{"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/achieving-timestamp-prediction-while","title":"Achieving Timestamp Prediction While Recognizing with Non-Autoregressive End-to-End ASR Model","arxiv_id":"2301.12343","date":"2023-01-29","proceeding":null,"authors":["Xian Shi","Yanni Chen","Shiliang Zhang","Zhijie Yan"],"abstract":"Conventional ASR systems use frame-level phoneme posterior to conduct force-alignment~(FA) and provide timestamps, while end-to-end ASR systems especially AED based ones are short of such ability. This paper proposes to perform timestamp prediction~(TP) while recognizing by utilizing continuous integrate-and-fire~(CIF) mechanism in non-autoregressive ASR model - Paraformer. Foucing on the fire place bias issue of CIF, we conduct post-processing strategies including fire-delay and silence insertion. Besides, we propose to use scaled-CIF to smooth the weights of CIF output, which is proved beneficial for both ASR and TP task. Accumulated averaging shift~(AAS) and diarization error rate~(DER) are adopted to measure the quality of timestamps and we compare these metrics of proposed system and conventional hybrid force-alignment system. The experiment results over manually-marked timestamps testset show that the proposed optimization methods significantly improve the accuracy of CIF timestamps, reducing 66.7\\% and 82.1\\% of AAS and DER respectively. Comparing to Kaldi force-alignment trained with the same data, optimized CIF timestamps achieved 12.3\\% relative AAS reduction.","url_abs":"https://arxiv.org/abs/2301.12343v1","url_pdf":"https://arxiv.org/pdf/2301.12343v1.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":"achieving-timestamp-prediction-while","repo_url":"https://github.com/alibaba-damo-academy/FunASR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.12343","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}