{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"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":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"1611.04076","title":"Least Squares Generative Adversarial Networks","created":"2016-11-13","cited_by_count":1001},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"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":"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":"2112.07804","title":"Tackling the Generative Learning Trilemma with Denoising Diffusion GANs","created":"2021-12-15","cited_by_count":516},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"1710.10467","title":"Generalized End-to-End Loss for Speaker Verification","created":"2017-10-28","cited_by_count":293},{"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":"1803.09047","title":"Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron","created":"2018-03-24","cited_by_count":173},{"id":"2105.02446","title":"DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism","created":"2021-05-06","cited_by_count":154},{"id":"2006.06873","title":"FastPitch: Parallel Text-to-speech with Pitch Prediction","created":"2020-06-11","cited_by_count":151},{"id":"2103.00993","title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","created":"2021-03-01","cited_by_count":98},{"id":"2106.03153","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","created":"2021-06-06","cited_by_count":93},{"id":"2203.08488","title":"Pushing the limits of raw waveform speaker recognition","created":"2022-03-16","cited_by_count":51},{"id":"2109.15166","title":"PortaSpeech: Portable and High-Quality Generative Text-to-Speech","created":"2021-09-30","cited_by_count":47},{"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":"2202.13066","title":"Revisiting Over-Smoothness in Text to Speech","created":"2022-02-26","cited_by_count":32},{"id":"2008.01490","title":"Expressive TTS Training with Frame and Style Reconstruction Loss","created":"2020-08-04","cited_by_count":30},{"id":"2012.07267","title":"Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis","created":"2020-12-14","cited_by_count":28},{"id":"2011.05161","title":"Improving Prosody Modelling with Cross-Utterance BERT Embeddings for End-to-end Speech Synthesis","created":"2020-11-06","cited_by_count":27},{"id":"1906.10508","title":"Non-Parallel Sequence-to-Sequence Voice Conversion with Disentangled Linguistic and Speaker Representations","created":"2019-06-25","cited_by_count":23},{"id":"2202.07816","title":"ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech","created":"2022-02-16","cited_by_count":22},{"id":"1810.06865","title":"Sequence-to-Sequence Acoustic Modeling for Voice Conversion","created":"2018-10-16","cited_by_count":20},{"id":"2204.11792","title":"SyntaSpeech: Syntax-Aware Generative Adversarial Text-to-Speech","created":"2022-04-25","cited_by_count":18},{"id":"2105.13086","title":"Phone-Level Prosody Modelling with GMM-Based MDN for Diverse and Controllable Speech Synthesis","created":"2021-05-27","cited_by_count":10},{"id":"2207.01718","title":"BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model","created":"2022-07-04","cited_by_count":10},{"id":"2110.02952","title":"Hierarchical prosody modeling and control in non-autoregressive parallel neural TTS","created":"2021-10-06","cited_by_count":9},{"id":"2110.03012","title":"Emphasis control for parallel neural TTS","created":"2021-10-06","cited_by_count":9},{"id":"2206.15067","title":"Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems","created":"2022-06-30","cited_by_count":9},{"id":"2206.14643","title":"Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody","created":"2022-06-29","cited_by_count":5},{"id":"2209.06484","title":"ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTS","created":"2022-09-14","cited_by_count":5},{"id":"2306.07489","title":"PauseSpeech: Natural Speech Synthesis via Pre-trained Language Model and Pause-based Prosody Modeling","created":"2023-06-13","cited_by_count":5},{"id":"2302.12391","title":"PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS","created":"2023-02-24","cited_by_count":4},{"id":"2201.09472","title":"Disentangling Style and Speaker Attributes for TTS Style Transfer","created":"2022-01-24","cited_by_count":3},{"id":"2204.05753","title":"Enhancement of Pitch Controllability using Timbre-Preserving Pitch Augmentation in FastPitch","created":"2022-04-12","cited_by_count":1}],"next_cursor":null}