{"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/automatic-measurement-of-vowel-duration-via","title":"Automatic measurement of vowel duration via structured prediction","arxiv_id":"1610.08166","date":"2016-10-26","proceeding":null,"authors":["Yossi Adi","Joseph Keshet","Emily Cibelli","Erin Gustafson","Cynthia Clopper","Matthew Goldrick"],"abstract":"A key barrier to making phonetic studies scalable and replicable is the need\nto rely on subjective, manual annotation. To help meet this challenge, a\nmachine learning algorithm was developed for automatic measurement of a widely\nused phonetic measure: vowel duration. Manually-annotated data were used to\ntrain a model that takes as input an arbitrary length segment of the acoustic\nsignal containing a single vowel that is preceded and followed by consonants\nand outputs the duration of the vowel. The model is based on the structured\nprediction framework. The input signal and a hypothesized set of a vowel's\nonset and offset are mapped to an abstract vector space by a set of acoustic\nfeature functions. The learning algorithm is trained in this space to minimize\nthe difference in expectations between predicted and manually-measured vowel\ndurations. The trained model can then automatically estimate vowel durations\nwithout phonetic or orthographic transcription. Results comparing the model to\nthree sets of manually annotated data suggest it out-performed the current gold\nstandard for duration measurement, an HMM-based forced aligner (which requires\northographic or phonetic transcription as an input).","url_abs":"http://arxiv.org/abs/1610.08166v1","url_pdf":"http://arxiv.org/pdf/1610.08166v1.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":"automatic-measurement-of-vowel-duration-via","repo_url":"https://github.com/adiyoss/AutoVowelDuration","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}