{"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/a-variance-modeling-framework-based-on","title":"A variance modeling framework based on variational autoencoders for speech enhancement","arxiv_id":"1902.01605","date":"2019-02-05","proceeding":null,"authors":["Simon Leglaive","Laurent Girin","Radu Horaud"],"abstract":"In this paper we address the problem of enhancing speech signals in noisy\nmixtures using a source separation approach. We explore the use of neural\nnetworks as an alternative to a popular speech variance model based on\nsupervised non-negative matrix factorization (NMF). More precisely, we use a\nvariational autoencoder as a speaker-independent supervised generative speech\nmodel, highlighting the conceptual similarities that this approach shares with\nits NMF-based counterpart. In order to be free of generalization issues\nregarding the noisy recording environments, we follow the approach of having a\nsupervised model only for the target speech signal, the noise model being based\non unsupervised NMF. We develop a Monte Carlo expectation-maximization\nalgorithm for inferring the latent variables in the variational autoencoder and\nestimating the unsupervised model parameters. Experiments show that the\nproposed method outperforms a semi-supervised NMF baseline and a\nstate-of-the-art fully supervised deep learning approach.","url_abs":"http://arxiv.org/abs/1902.01605v1","url_pdf":"http://arxiv.org/pdf/1902.01605v1.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":"a-variance-modeling-framework-based-on","repo_url":"https://github.com/sleglaive/MLSP-2018","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}