{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"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":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"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":"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":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"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":"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":"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":"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":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"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":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379},{"id":"1511.05644","title":"Adversarial Autoencoders","created":"2015-11-18","cited_by_count":364},{"id":"1705.07120","title":"VAE with a VampPrior","created":"2017-05-19","cited_by_count":248},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243},{"id":"1611.02648","title":"Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders","created":"2016-11-08","cited_by_count":220},{"id":"1905.05879","title":"AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","created":"2019-05-14","cited_by_count":192},{"id":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179},{"id":"2405.15682","title":"The Road Less Scheduled","created":"2024-05-24","cited_by_count":163},{"id":"2104.01409","title":"Diff-TTS: A Denoising Diffusion Model for Text-to-Speech","created":"2021-04-03","cited_by_count":157},{"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":"2207.06389","title":"ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech","created":"2022-07-13","cited_by_count":149},{"id":"2309.03199","title":"Matcha-TTS: A fast TTS architecture with conditional flow matching","created":"2023-09-06","cited_by_count":145},{"id":"2001.09239","title":"Multi-task self-supervised learning for Robust Speech Recognition","created":"2020-01-25","cited_by_count":130},{"id":"2305.09636","title":"SoundStorm: Efficient Parallel Audio Generation","created":"2023-05-16","cited_by_count":114},{"id":"2210.17016","title":"Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit","created":"2022-10-31","cited_by_count":97},{"id":"1901.08810","title":"Unsupervised speech representation learning using WaveNet autoencoders","created":"2019-01-25","cited_by_count":90},{"id":"1704.00784","title":"Online and Linear-Time Attention by Enforcing Monotonic Alignments","created":"2017-04-03","cited_by_count":85},{"id":"1712.05382","title":"Monotonic Chunkwise Attention","created":"2017-12-14","cited_by_count":83},{"id":"2312.02116","title":"GIVT: Generative Infinite-Vocabulary Transformers","created":"2023-12-04","cited_by_count":80},{"id":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71},{"id":"2402.01912","title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations","created":"2024-02-02","cited_by_count":67},{"id":"2305.07243","title":"Better speech synthesis through scaling","created":"2023-05-12","cited_by_count":63},{"id":"2005.08520","title":"Robust Training of Vector Quantized Bottleneck Models","created":"2020-05-18","cited_by_count":54},{"id":"2201.11972","title":"DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs","created":"2022-01-28","cited_by_count":43},{"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":"1906.00672","title":"Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS","created":"2019-06-03","cited_by_count":33},{"id":"2205.15439","title":"StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis","created":"2022-05-30","cited_by_count":33},{"id":"2203.16852","title":"JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech","created":"2022-03-31","cited_by_count":26},{"id":"2302.04215","title":"A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech","created":"2023-02-08","cited_by_count":22},{"id":"1607.05690","title":"Stochastic Backpropagation through Mixture Density Distributions","created":"2016-07-19","cited_by_count":14},{"id":"2406.05401","title":"Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech","created":"2024-06-08","cited_by_count":5}],"next_cursor":null}