{"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/leveraging-translations-for-speech","title":"Leveraging translations for speech transcription in low-resource settings","arxiv_id":"1803.08991","date":"2018-03-23","proceeding":null,"authors":["Antonis Anastasopoulos","David Chiang"],"abstract":"Recently proposed data collection frameworks for endangered language\ndocumentation aim not only to collect speech in the language of interest, but\nalso to collect translations into a high-resource language that will render the\ncollected resource interpretable. We focus on this scenario and explore whether\nwe can improve transcription quality under these extremely low-resource\nsettings with the assistance of text translations. We present a neural\nmulti-source model and evaluate several variations of it on three low-resource\ndatasets. We find that our multi-source model with shared attention outperforms\nthe baselines, reducing transcription character error rate by up to 12.3%.","url_abs":"http://arxiv.org/abs/1803.08991v2","url_pdf":"http://arxiv.org/pdf/1803.08991v2.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":"leveraging-translations-for-speech","repo_url":"https://bitbucket.org/antonis/dynet-multisource-models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1803.08991","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}