{"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/speaker-anonymization-using-neural-audio","title":"Speaker anonymization using neural audio codec language models","arxiv_id":"2309.14129","date":"2023-09-25","proceeding":null,"authors":["Michele Panariello","Francesco Nespoli","Massimiliano Todisco","Nicholas Evans"],"abstract":"The vast majority of approaches to speaker anonymization involve the extraction of fundamental frequency estimates, linguistic features and a speaker embedding which is perturbed to obfuscate the speaker identity before an anonymized speech waveform is resynthesized using a vocoder. Recent work has shown that x-vector transformations are difficult to control consistently: other sources of speaker information contained within fundamental frequency and linguistic features are re-entangled upon vocoding, meaning that anonymized speech signals still contain speaker information. We propose an approach based upon neural audio codecs (NACs), which are known to generate high-quality synthetic speech when combined with language models. NACs use quantized codes, which are known to effectively bottleneck speaker-related information: we demonstrate the potential of speaker anonymization systems based on NAC language modeling by applying the evaluation framework of the Voice Privacy Challenge 2022.","url_abs":"https://arxiv.org/abs/2309.14129v3","url_pdf":"https://arxiv.org/pdf/2309.14129v3.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":"speaker-anonymization-using-neural-audio","repo_url":"https://github.com/eurecom-asp/spk_anon_nac_lm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"speaker-anonymization-using-neural-audio","repo_url":"https://github.com/m-pana/spk_anon_nac_lm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"speaker-anonymization-using-neural-audio","repo_url":"https://github.com/voice-privacy-challenge/voice-privacy-challenge-2024","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speaker-anonymization","task_name":"Speaker anonymization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}