{"list":"other","total":60,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"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":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"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":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"1703.07332","title":"How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)","created":"2017-03-21","cited_by_count":525},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"2204.02152","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","created":"2022-04-05","cited_by_count":390},{"id":"2407.05407","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","created":"2024-07-07","cited_by_count":334},{"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":"2208.05830","title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","created":"2022-08-11","cited_by_count":197},{"id":"2211.03929","title":"Comparative layer-wise analysis of self-supervised speech models","created":"2022-11-08","cited_by_count":158},{"id":"2306.00814","title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","created":"2023-06-01","cited_by_count":153},{"id":"2309.03199","title":"Matcha-TTS: A fast TTS architecture with conditional flow matching","created":"2023-09-06","cited_by_count":145},{"id":"1904.08352","title":"MOSNet: Deep Learning based Objective Assessment for Voice Conversion","created":"2019-04-17","cited_by_count":127},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"id":"2012.06185","title":"Exploring wav2vec 2.0 on speaker verification and language identification","created":"2020-12-11","cited_by_count":95},{"id":"1810.07217","title":"Hierarchical Generative Modeling for Controllable Speech Synthesis","created":"2018-10-16","cited_by_count":93},{"id":"2110.14513","title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","created":"2021-10-27","cited_by_count":81},{"id":"2203.06849","title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","created":"2022-03-14","cited_by_count":77},{"id":"2005.08209","title":"Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis","created":"2020-05-17","cited_by_count":74},{"id":"1804.00326","title":"Seeing Voices and Hearing Faces: Cross-modal biometric matching","created":"2018-04-01","cited_by_count":60},{"id":"2310.16338","title":"Generative Pre-training for Speech with Flow Matching","created":"2023-10-25","cited_by_count":55},{"id":"2011.00406","title":"Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies","created":"2020-11-01","cited_by_count":47},{"id":"2312.07360","title":"Boosting Latent Diffusion with Flow Matching","created":"2023-12-12","cited_by_count":44},{"id":"2204.01726","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","created":"2022-04-04","cited_by_count":41},{"id":"2207.07036","title":"u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality","created":"2022-07-14","cited_by_count":39},{"id":"2203.07960","title":"Investigating self-supervised learning for speech enhancement and separation","created":"2022-03-15","cited_by_count":35},{"id":"2205.02058","title":"SVTS: Scalable Video-to-Speech Synthesis","created":"2022-05-04","cited_by_count":35},{"id":"2211.09383","title":"Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":34},{"id":"2312.10825","title":"Latent Space Editing in Transformer-Based Flow Matching","created":"2023-12-17","cited_by_count":32},{"id":"2212.04054","title":"Learning to Dub Movies via Hierarchical Prosody Models","created":"2022-12-08","cited_by_count":29},{"id":"2305.19603","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","created":"2023-05-31","cited_by_count":28},{"id":"2104.13332","title":"End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks","created":"2021-04-27","cited_by_count":27},{"id":"2202.07816","title":"ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech","created":"2022-02-16","cited_by_count":22},{"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":"2212.04559","title":"SpeechLMScore: Evaluating speech generation using speech language model","created":"2022-12-08","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":"2011.07340","title":"Speech Prediction in Silent Videos using Variational Autoencoders","created":"2020-11-14","cited_by_count":18},{"id":"2310.19636","title":"Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition","created":"2023-10-30","cited_by_count":17},{"id":"2410.20478","title":"MusicFlow: Cascaded Flow Matching for Text Guided Music Generation","created":"2024-10-27","cited_by_count":15},{"id":"2308.15256","title":"Let There Be Sound: Reconstructing High Quality Speech from Silent Videos","created":"2023-08-29","cited_by_count":12},{"id":"2407.18505","title":"VoxSim: A perceptual voice similarity dataset","created":"2024-07-26","cited_by_count":10},{"id":"2307.16171","title":"HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer","created":"2023-07-30","cited_by_count":9},{"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":"2310.17049","title":"Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer","created":"2023-10-25","cited_by_count":3},{"id":"2406.05681","title":"Towards Expressive Zero-Shot Speech Synthesis with Hierarchical Prosody Modeling","created":"2024-06-09","cited_by_count":3}],"next_cursor":null}