{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/transfer-learning-from-speaker-verification","title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","arxiv_id":"1806.04558","date":"2018-06-12","proceeding":"NeurIPS 2018 12","authors":["Ye Jia","Yu Zhang","Ron J. Weiss","Quan Wang","Jonathan Shen","Fei Ren","Zhifeng Chen","Patrick Nguyen","Ruoming Pang","Ignacio Lopez Moreno","Yonghui Wu"],"abstract":"Clone a voice in 5 seconds to generate arbitrary speech in real-time","url_abs":"http://arxiv.org/abs/1806.04558v4","url_pdf":"http://arxiv.org/pdf/1806.04558v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"transfer-learning-from-speaker-verification","repo_url":"https://github.com/CorentinJ/Real-Time-Voice-Cloning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"transfer-learning-from-speaker-verification","repo_url":"https://github.com/GNovich/Talk2Me","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"transfer-learning-from-speaker-verification","repo_url":"https://github.com/Suhee05/Text-Independent-Speaker-Verification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"transfer-learning-from-speaker-verification","repo_url":"https://github.com/kingridda/voice-cloning-AI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"transfer-learning-from-speaker-verification","repo_url":"https://github.com/majidAdibian77/persian-SV2TTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"transfer-learning-from-speaker-verification","repo_url":"https://github.com/tigthor/Voice-Cloning-AI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"transfer-learning-from-speaker-verification","repo_url":"https://github.com/MugheesQasim/Voice-Cloning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"transfer-learning-from-speaker-verification","repo_url":"https://github.com/PaddlePaddle/PaddleSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"transfer-learning-from-speaker-verification","repo_url":"https://github.com/RuntimeRacer/rtvc-gcloud","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"transfer-learning-from-speaker-verification","repo_url":"https://github.com/ndk03/Accent-Preserving-Voice-Cloning-using-SV2TTS/tree/master/Speech-Modeling-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"transfer-learning-from-speaker-verification","repo_url":"https://github.com/smoke-trees/Voice-synthesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"speaker-verification","task_name":"Speaker Verification"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-synthesis","task_name":"Text-To-Speech Synthesis"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"voice-cloning","task_name":"Voice Cloning"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.04558","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}