{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"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":"1912.01865","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","created":"2019-12-04","cited_by_count":1098},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"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":"1904.02882","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","created":"2019-04-05","cited_by_count":649},{"id":"1907.11922","title":"MaskGAN: Towards Diverse and Interactive Facial Image Manipulation","created":"2019-07-27","cited_by_count":628},{"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":"1804.00015","title":"ESPnet: End-to-End Speech Processing Toolkit","created":"2018-03-30","cited_by_count":558},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"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":"2005.11129","title":"Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search","created":"2020-05-22","cited_by_count":273},{"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":"1911.12861","title":"SEAN: Image Synthesis with Semantic Region-Adaptive Normalization","created":"2019-11-28","cited_by_count":253},{"id":"1905.01723","title":"Few-Shot Unsupervised Image-to-Image Translation","created":"2019-05-05","cited_by_count":222},{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184},{"id":"1803.09047","title":"Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron","created":"2018-03-24","cited_by_count":173},{"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":"2006.06873","title":"FastPitch: Parallel Text-to-speech with Pitch Prediction","created":"2020-06-11","cited_by_count":151},{"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":"2103.16877","title":"ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows","created":"2021-03-31","cited_by_count":113},{"id":"2103.00993","title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","created":"2021-03-01","cited_by_count":98},{"id":"1810.07217","title":"Hierarchical Generative Modeling for Controllable Speech Synthesis","created":"2018-10-16","cited_by_count":93},{"id":"2106.03153","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","created":"2021-06-06","cited_by_count":93},{"id":"2110.15018","title":"TorchAudio: Building Blocks for Audio and Speech Processing","created":"2021-10-28","cited_by_count":83},{"id":"1904.05742","title":"One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization","created":"2019-04-10","cited_by_count":82},{"id":"1812.04342","title":"Learning latent representations for style control and transfer in end-to-end speech synthesis","created":"2018-12-11","cited_by_count":61},{"id":"2107.10394","title":"StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion","created":"2021-07-21","cited_by_count":58},{"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":"2103.15060","title":"PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS","created":"2021-03-28","cited_by_count":52},{"id":"2109.15166","title":"PortaSpeech: Portable and High-Quality Generative Text-to-Speech","created":"2021-09-30","cited_by_count":47},{"id":"1910.11997","title":"Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens","created":"2019-10-26","cited_by_count":44},{"id":"2011.00316","title":"AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization","created":"2020-10-31","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":"2002.03785","title":"Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis","created":"2020-02-06","cited_by_count":41},{"id":"2103.14574","title":"Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling","created":"2021-03-26","cited_by_count":31},{"id":"2008.01490","title":"Expressive TTS Training with Frame and Style Reconstruction Loss","created":"2020-08-04","cited_by_count":30},{"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":"2110.07840","title":"ESPnet2-TTS: Extending the Edge of TTS Research","created":"2021-10-15","cited_by_count":22},{"id":"2005.03295","title":"Cotatron: Transcription-Guided Speech Encoder for Any-to-Many Voice Conversion without Parallel Data","created":"2020-05-07","cited_by_count":14},{"id":"2012.03500","title":"EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture","created":"2020-12-07","cited_by_count":14},{"id":"2106.04312","title":"Speech BERT Embedding For Improving Prosody in Neural TTS","created":"2021-06-08","cited_by_count":11}],"next_cursor":null}