{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"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":"1711.09020","title":"StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation","created":"2017-11-24","cited_by_count":1039},{"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":"1703.10593","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","created":"2017-03-30","cited_by_count":707},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"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":"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":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","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":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243},{"id":"1802.04208","title":"Adversarial Audio Synthesis","created":"2018-02-12","cited_by_count":225},{"id":"1711.10433","title":"Parallel WaveNet: Fast High-Fidelity Speech Synthesis","created":"2017-11-28","cited_by_count":215},{"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":"2203.07378","title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","created":"2022-03-14","cited_by_count":157},{"id":"1611.02200","title":"Unsupervised Cross-Domain Image Generation","created":"2016-11-07","cited_by_count":125},{"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":"2109.03264","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","created":"2021-09-07","cited_by_count":119},{"id":"2105.14762","title":"Emotional Voice Conversion: Theory, Databases and ESD","created":"2021-05-31","cited_by_count":115},{"id":"2008.03648","title":"An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning","created":"2020-08-09","cited_by_count":112},{"id":"1702.07825","title":"Deep Voice: Real-time Neural Text-to-Speech","created":"2017-02-25","cited_by_count":83},{"id":"1806.02169","title":"StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks","created":"2018-06-06","cited_by_count":78},{"id":"1705.08947","title":"Deep Voice 2: Multi-Speaker Neural Text-to-Speech","created":"2017-05-24","cited_by_count":75},{"id":"1904.04631","title":"CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion","created":"2019-04-09","cited_by_count":46},{"id":"1610.04019","title":"Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder","created":"2016-10-13","cited_by_count":45},{"id":"2201.03967","title":"Emotion Intensity and its Control for Emotional Voice Conversion","created":"2022-01-10","cited_by_count":35},{"id":"1808.01410","title":"Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesis","created":"2018-08-04","cited_by_count":32},{"id":"1711.05447","title":"Emotional End-to-End Neural Speech Synthesizer","created":"2017-11-15","cited_by_count":30},{"id":"2008.01490","title":"Expressive TTS Training with Frame and Style Reconstruction Loss","created":"2020-08-04","cited_by_count":30},{"id":"2011.08477","title":"Fine-grained Emotion Strength Transfer, Control and Prediction for Emotional Speech Synthesis","created":"2020-11-17","cited_by_count":29},{"id":"2111.07402","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","created":"2021-11-14","cited_by_count":29},{"id":"2201.06460","title":"MsEmoTTS: Multi-scale emotion transfer, prediction, and control for emotional speech synthesis","created":"2022-01-17","cited_by_count":29},{"id":"1911.01635","title":"Emotional speech synthesis with rich and granularized control","created":"2019-11-05","cited_by_count":28},{"id":"2002.00198","title":"Transforming Spectrum and Prosody for Emotional Voice Conversion with Non-Parallel Training Data","created":"2020-02-01","cited_by_count":26},{"id":"2011.05707","title":"Low-resource expressive text-to-speech using data augmentation","created":"2020-11-11","cited_by_count":26},{"id":"1811.04076","title":"AttS2S-VC: Sequence-to-Sequence Voice Conversion with Attention and Context Preservation Mechanisms","created":"2018-11-09","cited_by_count":22},{"id":"2109.06733","title":"Cross-speaker emotion disentangling and transfer for end-to-end speech synthesis","created":"2021-09-14","cited_by_count":21},{"id":"1907.06333","title":"Myers-Briggs Personality Classification and Personality-Specific Language Generation Using Pre-trained Language Models","created":"2019-07-15","cited_by_count":20},{"id":"1906.10859","title":"End-to-End Emotional Speech Synthesis Using Style Tokens and Semi-Supervised Training","created":"2019-06-26","cited_by_count":19},{"id":"2010.13350","title":"Emotion controllable speech synthesis using emotion-unlabeled dataset with the assistance of cross-domain speech emotion recognition","created":"2020-10-26","cited_by_count":19},{"id":"2104.01408","title":"Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability","created":"2021-04-03","cited_by_count":19},{"id":"1811.01174","title":"Nonparallel Emotional Speech Conversion","created":"2018-11-03","cited_by_count":17},{"id":"2205.01780","title":"The ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Bursts","created":"2022-05-03","cited_by_count":16},{"id":"1911.06149","title":"Emotional Voice Conversion using Multitask Learning with Text-to-speech","created":"2019-11-11","cited_by_count":15},{"id":"2206.14866","title":"iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre","created":"2022-06-29","cited_by_count":15},{"id":"2204.00400","title":"Probing Speech Emotion Recognition Transformers for Linguistic Knowledge","created":"2022-04-01","cited_by_count":13},{"id":"2107.03748","title":"Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer","created":"2021-07-08","cited_by_count":10},{"id":"1911.12760","title":"Using VAEs and Normalizing Flows for One-shot Text-To-Speech Synthesis of Expressive Speech","created":"2019-11-28","cited_by_count":8},{"id":"2005.09178","title":"Transferring Source Style in Non-Parallel Voice Conversion","created":"2020-05-19","cited_by_count":7},{"id":"2107.08361","title":"An Improved StarGAN for Emotional Voice Conversion: Enhancing Voice Quality and Data Augmentation","created":"2021-07-18","cited_by_count":7},{"id":"2203.15873","title":"An Overview & Analysis of Sequence-to-Sequence Emotional Voice Conversion","created":"2022-03-29","cited_by_count":6},{"id":"2004.03781","title":"Emotional Voice Conversion With Cycle-consistent Adversarial Network","created":"2020-04-08","cited_by_count":5},{"id":"2202.06409","title":"Distribution augmentation for low-resource expressive text-to-speech","created":"2022-02-13","cited_by_count":5},{"id":"2104.01807","title":"StarGAN-based Emotional Voice Conversion for Japanese Phrases","created":"2021-04-05","cited_by_count":4},{"id":"2206.12563","title":"Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms","created":"2022-06-25","cited_by_count":3},{"id":"2110.09780","title":"Improving Emotional Speech Synthesis by Using SUS-Constrained VAE and Text Encoder Aggregation","created":"2021-10-19","cited_by_count":2},{"id":"2012.06847","title":"AffectON: Incorporating Affect Into Dialog Generation","created":"2020-12-12","cited_by_count":1}],"next_cursor":null}