{"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/an-unsupervised-probability-model-for-speech","title":"An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages","arxiv_id":"1609.08139","date":"2016-09-26","proceeding":"EMNLP 2016 11","authors":["Antonios Anastasopoulos","David Chiang","Long Duong"],"abstract":"For many low-resource languages, spoken language resources are more likely to\nbe annotated with translations than with transcriptions. Translated speech data\nis potentially valuable for documenting endangered languages or for training\nspeech translation systems. A first step towards making use of such data would\nbe to automatically align spoken words with their translations. We present a\nmodel that combines Dyer et al.'s reparameterization of IBM Model 2\n(fast-align) and k-means clustering using Dynamic Time Warping as a distance\nmetric. The two components are trained jointly using expectation-maximization.\nIn an extremely low-resource scenario, our model performs significantly better\nthan both a neural model and a strong baseline.","url_abs":"http://arxiv.org/abs/1609.08139v1","url_pdf":"http://arxiv.org/pdf/1609.08139v1.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":"an-unsupervised-probability-model-for-speech","repo_url":"https://bitbucket.org/ndnlp/speech2translation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"dynamic-time-warping","task_name":"Dynamic Time Warping"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"k-means-clustering","method_name":"k-Means Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1609.08139","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}