{"list":"other","total":55,"rows":[{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"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":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"1910.06711","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","created":"2019-10-08","cited_by_count":354},{"id":"1910.11480","title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","created":"2019-10-25","cited_by_count":340},{"id":"1811.00002","title":"WaveGlow: A Flow-based Generative Network for Speech Synthesis","created":"2018-10-31","cited_by_count":309},{"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":"1704.01279","title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","created":"2017-04-05","cited_by_count":225},{"id":"1802.04208","title":"Adversarial Audio Synthesis","created":"2018-02-12","cited_by_count":225},{"id":"1812.08466","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","created":"2018-12-20","cited_by_count":225},{"id":"1802.08435","title":"Efficient Neural Audio Synthesis","created":"2018-02-23","cited_by_count":219},{"id":"1810.12247","title":"Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset","created":"2018-10-29","cited_by_count":217},{"id":"1711.10433","title":"Parallel WaveNet: Fast High-Fidelity Speech Synthesis","created":"2017-11-28","cited_by_count":215},{"id":"2001.04643","title":"DDSP: Differentiable Digital Signal Processing","created":"2020-01-14","cited_by_count":178},{"id":"1703.09452","title":"SEGAN: Speech Enhancement Generative Adversarial Network","created":"2017-03-28","cited_by_count":166},{"id":"1709.06298","title":"MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment","created":"2017-09-19","cited_by_count":151},{"id":"1902.08710","title":"GANSynth: Adversarial Neural Audio Synthesis","created":"2019-02-23","cited_by_count":116},{"id":"1612.07837","title":"SampleRNN: An Unconditional End-to-End Neural Audio Generation Model","created":"2016-12-22","cited_by_count":110},{"id":"1810.11846","title":"LPCNet: Improving Neural Speech Synthesis Through Linear Prediction","created":"2018-10-28","cited_by_count":110},{"id":"1909.11646","title":"High Fidelity Speech Synthesis with Adversarial Networks","created":"2019-09-25","cited_by_count":92},{"id":"1702.07825","title":"Deep Voice: Real-time Neural Text-to-Speech","created":"2017-02-25","cited_by_count":83},{"id":"2006.03575","title":"End-to-End Adversarial Text-to-Speech","created":"2020-06-05","cited_by_count":77},{"id":"1705.08947","title":"Deep Voice 2: Multi-Speaker Neural Text-to-Speech","created":"2017-05-24","cited_by_count":75},{"id":"1703.10847","title":"MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation","created":"2017-03-31","cited_by_count":72},{"id":"1807.07281","title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","created":"2018-07-19","cited_by_count":70},{"id":"1811.02155","title":"FloWaveNet : A Generative Flow for Raw Audio","created":"2018-11-06","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":"1904.12088","title":"Neural source-filter waveform models for statistical parametric speech synthesis","created":"2019-04-27","cited_by_count":46},{"id":"1906.01083","title":"MelNet: A Generative Model for Audio in the Frequency Domain","created":"2019-06-04","cited_by_count":42},{"id":"1811.09620","title":"TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer","created":"2018-11-22","cited_by_count":33},{"id":"1810.09785","title":"SING: Symbol-to-Instrument Neural Generator","created":"2018-10-23","cited_by_count":23},{"id":"1808.06719","title":"Fast Spectrogram Inversion using Multi-head Convolutional Neural Networks","created":"2018-08-20","cited_by_count":22},{"id":"1907.00971","title":"Universal audio synthesizer control with normalizing flows","created":"2019-07-01","cited_by_count":17},{"id":"1709.08041","title":"Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks","created":"2017-09-23","cited_by_count":16},{"id":"1704.03809","title":"A Neural Parametric Singing Synthesizer","created":"2017-04-12","cited_by_count":14},{"id":"1904.04472","title":"Probability density distillation with generative adversarial networks for high-quality parallel waveform generation","created":"2019-04-09","cited_by_count":14},{"id":"1805.08501","title":"Generative timbre spaces: regularizing variational auto-encoders with perceptual metrics","created":"2018-05-22","cited_by_count":13},{"id":"1807.11470","title":"Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis","created":"2018-07-30","cited_by_count":13},{"id":"1801.00887","title":"DeepJ: Style-Specific Music Generation","created":"2018-01-03","cited_by_count":12},{"id":"1806.09905","title":"Conditioning Deep Generative Raw Audio Models for Structured Automatic Music","created":"2018-06-26","cited_by_count":10},{"id":"1904.07944","title":"Expediting TTS Synthesis with Adversarial Vocoding","created":"2019-04-16","cited_by_count":10},{"id":"1907.02637","title":"Neural Drum Machine : An Interactive System for Real-time Synthesis of Drum Sounds","created":"2019-07-04","cited_by_count":9},{"id":"1804.02181","title":"Generative adversarial network-based approach to signal reconstruction from magnitude spectrograms","created":"2018-04-06","cited_by_count":8},{"id":"2006.06426","title":"Deep generative models for musical audio synthesis","created":"2020-06-10","cited_by_count":6},{"id":"1707.01670","title":"Statistical Parametric Speech Synthesis Using Generative Adversarial Networks Under A Multi-task Learning Framework","created":"2017-07-06","cited_by_count":5},{"id":"2008.01393","title":"Neural Granular Sound Synthesis","created":"2020-08-04","cited_by_count":4},{"id":"1801.07910","title":"Waveform Modeling and Generation Using Hierarchical Recurrent Neural Networks for Speech Bandwidth Extension","created":"2018-01-24","cited_by_count":3},{"id":"1807.11679","title":"Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder","created":"2018-07-31","cited_by_count":3},{"id":"2002.00417","title":"WaveTTS: Tacotron-based TTS with Joint Time-Frequency Domain Loss","created":"2020-02-02","cited_by_count":2},{"id":"2004.00001","title":"VaPar Synth -- A Variational Parametric Model for Audio Synthesis","created":"2020-03-30","cited_by_count":2}],"next_cursor":null}