{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"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":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"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":"2006.04558","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","created":"2020-06-08","cited_by_count":717},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379},{"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},{"id":"1803.09017","title":"Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis","created":"2018-03-23","cited_by_count":259},{"id":"2304.09116","title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","created":"2023-04-18","cited_by_count":235},{"id":"1905.05879","title":"AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","created":"2019-05-14","cited_by_count":192},{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184},{"id":"2205.04421","title":"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality","created":"2022-05-09","cited_by_count":152},{"id":"2306.07691","title":"StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models","created":"2023-06-13","cited_by_count":152},{"id":"2010.14794","title":"Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset","created":"2020-10-28","cited_by_count":121},{"id":"2105.14762","title":"Emotional Voice Conversion: Theory, Databases and ESD","created":"2021-05-31","cited_by_count":115},{"id":"2211.12171","title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions","created":"2022-11-22","cited_by_count":110},{"id":"2103.00993","title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","created":"2021-03-01","cited_by_count":98},{"id":"2301.13662","title":"InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt","created":"2023-01-31","cited_by_count":92},{"id":"2004.11284","title":"Unsupervised Speech Decomposition via Triple Information Bottleneck","created":"2020-04-23","cited_by_count":88},{"id":"1702.07825","title":"Deep Voice: Real-time Neural Text-to-Speech","created":"2017-02-25","cited_by_count":83},{"id":"1705.08947","title":"Deep Voice 2: Multi-Speaker Neural Text-to-Speech","created":"2017-05-24","cited_by_count":75},{"id":"2111.14706","title":"ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet","created":"2021-11-29","cited_by_count":53},{"id":"2308.14430","title":"TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models","created":"2023-08-28","cited_by_count":48},{"id":"2205.14807","title":"BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis","created":"2022-05-30","cited_by_count":44},{"id":"2006.04664","title":"MultiSpeech: Multi-Speaker Text to Speech with Transformer","created":"2020-06-08","cited_by_count":42},{"id":"2204.00436","title":"AdaSpeech 4: Adaptive Text to Speech in Zero-Shot Scenarios","created":"2022-04-01","cited_by_count":41},{"id":"2305.19522","title":"PromptStyle: Controllable Style Transfer for Text-to-Speech with Natural Language Descriptions","created":"2023-05-31","cited_by_count":34},{"id":"2111.04040","title":"Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech","created":"2021-11-07","cited_by_count":22},{"id":"2212.14518","title":"ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech","created":"2022-12-30","cited_by_count":21},{"id":"2104.09715","title":"AdaSpeech 2: Adaptive Text to Speech with Untranscribed Data","created":"2021-04-20","cited_by_count":17},{"id":"2208.08757","title":"Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion","created":"2022-08-18","cited_by_count":14},{"id":"2106.15123","title":"FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis","created":"2021-06-29","cited_by_count":12},{"id":"2007.15281","title":"Speaking Speed Control of End-to-End Speech Synthesis using Sentence-Level Conditioning","created":"2020-07-30","cited_by_count":8}],"next_cursor":null}