{"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/robust-universal-neural-vocoding","title":"Robust universal neural vocoding","arxiv_id":"1811.06292","date":"2018-11-15","proceeding":null,"authors":["Jaime Lorenzo-Trueba","Thomas Drugman","Javier Latorre","Thomas Merritt","Bartosz Putrycz","Roberto Barra-Chicote"],"abstract":"This paper introduces a robust universal neural vocoder trained with 74\nspeakers (comprised of both genders) coming from 17 languages. This vocoder is\nshown to be capable of generating speech of consistently good quality (98%\nrelative mean MUSHRA when compared to natural speech) regardless of whether the\ninput spectrogram comes from a speaker, style or recording condition seen\nduring training or from an out-of-domain scenario.\n  Together with the system, we present a full text-to-speech analysis of\nrobustness of a number of implemented systems. The complexity of systems tested\nrange from a convolutional neural networks-based system conditioned on\nlinguistics to a recurrent neural networks-based system conditioned on\nmel-spectrograms. The analysis shows that convolutional neural networks-based\nsystems are prone to occasional instabilities, while the recurrent approaches\nare significantly more stable and capable of providing universalizing\nrobustness.","url_abs":"http://arxiv.org/abs/1811.06292v1","url_pdf":"http://arxiv.org/pdf/1811.06292v1.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":"robust-universal-neural-vocoding","repo_url":"https://github.com/anandaswarup/waveRNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"robust-universal-neural-vocoding","repo_url":"https://github.com/avanitanna/robustfragmentvc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"robust-universal-neural-vocoding","repo_url":"https://github.com/bshall/UniversalVocoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"robust-universal-neural-vocoding","repo_url":"https://github.com/bshall/ZeroSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"robust-universal-neural-vocoding","repo_url":"https://github.com/howard1337/S2VC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"robust-universal-neural-vocoding","repo_url":"https://github.com/m-toman/tacorn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"robust-universal-neural-vocoding","repo_url":"https://github.com/yistLin/FragmentVC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"robust-universal-neural-vocoding","repo_url":"https://github.com/yistlin/universal-vocoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}