{"list":"other","total":96,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2303.01469","title":"Consistency Models","created":"2023-03-02","cited_by_count":1822},{"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":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"1912.02762","title":"Normalizing Flows for Probabilistic Modeling and Inference","created":"2019-12-05","cited_by_count":1323},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2303.08797","title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","created":"2023-03-15","cited_by_count":939},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"2401.08740","title":"SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers","created":"2024-01-16","cited_by_count":737},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"1711.06077","title":"The Perception-Distortion Tradeoff","created":"2017-11-16","cited_by_count":587},{"id":"1905.06922","title":"On Variational Bounds of Mutual Information","created":"2019-05-16","cited_by_count":559},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"1701.05517","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","created":"2017-01-19","cited_by_count":417},{"id":"1512.09300","title":"Autoencoding beyond pixels using a learned similarity metric","created":"2015-12-31","cited_by_count":407},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"2101.02388","title":"Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed","created":"2021-01-07","cited_by_count":348},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"1710.10467","title":"Generalized End-to-End Loss for Speaker Verification","created":"2017-10-28","cited_by_count":293},{"id":"1806.04558","title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","created":"2018-06-12","cited_by_count":282},{"id":"2207.14255","title":"Efficient Training of Language Models to Fill in the Middle","created":"2022-07-28","cited_by_count":255},{"id":"2206.04658","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","created":"2022-06-09","cited_by_count":251},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243},{"id":"2305.18455","title":"Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models","created":"2023-05-29","cited_by_count":236},{"id":"1711.10433","title":"Parallel WaveNet: Fast High-Fidelity Speech Synthesis","created":"2017-11-28","cited_by_count":215},{"id":"2404.04057","title":"Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation","created":"2024-04-05","cited_by_count":214},{"id":"1901.07821","title":"Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff","created":"2019-01-23","cited_by_count":211},{"id":"2210.17432","title":"SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control","created":"2022-10-31","cited_by_count":194},{"id":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187},{"id":"1611.02731","title":"Variational Lossy Autoencoder","created":"2016-11-08","cited_by_count":176},{"id":"2211.13449","title":"Fast Sampling of Diffusion Models via Operator Learning","created":"2022-11-24","cited_by_count":175},{"id":"2302.03540","title":"Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision","created":"2023-02-07","cited_by_count":169},{"id":"2303.03926","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","created":"2023-03-07","cited_by_count":167},{"id":"2310.00704","title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","created":"2023-10-01","cited_by_count":127},{"id":"2403.16973","title":"VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild","created":"2024-03-25","cited_by_count":120},{"id":"2303.04248","title":"TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation","created":"2023-03-07","cited_by_count":116},{"id":"2402.09470","title":"Rolling Diffusion Models","created":"2024-02-12","cited_by_count":104},{"id":"2305.13311","title":"VDT: General-purpose Video Diffusion Transformers via Mask Modeling","created":"2023-05-22","cited_by_count":103},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101},{"id":"2306.05544","title":"BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping","created":"2023-06-08","cited_by_count":98},{"id":"2210.17016","title":"Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit","created":"2022-10-31","cited_by_count":97},{"id":"2305.02765","title":"HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec","created":"2023-05-04","cited_by_count":97},{"id":"2305.16107","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","created":"2023-05-25","cited_by_count":87},{"id":"2308.16692","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","created":"2023-08-31","cited_by_count":87},{"id":"2305.08842","title":"Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks","created":"2023-05-15","cited_by_count":82},{"id":"2312.02116","title":"GIVT: Generative Infinite-Vocabulary Transformers","created":"2023-12-04","cited_by_count":80},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78},{"id":"2308.06873","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","created":"2023-08-14","cited_by_count":64},{"id":"2212.08055","title":"UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units","created":"2022-12-15","cited_by_count":60},{"id":"2005.05957","title":"Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis","created":"2020-05-12","cited_by_count":54},{"id":"1912.01219","title":"WaveFlow: A Compact Flow-based Model for Raw Audio","created":"2019-12-03","cited_by_count":51},{"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},{"id":"2305.16608","title":"AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec","created":"2023-05-26","cited_by_count":47},{"id":"2402.19159","title":"Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping","created":"2024-02-29","cited_by_count":46},{"id":"2309.07405","title":"FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec","created":"2023-09-14","cited_by_count":44},{"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},{"id":"2402.13236","title":"Towards audio language modeling -- an overview","created":"2024-02-20","cited_by_count":40},{"id":"2011.03568","title":"Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis","created":"2020-11-06","cited_by_count":38},{"id":"2110.10139","title":"Chunked Autoregressive GAN for Conditional Waveform Synthesis","created":"2021-10-19","cited_by_count":38},{"id":"2306.07547","title":"UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding","created":"2023-06-13","cited_by_count":37},{"id":"2404.02781","title":"CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech","created":"2024-04-03","cited_by_count":37},{"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},{"id":"2107.01554","title":"EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion","created":"2021-07-04","cited_by_count":32},{"id":"2010.11255","title":"The IDLAB VoxSRC-20 Submission: Large Margin Fine-Tuning and Quality-Aware Score Calibration in DNN Based Speaker Verification","created":"2020-10-21","cited_by_count":23},{"id":"2305.16150","title":"Unifying GANs and Score-Based Diffusion as Generative Particle Models","created":"2023-05-25","cited_by_count":21},{"id":"2310.05224","title":"Generative Spoken Language Model based on continuous word-sized audio tokens","created":"2023-10-08","cited_by_count":19},{"id":"2202.07273","title":"SpeechPainter: Text-conditioned Speech Inpainting","created":"2022-02-15","cited_by_count":17},{"id":"2105.13086","title":"Phone-Level Prosody Modelling with GMM-Based MDN for Diverse and Controllable Speech Synthesis","created":"2021-05-27","cited_by_count":10},{"id":"2206.13865","title":"RetrieverTTS: Modeling Decomposed Factors for Text-Based Speech Insertion","created":"2022-06-28","cited_by_count":10},{"id":"2310.01400","title":"Sequential Data Generation with Groupwise Diffusion Process","created":"2023-10-02","cited_by_count":5}],"next_cursor":null}