{"list":"other","total":130,"rows":[{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"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":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"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":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"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":"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":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"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":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2005.07143","title":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification","created":"2020-05-14","cited_by_count":628},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"2106.06909","title":"GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio","created":"2021-06-13","cited_by_count":399},{"id":"2204.02152","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","created":"2022-04-05","cited_by_count":390},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379},{"id":"2410.06885","title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","created":"2024-10-09","cited_by_count":361},{"id":"1910.06711","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","created":"2019-10-08","cited_by_count":354},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"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":"2407.05407","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","created":"2024-07-07","cited_by_count":334},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324},{"id":"1811.00002","title":"WaveGlow: A Flow-based Generative Network for Speech Synthesis","created":"2018-10-31","cited_by_count":309},{"id":"2406.02430","title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","created":"2024-06-04","cited_by_count":300},{"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":"2304.12995","title":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","created":"2023-04-25","cited_by_count":265},{"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":"2206.04658","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","created":"2022-06-09","cited_by_count":251},{"id":"2304.09116","title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","created":"2023-04-18","cited_by_count":235},{"id":"1802.04208","title":"Adversarial Audio Synthesis","created":"2018-02-12","cited_by_count":225},{"id":"1802.08435","title":"Efficient Neural Audio Synthesis","created":"2018-02-23","cited_by_count":219},{"id":"2104.09494","title":"NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets","created":"2021-04-19","cited_by_count":192},{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184},{"id":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179},{"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":"2302.03540","title":"Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision","created":"2023-02-07","cited_by_count":169},{"id":"2409.00750","title":"MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer","created":"2024-09-01","cited_by_count":161},{"id":"2104.01409","title":"Diff-TTS: A Denoising Diffusion Model for Text-to-Speech","created":"2021-04-03","cited_by_count":157},{"id":"2306.00814","title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","created":"2023-06-01","cited_by_count":153},{"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":"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":"2406.18009","title":"E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS","created":"2024-06-26","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":"1909.05358","title":"Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset","created":"2019-09-01","cited_by_count":140},{"id":"2204.09934","title":"FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis","created":"2022-04-21","cited_by_count":136},{"id":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129},{"id":"2310.00704","title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","created":"2023-10-01","cited_by_count":127},{"id":"2312.15821","title":"Audiobox: Unified Audio Generation with Natural Language Prompts","created":"2023-12-25","cited_by_count":120},{"id":"2105.14762","title":"Emotional Voice Conversion: Theory, Databases and ESD","created":"2021-05-31","cited_by_count":115},{"id":"2211.12171","title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions","created":"2022-11-22","cited_by_count":110},{"id":"2305.02765","title":"HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec","created":"2023-05-04","cited_by_count":97},{"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":"1909.11646","title":"High Fidelity Speech Synthesis with Adversarial Networks","created":"2019-09-25","cited_by_count":92},{"id":"2301.13662","title":"InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt","created":"2023-01-31","cited_by_count":92},{"id":"2106.07889","title":"UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation","created":"2021-06-15","cited_by_count":74},{"id":"1910.10838","title":"Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings","created":"2019-10-23","cited_by_count":73},{"id":"2207.01063","title":"DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech","created":"2022-07-03","cited_by_count":69},{"id":"2303.13336","title":"A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI","created":"2023-03-23","cited_by_count":68},{"id":"2409.03283","title":"FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications","created":"2024-09-05","cited_by_count":68},{"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":"2407.08551","title":"Autoregressive Speech Synthesis without Vector Quantization","created":"2024-07-11","cited_by_count":65},{"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":"2104.05557","title":"SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model","created":"2021-04-02","cited_by_count":56},{"id":"2310.16338","title":"Generative Pre-training for Speech with Flow Matching","created":"2023-10-25","cited_by_count":55},{"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":"2306.03509","title":"Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias","created":"2023-06-06","cited_by_count":51},{"id":"2401.07333","title":"ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering","created":"2024-01-14","cited_by_count":50},{"id":"2010.11439","title":"Parallel Tacotron: Non-Autoregressive and Controllable TTS","created":"2020-10-22","cited_by_count":49},{"id":"2308.14430","title":"TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models","created":"2023-08-28","cited_by_count":48},{"id":"2406.07855","title":"VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment","created":"2024-06-12","cited_by_count":38},{"id":"2404.02781","title":"CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech","created":"2024-04-03","cited_by_count":37},{"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":"2211.09383","title":"Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":34},{"id":"2305.19522","title":"PromptStyle: Controllable Style Transfer for Text-to-Speech with Natural Language Descriptions","created":"2023-05-31","cited_by_count":34},{"id":"2210.03538","title":"An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era","created":"2022-10-06","cited_by_count":33},{"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":"2011.08679","title":"Controllable Emotion Transfer For End-to-End Speech Synthesis","created":"2020-11-17","cited_by_count":32},{"id":"2107.01554","title":"EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion","created":"2021-07-04","cited_by_count":32},{"id":"2406.11427","title":"DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors","created":"2024-06-17","cited_by_count":32},{"id":"2311.00945","title":"E3 TTS: Easy End-to-End Diffusion-based Text to Speech","created":"2023-11-02","cited_by_count":30},{"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":"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":"2110.02584","title":"EdiTTS: Score-based Editing for Controllable Text-to-Speech","created":"2021-10-06","cited_by_count":28},{"id":"2305.19269","title":"Make-A-Voice: Unified Voice Synthesis With Discrete Representation","created":"2023-05-30","cited_by_count":27},{"id":"2102.01106","title":"Universal Neural Vocoding with Parallel WaveNet","created":"2021-02-01","cited_by_count":25},{"id":"2309.08140","title":"PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions","created":"2023-09-15","cited_by_count":25}],"next_cursor":"100"}