{"total":29,"rows":[{"id":"2412.00174","title":"SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters","created":"2024-11-29","cited_by_count":18,"area":null},{"id":"2407.12707","title":"TTSDS -- Text-to-Speech Distribution Score","created":"2024-07-17","cited_by_count":14,"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":"2404.18791","title":"Certification of Speaker Recognition Models to Additive Perturbations","created":"2024-04-29","cited_by_count":6,"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":"2409.06348","title":"VoiceWukong: Benchmarking Deepfake Voice Detection","created":"2024-09-10","cited_by_count":5,"area":null},{"id":"2407.00913","title":"SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2409.13049","title":"DiffSSD: A Diffusion-Based Dataset For Speech Forensics","created":"2024-09-19","cited_by_count":4,"area":null},{"id":"2512.10652","title":"TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2405.08720","title":"The Lost Melody: Empirical Observations on Text-to-Video Generation From A Storytelling Perspective","created":"2024-05-13","cited_by_count":3,"area":null},{"id":"2510.22622","title":"DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detection","created":"2025-10-26","cited_by_count":3,"area":null},{"id":"2507.02606","title":"De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks","created":"2025-07-03","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":"2407.13153","title":"Preset-Voice Matching for Privacy Regulated Speech-to-Speech Translation Systems","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2409.11308","title":"SpMis: An Investigation of Synthetic Spoken Misinformation Detection","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2411.05903","title":"Towards Multi-Modal Mastery: A 4.5B Parameter Truly Multi-Modal Small Language Model","created":"2024-11-08","cited_by_count":1,"area":null},{"id":"2506.02414","title":"StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion","created":"2025-06-03","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":"2601.13148","title":"ICo3D: An Interactive Conversational 3D Virtual Human","created":"2026-01-19","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":"2510.19414","title":"EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2604.23703","title":"Talking Slide Avatars: Open-Source Multimodal Communication Approach for Teaching","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2604.24770","title":"Elderly-Contextual Data Augmentation via Speech Synthesis for Elderly ASR","created":"2026-04-15","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":"2608.11752","title":"UniSwap: Streaming Audio-Visual Identity Swapping for Talking Videos","created":"2026-08-12","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":"2609.35411","title":"GLAD: Global-Local Adaptive Detector for Robust Speech Deepfake Detection","created":"2026-09-28","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},{"id":"2610.18669","title":"Known-Voice Cloning and the Limits of Personality Transfer for Character Design","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}