{"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/parsing-speech-a-neural-approach-to","title":"Parsing Speech: A Neural Approach to Integrating Lexical and Acoustic-Prosodic Information","arxiv_id":"1704.07287","date":"2017-04-24","proceeding":"NAACL 2018 6","authors":["Trang Tran","Shubham Toshniwal","Mohit Bansal","Kevin Gimpel","Karen Livescu","Mari Ostendorf"],"abstract":"In conversational speech, the acoustic signal provides cues that help\nlisteners disambiguate difficult parses. For automatically parsing spoken\nutterances, we introduce a model that integrates transcribed text and\nacoustic-prosodic features using a convolutional neural network over energy and\npitch trajectories coupled with an attention-based recurrent neural network\nthat accepts text and prosodic features. We find that different types of\nacoustic-prosodic features are individually helpful, and together give\nstatistically significant improvements in parse and disfluency detection F1\nscores over a strong text-only baseline. For this study with known sentence\nboundaries, error analyses show that the main benefit of acoustic-prosodic\nfeatures is in sentences with disfluencies, attachment decisions are most\nimproved, and transcription errors obscure gains from prosody.","url_abs":"http://arxiv.org/abs/1704.07287v2","url_pdf":"http://arxiv.org/pdf/1704.07287v2.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":"parsing-speech-a-neural-approach-to","repo_url":"https://github.com/shtoshni92/speech_parsing","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.07287","atlas_url":"https://app.syntology.ai/?focus=1704.07287","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}