{"list":"other","total":70,"rows":[{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260},{"id":"2108.05080","title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","created":"2021-08-11","cited_by_count":181},{"id":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181},{"id":"2109.00537","title":"ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection","created":"2021-09-01","cited_by_count":161},{"id":"2203.16263","title":"Does Audio Deepfake Detection Generalize?","created":"2022-03-30","cited_by_count":135},{"id":"2212.07525","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","created":"2022-12-14","cited_by_count":110},{"id":"2408.08739","title":"ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale","created":"2024-08-16","cited_by_count":91},{"id":"2111.04433","title":"RawBoost: A Raw Data Boosting and Augmentation Method applied to Automatic Speaker Verification Anti-Spoofing","created":"2021-11-08","cited_by_count":67},{"id":"1711.00354","title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis","created":"2017-10-28","cited_by_count":58},{"id":"2102.05889","title":"ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech","created":"2021-02-11","cited_by_count":58},{"id":"2401.09512","title":"MLAAD: The Multi-Language Audio Anti-Spoofing Dataset","created":"2024-01-17","cited_by_count":56},{"id":"2310.16338","title":"Generative Pre-training for Speech with Flow Matching","created":"2023-10-25","cited_by_count":55},{"id":"2402.11337","title":"Learning by Reconstruction Produces Uninformative Features For Perception","created":"2024-02-17","cited_by_count":55},{"id":"1903.11269","title":"CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages","created":"2019-03-27","cited_by_count":54},{"id":"2204.05177","title":"The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterance","created":"2022-04-11","cited_by_count":47},{"id":"2503.02857","title":"Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024","created":"2025-03-04","cited_by_count":45},{"id":"2104.03617","title":"Half-Truth: A Partially Fake Audio Detection Dataset","created":"2021-04-08","cited_by_count":44},{"id":"2304.13085","title":"AI-Synthesized Voice Detection Using Neural Vocoder Artifacts","created":"2023-04-25","cited_by_count":41},{"id":"2506.10274","title":"Discrete Audio Tokens: More Than a Survey!","created":"2025-06-12","cited_by_count":38},{"id":"2106.12914","title":"Speech is Silver, Silence is Golden: What do ASVspoof-trained Models Really Learn?","created":"2021-06-23","cited_by_count":37},{"id":"2405.04880","title":"The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio","created":"2024-05-08","cited_by_count":31},{"id":"2404.13914","title":"A Survey on Speech Deepfake Detection","created":"2024-04-22","cited_by_count":27},{"id":"2409.17285","title":"SpoofCeleb: Speech Deepfake Detection and SASV In The Wild","created":"2024-09-18","cited_by_count":22},{"id":"2309.07525","title":"SingFake: Singing Voice Deepfake Detection","created":"2023-09-14","cited_by_count":21},{"id":"2409.09272","title":"SafeEar: Content Privacy-Preserving Audio Deepfake Detection","created":"2024-09-14","cited_by_count":21},{"id":"2409.08731","title":"DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset","created":"2024-09-13","cited_by_count":20},{"id":"2309.06014","title":"Can large-scale vocoded spoofed data improve speech spoofing countermeasure with a self-supervised front end?","created":"2023-09-12","cited_by_count":17},{"id":"2209.08000","title":"TIMIT-TTS: a Text-to-Speech Dataset for Multimodal Synthetic Media Detection","created":"2022-09-16","cited_by_count":16},{"id":"2405.08838","title":"PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Dataset","created":"2024-05-14","cited_by_count":16},{"id":"2406.07237","title":"CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems","created":"2024-06-11","cited_by_count":16},{"id":"2407.08016","title":"Source Tracing of Audio Deepfake Systems","created":"2024-07-10","cited_by_count":15},{"id":"2207.12308","title":"CFAD: A Chinese Dataset for Fake Audio Detection","created":"2022-07-12","cited_by_count":14},{"id":"2409.14743","title":"LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation","created":"2024-09-23","cited_by_count":14},{"id":"2506.21090","title":"Post-training for Deepfake Speech Detection","created":"2025-06-26","cited_by_count":11},{"id":"2502.20067","title":"UniCodec: Unified Audio Codec with Single Domain-Adaptive Codebook","created":"2025-02-27","cited_by_count":10},{"id":"2510.25955","title":"SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations","created":"2025-10-29","cited_by_count":10},{"id":"2309.07707","title":"CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders","created":"2023-09-14","cited_by_count":9},{"id":"2408.16132","title":"SVDD 2024: The Inaugural Singing Voice Deepfake Detection Challenge","created":"2024-08-28","cited_by_count":8},{"id":"2410.06796","title":"Diffuse or Confuse: A Diffusion Deepfake Speech Dataset","created":"2024-10-09","cited_by_count":8},{"id":"1904.03365","title":"ReMASC: Realistic Replay Attack Corpus for Voice Controlled Systems","created":"2019-04-06","cited_by_count":7},{"id":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7},{"id":"2508.04143","title":"Multilingual Source Tracing of Speech Deepfakes: A First Benchmark","created":"2025-08-06","cited_by_count":7},{"id":"2409.08711","title":"Text-To-Speech Synthesis In The Wild","created":"2024-09-13","cited_by_count":6},{"id":"2505.14862","title":"Replay Attacks Against Audio Deepfake Detection","created":"2025-05-20","cited_by_count":6},{"id":"2302.09437","title":"RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness","created":"2023-02-18","cited_by_count":5},{"id":"2501.06514","title":"Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set Condition","created":"2025-01-11","cited_by_count":5},{"id":"2503.00733","title":"UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation","created":"2025-03-02","cited_by_count":5},{"id":"2506.14396","title":"Manipulated Regions Localization For Partially Deepfake Audio: A Survey","created":"2025-06-17","cited_by_count":5},{"id":"2407.14006","title":"MSceneSpeech: A Multi-Scene Speech Dataset For Expressive Speech Synthesis","created":"2024-07-19","cited_by_count":4},{"id":"2409.13049","title":"DiffSSD: A Diffusion-Based Dataset For Speech Forensics","created":"2024-09-19","cited_by_count":4},{"id":"2412.11538","title":"MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond","created":"2024-12-16","cited_by_count":4},{"id":"2505.23962","title":"Can Emotion Fool Anti-spoofing?","created":"2025-05-29","cited_by_count":4},{"id":"2509.04161","title":"Wav2DF-TSL: Two-stage Learning with Efficient Pre-training and Hierarchical Experts Fusion for Robust Audio Deepfake Detection","created":"2025-09-04","cited_by_count":4},{"id":"2010.01793","title":"JSSS: free Japanese speech corpus for summarization and simplification","created":"2020-10-05","cited_by_count":3},{"id":"2403.08654","title":"An Efficient End-to-End Approach to Noise Invariant Speech Features via Multi-Task Learning","created":"2024-03-13","cited_by_count":2},{"id":"2406.07254","title":"SRC4VC: Smartphone-Recorded Corpus for Voice Conversion Benchmark","created":"2024-06-11","cited_by_count":2},{"id":"2408.10853","title":"Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio?","created":"2024-08-20","cited_by_count":2},{"id":"2509.21597","title":"AUDDT: A Unified Benchmark Toolkit for Audio and Speech Deepfake Detectors","created":"2025-09-25","cited_by_count":2},{"id":"2404.17721","title":"An RFP dataset for Real, Fake, and Partially fake audio detection","created":"2024-04-26","cited_by_count":1},{"id":"2502.05674","title":"ShiftySpeech: A Large-Scale Synthetic Speech Dataset with Distribution Shifts","created":"2025-02-08","cited_by_count":1},{"id":"2506.19014","title":"IndieFake Dataset: A Benchmark Dataset for Audio Deepfake Detection","created":"2025-06-23","cited_by_count":1}],"next_cursor":null}