{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"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":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"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":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"1904.02882","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","created":"2019-04-05","cited_by_count":649},{"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":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"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":"2406.02430","title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","created":"2024-06-04","cited_by_count":300},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288},{"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":"2304.09116","title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","created":"2023-04-18","cited_by_count":235},{"id":"1905.05879","title":"AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","created":"2019-05-14","cited_by_count":192},{"id":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179},{"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":"2303.03926","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","created":"2023-03-07","cited_by_count":167},{"id":"2409.00750","title":"MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer","created":"2024-09-01","cited_by_count":161},{"id":"2406.05370","title":"VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers","created":"2024-06-08","cited_by_count":122},{"id":"2403.16973","title":"VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild","created":"2024-03-25","cited_by_count":120},{"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":"2409.09305","title":"The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech","created":"2024-09-14","cited_by_count":83},{"id":"2110.14513","title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","created":"2021-10-27","cited_by_count":81},{"id":"2210.15418","title":"FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion","created":"2022-10-27","cited_by_count":80},{"id":"2204.09224","title":"ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers","created":"2022-04-20","cited_by_count":74},{"id":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71},{"id":"2305.07243","title":"Better speech synthesis through scaling","created":"2023-05-12","cited_by_count":63},{"id":"2404.02677","title":"The VoicePrivacy 2024 Challenge Evaluation Plan","created":"2024-04-03","cited_by_count":41},{"id":"2402.13236","title":"Towards audio language modeling -- an overview","created":"2024-02-20","cited_by_count":40},{"id":"2211.09407","title":"NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis","created":"2022-11-17","cited_by_count":38},{"id":"2110.06280","title":"S3PRL-VC: Open-source Voice Conversion Framework with Self-supervised Speech Representations","created":"2021-10-12","cited_by_count":23},{"id":"2306.10521","title":"LM-VC: Zero-shot Voice Conversion via Speech Generation based on Language Models","created":"2023-06-18","cited_by_count":18},{"id":"2104.02901","title":"S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations","created":"2021-04-07","cited_by_count":17},{"id":"2311.14957","title":"Multi-Scale Sub-Band Constant-Q Transform Discriminator for High-Fidelity Vocoder","created":"2023-11-25","cited_by_count":13},{"id":"2010.12788","title":"GAZEV: GAN-Based Zero-Shot Voice Conversion over Non-parallel Speech Corpus","created":"2020-10-24","cited_by_count":10},{"id":"2409.03655","title":"Privacy versus Emotion Preservation Trade-offs in Emotion-Preserving Speaker Anonymization","created":"2024-09-05","cited_by_count":10},{"id":"2401.11053","title":"StreamVoice: Streamable Context-Aware Language Modeling for Real-time Zero-Shot Voice Conversion","created":"2024-01-19","cited_by_count":9},{"id":"2111.03811","title":"SIG-VC: A Speaker Information Guided Zero-shot Voice Conversion System for Both Human Beings and Machines","created":"2021-11-06","cited_by_count":5},{"id":"2206.09103","title":"Identifying Source Speakers for Voice Conversion based Spoofing Attacks on Speaker Verification Systems","created":"2022-06-18","cited_by_count":5},{"id":"2406.04951","title":"The Database and Benchmark for the Source Speaker Tracing Challenge 2024","created":"2024-06-07","cited_by_count":2}],"next_cursor":null}