speech anonymization with low latency","created":"2025-09-04","cited_by_count":7,"area":null},{"id":"2601.13948","title":"Stream-Voice-Anon: Enhancing Utility of Real-Time Speaker Anonymization via Neural Audio Codec and Language Models","created":"2026-01-20","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":"2601.03888","title":"IndexTTS 2.5 Technical Report","created":"2026-01-07","cited_by_count":6,"area":null},{"id":"2505.20506","title":"ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2505.15772","title":"MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2505.17426","title":"UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2508.16843","title":"A Survey of Threats Against Voice Authentication and Anti-Spoofing Systems","created":"2025-08-22","cited_by_count":2,"area":null},{"id":"2502.06560","title":"Position: It's Time to Act on the Risk of Efficient Personalized Text Generation","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2506.07646","title":"Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2509.07677","title":"Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems","created":"2025-09-09","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":"2609.08703","title":"TontaubeV1: Streaming Text-to-Speech with Hierarchical Codec Modeling and Bounded Context","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2504.03289","title":"RWKVTTS: Yet another TTS based on RWKV-7","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2509.09155","title":"HISPASpoof: A New Dataset For Spanish Speech Forensics","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2509.22808","title":"ArFake: A Robust Framework for Multi-Dialect Arabic Speech Spoofing Detection Benchmark","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.19414","title":"EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2510.26190","title":"SP-MCQA: Evaluating Intelligibility of TTS Beyond the Word Level","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2511.07099","title":"E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2603.04219","title":"ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.05800","title":"StreamWise: Serving Multi-Modal Generation in Real-Time at Scale","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.16924","title":"SimulU: Training-free Policy for Long-form Simultaneous Speech-to-Speech Translation","created":"2026-03-11","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":"2605.31173","title":"MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.04553","title":"Lights, Camera, Carbon: Architectural Scaling Laws for Video Generation Energy Consumption","created":"2026-07-05","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},{"id":"2610.18247","title":"PACT: A Pragmatic Prompting Framework for Expressive and Voice-Preserving Speech-to-Speech Translation","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}