{"total":282,"rows":[{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752,"area":null},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379,"area":null},{"id":"2101.05278","title":"GAN Inversion: A Survey","created":"2021-01-14","cited_by_count":367,"area":null},{"id":"2112.02418","title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone","created":"2021-12-04","cited_by_count":278,"area":null},{"id":"2206.04658","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","created":"2022-06-09","cited_by_count":251,"area":null},{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"area":null},{"id":"2108.05080","title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","created":"2021-08-11","cited_by_count":181,"area":null},{"id":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179,"area":null},{"id":"2109.13821","title":"Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme","created":"2021-09-28","cited_by_count":100,"area":"diffusion"},{"id":"2103.00993","title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","created":"2021-03-01","cited_by_count":98,"area":null},{"id":"2106.03153","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","created":"2021-06-06","cited_by_count":93,"area":null},{"id":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85,"area":null},{"id":"2111.11755","title":"Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance","created":"2021-11-23","cited_by_count":84,"area":"diffusion"},{"id":"2103.00484","title":"Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward","created":"2021-02-25","cited_by_count":82,"area":null},{"id":"2110.14513","title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","created":"2021-10-27","cited_by_count":81,"area":null},{"id":"2311.15308","title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","created":"2023-11-26","cited_by_count":80,"area":null},{"id":"2402.00045","title":"Detecting Multimedia Generated by Large AI Models: A Survey","created":"2024-01-22","cited_by_count":76,"area":"diffusion"},{"id":"2107.08661","title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","created":"2021-07-19","cited_by_count":71,"area":null},{"id":"2201.03713","title":"CVSS Corpus and Massively Multilingual Speech-to-Speech Translation","created":"2022-01-11","cited_by_count":71,"area":null},{"id":"2308.06873","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","created":"2023-08-14","cited_by_count":64,"area":null},{"id":"2406.02951","title":"AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection","created":"2024-06-05","cited_by_count":59,"area":null},{"id":"2310.16338","title":"Generative Pre-training for Speech with Flow Matching","created":"2023-10-25","cited_by_count":55,"area":"diffusion"},{"id":"2103.15060","title":"PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS","created":"2021-03-28","cited_by_count":52,"area":null},{"id":"2306.03509","title":"Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias","created":"2023-06-06","cited_by_count":51,"area":null},{"id":"2204.03083","title":"Audio-Visual Person-of-Interest DeepFake Detection","created":"2022-04-06","cited_by_count":43,"area":null},{"id":"2305.01979","title":"Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization","created":"2023-05-03","cited_by_count":43,"area":null},{"id":"2204.01726","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","created":"2022-04-04","cited_by_count":41,"area":null},{"id":"2406.07867","title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","created":"2024-06-12","cited_by_count":41,"area":null},{"id":"2502.18924","title":"MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis","created":"2025-02-26","cited_by_count":41,"area":"diffusion"},{"id":"2203.09690","title":"A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing","created":"2022-03-18","cited_by_count":40,"area":null},{"id":"2110.08243","title":"Neural Dubber: Dubbing for Videos According to Scripts","created":"2021-10-15","cited_by_count":39,"area":null},{"id":"2106.15764","title":"The Threat of Offensive AI to Organizations","created":"2021-06-30","cited_by_count":38,"area":null},{"id":"2103.04088","title":"Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech","created":"2021-03-06","cited_by_count":37,"area":null},{"id":"2205.02058","title":"SVTS: Scalable Video-to-Speech Synthesis","created":"2022-05-04","cited_by_count":35,"area":null},{"id":"2205.15370","title":"Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Data","created":"2022-05-30","cited_by_count":35,"area":"diffusion"},{"id":"2311.12454","title":"HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis","created":"2023-11-21","cited_by_count":35,"area":null},{"id":"2211.09383","title":"Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":34,"area":"diffusion"},{"id":"2406.05551","title":"Autoregressive Diffusion Transformer for Text-to-Speech Synthesis","created":"2024-06-08","cited_by_count":34,"area":"diffusion"},{"id":"2109.02993","title":"Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors","created":"2021-09-07","cited_by_count":32,"area":null},{"id":"2110.04621","title":"Universal Paralinguistic Speech Representations Using Self-Supervised Conformers","created":"2021-10-09","cited_by_count":32,"area":null},{"id":"2212.04054","title":"Learning to Dub Movies via Hierarchical Prosody Models","created":"2022-12-08","cited_by_count":29,"area":null},{"id":"2304.14535","title":"Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization","created":"2023-04-27","cited_by_count":28,"area":null},{"id":"2103.11401","title":"SwissDial: Parallel Multidialectal Corpus of Spoken Swiss German","created":"2021-03-21","cited_by_count":26,"area":null},{"id":"2307.16430","title":"VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design","created":"2023-07-31","cited_by_count":25,"area":null},{"id":"2108.12226","title":"Injecting Text in Self-Supervised Speech Pretraining","created":"2021-08-27","cited_by_count":24,"area":null},{"id":"2109.06912","title":"fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit","created":"2021-09-14","cited_by_count":24,"area":null},{"id":"2110.11479","title":"Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition","created":"2021-10-21","cited_by_count":24,"area":null},{"id":"2111.12890","title":"V2C: Visual Voice Cloning","created":"2021-11-25","cited_by_count":24,"area":null},{"id":"2110.06280","title":"S3PRL-VC: Open-source Voice Conversion Framework with Self-supervised Speech Representations","created":"2021-10-12","cited_by_count":23,"area":null},{"id":"2312.10579","title":"DER-GCN: Dialogue and Event Relation-Aware Graph Convolutional Neural Network for Multimodal Dialogue Emotion Recognition","created":"2023-12-17","cited_by_count":23,"area":null},{"id":"2412.00175","title":"Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning","created":"2024-11-29","cited_by_count":23,"area":null},{"id":"2110.07840","title":"ESPnet2-TTS: Extending the Edge of TTS Research","created":"2021-10-15","cited_by_count":22,"area":null},{"id":"2111.04040","title":"Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech","created":"2021-11-07","cited_by_count":22,"area":null},{"id":"2303.01664","title":"Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations","created":"2023-03-03","cited_by_count":22,"area":null},{"id":"2205.07211","title":"GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech","created":"2022-05-15","cited_by_count":21,"area":null},{"id":"2205.10839","title":"Deep Learning for Visual Speech Analysis: A Survey","created":"2022-05-22","cited_by_count":21,"area":null},{"id":"2312.10741","title":"StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis","created":"2023-12-17","cited_by_count":21,"area":null},{"id":"2405.10272","title":"Faces that Speak: Jointly Synthesising Talking Face and Speech from Text","created":"2024-05-16","cited_by_count":21,"area":null},{"id":"2306.02982","title":"PolyVoice: Language Models for Speech to Speech Translation","created":"2023-06-05","cited_by_count":19,"area":null},{"id":"2406.04673","title":"MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models","created":"2024-06-07","cited_by_count":19,"area":"diffusion"},{"id":"2411.02625","title":"EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector","created":"2024-11-04","cited_by_count":19,"area":null},{"id":"2103.09474","title":"STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech","created":"2021-03-17","cited_by_count":18,"area":null},{"id":"2106.15153","title":"GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis","created":"2021-06-29","cited_by_count":18,"area":null},{"id":"2208.01366","title":"Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess","created":"2022-08-02","cited_by_count":18,"area":null},{"id":"2104.09715","title":"AdaSpeech 2: Adaptive Text to Speech with Untranscribed Data","created":"2021-04-20","cited_by_count":17,"area":null},{"id":"2108.04325","title":"AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person","created":"2021-08-09","cited_by_count":17,"area":null},{"id":"2311.01458","title":"Detecting Deepfakes Without Seeing Any","created":"2023-11-02","cited_by_count":17,"area":null},{"id":"2105.03070","title":"SpeechNet: A Universal Modularized Model for Speech Processing Tasks","created":"2021-05-07","cited_by_count":16,"area":null},{"id":"2202.09950","title":"CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing","created":"2022-02-21","cited_by_count":16,"area":null},{"id":"2210.12223","title":"Low-Resource Multilingual and Zero-Shot Multispeaker TTS","created":"2022-10-21","cited_by_count":15,"area":null},{"id":"2401.10113","title":"Exposing Lip-syncing Deepfakes from Mouth Inconsistencies","created":"2024-01-18","cited_by_count":15,"area":null},{"id":"2106.12896","title":"Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech","created":"2021-06-24","cited_by_count":14,"area":null},{"id":"2111.05095","title":"Speaker Generation","created":"2021-11-07","cited_by_count":14,"area":null},{"id":"2312.02512","title":"AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2102.08328","title":"Context-Aware Prosody Correction for Text-Based Speech Editing","created":"2021-02-16","cited_by_count":13,"area":null},{"id":"2204.03594","title":"Heterogeneous Target Speech Separation","created":"2022-04-07","cited_by_count":13,"area":null},{"id":"2206.12229","title":"Exact Prosody Cloning in Zero-Shot Multispeaker Text-to-Speech","created":"2022-06-24","cited_by_count":13,"area":null},{"id":"2109.09598","title":"\"Hello, It's Me\": Deep Learning-based Speech Synthesis Attacks in the Real World","created":"2021-09-20","cited_by_count":12,"area":null},{"id":"2110.05798","title":"Adapting TTS models For New Speakers using Transfer Learning","created":"2021-10-12","cited_by_count":12,"area":null},{"id":"2111.04730","title":"Emotional Prosody Control for Speech Generation","created":"2021-11-07","cited_by_count":12,"area":null},{"id":"2111.10139","title":"More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech","created":"2021-11-19","cited_by_count":12,"area":null},{"id":"2204.02524","title":"Simple and Effective Unsupervised Speech Synthesis","created":"2022-04-06","cited_by_count":12,"area":null},{"id":"2312.16778","title":"Adversarial Representation with Intra-Modal and Inter-Modal Graph Contrastive Learning for Multimodal Emotion Recognition","created":"2023-12-28","cited_by_count":12,"area":null},{"id":"2102.00151","title":"Expressive Neural Voice Cloning","created":"2021-01-30","cited_by_count":11,"area":null},{"id":"2104.00931","title":"Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques","created":"2021-04-02","cited_by_count":11,"area":null},{"id":"2104.01604","title":"Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers","created":"2021-04-04","cited_by_count":11,"area":null},{"id":"2110.02891","title":"Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models","created":"2021-10-06","cited_by_count":11,"area":null},{"id":"2209.14098","title":"Deepfake audio detection by speaker verification","created":"2022-09-28","cited_by_count":11,"area":null},{"id":"2308.01831","title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","created":"2023-08-03","cited_by_count":11,"area":null},{"id":"2402.07383","title":"Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like","created":"2024-02-12","cited_by_count":11,"area":null},{"id":"2204.00618","title":"ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion","created":"2022-03-29","cited_by_count":10,"area":null},{"id":"2204.01672","title":"Residual-guided Personalized Speech Synthesis based on Face Image","created":"2022-04-01","cited_by_count":10,"area":null},{"id":"2210.15868","title":"Residual Adapters for Few-Shot Text-to-Speech Speaker Adaptation","created":"2022-10-28","cited_by_count":10,"area":null},{"id":"2206.13979","title":"Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection","created":"2022-06-27","cited_by_count":9,"area":null},{"id":"2210.06105","title":"SpecRNet: Towards Faster and More Accessible Audio DeepFake Detection","created":"2022-10-12","cited_by_count":9,"area":null},{"id":"2305.14097","title":"QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systems","created":"2023-05-23","cited_by_count":9,"area":null},{"id":"2406.06406","title":"Controlling Emotion in Text-to-Speech with Natural Language Prompts","created":"2024-06-10","cited_by_count":9,"area":null},{"id":"2409.09098","title":"AccentBox: Towards High-Fidelity Zero-Shot Accent Generation","created":"2024-09-13","cited_by_count":9,"area":null},{"id":"2202.08164","title":"Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module","created":"2022-02-16","cited_by_count":8,"area":null},{"id":"2204.10020","title":"Cross-Speaker Emotion Transfer for Low-Resource Text-to-Speech Using Non-Parallel Voice Conversion with Pitch-Shift Data Augmentation","created":"2022-04-21","cited_by_count":8,"area":null}],"next_cursor":"100"}