{"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-semisupervised-approach-for-language","title":"A Semisupervised Approach for Language Identification based on Ladder Networks","arxiv_id":"1604.00317","date":"2016-04-01","proceeding":null,"authors":["Ehud Ben-Reuven","Jacob Goldberger"],"abstract":"In this study we address the problem of training a neuralnetwork for language\nidentification using both labeled and unlabeled speech samples in the form of\ni-vectors. We propose a neural network architecture that can also handle\nout-of-set languages. We utilize a modified version of the recently proposed\nLadder Network semisupervised training procedure that optimizes the\nreconstruction costs of a stack of denoising autoencoders. We show that this\napproach can be successfully applied to the case where the training dataset is\ncomposed of both labeled and unlabeled acoustic data. The results show enhanced\nlanguage identification on the NIST 2015 language identification dataset.","url_abs":"http://arxiv.org/abs/1604.00317v1","url_pdf":"http://arxiv.org/pdf/1604.00317v1.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-semisupervised-approach-for-language","repo_url":"https://github.com/udibr/LRE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"language-identification","task_name":"Language Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}