{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"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":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"2006.04558","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","created":"2020-06-08","cited_by_count":717},{"id":"2106.06103","title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","created":"2021-06-11","cited_by_count":561},{"id":"2204.02152","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","created":"2022-04-05","cited_by_count":390},{"id":"1910.11480","title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","created":"2019-10-25","cited_by_count":340},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"1710.10467","title":"Generalized End-to-End Loss for Speaker Verification","created":"2017-10-28","cited_by_count":293},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"id":"2206.04658","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","created":"2022-06-09","cited_by_count":251},{"id":"2010.15258","title":"DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors","created":"2020-10-28","cited_by_count":241},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"2001.04643","title":"DDSP: Differentiable Digital Signal Processing","created":"2020-01-14","cited_by_count":178},{"id":"1804.03619","title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","created":"2018-04-10","cited_by_count":162},{"id":"2303.14307","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","created":"2023-03-25","cited_by_count":114},{"id":"2005.08209","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","created":"2020-05-17","cited_by_count":74},{"id":"2110.07603","title":"Sub-word Level Lip Reading With Visual Attention","created":"2021-10-14","cited_by_count":63},{"id":"1701.00495","title":"Vid2speech: Speech Reconstruction from Silent Video","created":"2017-01-02","cited_by_count":53},{"id":"2204.01726","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","created":"2022-04-04","cited_by_count":41},{"id":"2205.02058","title":"SVTS: Scalable Video-to-Speech Synthesis","created":"2022-05-04","cited_by_count":35},{"id":"2202.13066","title":"Revisiting Over-Smoothness in Text to Speech","created":"2022-02-26","cited_by_count":32},{"id":"2305.19603","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","created":"2023-05-31","cited_by_count":28},{"id":"2306.03258","title":"LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading","created":"2023-06-05","cited_by_count":22},{"id":"2308.07787","title":"DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding","created":"2023-08-15","cited_by_count":22},{"id":"2302.08841","title":"Lip-to-Speech Synthesis in the Wild with Multi-task Learning","created":"2023-02-17","cited_by_count":21},{"id":"2004.02541","title":"Vocoder-Based Speech Synthesis from Silent Videos","created":"2020-04-06","cited_by_count":20},{"id":"1907.01367","title":"Lipper: Synthesizing Thy Speech using Multi-View Lipreading","created":"2019-06-28","cited_by_count":19},{"id":"2011.04292","title":"STOI-Net: A Deep Learning based Non-Intrusive Speech Intelligibility Assessment Model","created":"2020-11-09","cited_by_count":19},{"id":"2011.07340","title":"Speech Prediction in Silent Videos using Variational Autoencoders","created":"2020-11-14","cited_by_count":18},{"id":"2204.01265","title":"Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video","created":"2022-04-04","cited_by_count":18},{"id":"2211.02903","title":"VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer","created":"2022-11-05","cited_by_count":14},{"id":"2105.13940","title":"Differentiable Artificial Reverberation","created":"2021-05-28","cited_by_count":11},{"id":"2112.04748","title":"LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading","created":"2021-12-09","cited_by_count":10},{"id":"2306.02044","title":"Why We Should Report the Details in Subjective Evaluation of TTS More Rigorously","created":"2023-06-03","cited_by_count":10},{"id":"2207.03800","title":"FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis","created":"2022-07-08","cited_by_count":8},{"id":"2209.00642","title":"Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild","created":"2022-09-01","cited_by_count":8},{"id":"2403.01087","title":"Towards Accurate Lip-to-Speech Synthesis in-the-Wild","created":"2024-03-02","cited_by_count":7},{"id":"2105.09652","title":"Speaker disentanglement in video-to-speech conversion","created":"2021-05-20","cited_by_count":6},{"id":"2202.09081","title":"VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion","created":"2022-02-18","cited_by_count":6},{"id":"2206.07458","title":"VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection","created":"2022-06-15","cited_by_count":6},{"id":"2206.02050","title":"Learning Speaker-specific Lip-to-Speech Generation","created":"2022-06-04","cited_by_count":3},{"id":"2306.15464","title":"Large-scale unsupervised audio pre-training for video-to-speech synthesis","created":"2023-06-27","cited_by_count":3},{"id":"2305.14359","title":"Zero-shot personalized lip-to-speech synthesis with face image based voice control","created":"2023-05-09","cited_by_count":2},{"id":"2303.00502","title":"On the Audio-visual Synchronization for Lip-to-Speech Synthesis","created":"2023-03-01","cited_by_count":1},{"id":"2309.07803","title":"SnakeGAN: A Universal Vocoder Leveraging DDSP Prior Knowledge and Periodic Inductive Bias","created":"2023-09-14","cited_by_count":1}],"next_cursor":null}