{"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/deep-xi-as-a-front-end-for-robust-automatic","title":"Deep Xi as a Front-End for Robust Automatic Speech Recognition","arxiv_id":"1906.07319","date":"2020-01-28","proceeding":null,"authors":[],"abstract":"Current front-ends for robust automatic speech recognition(ASR) include\nmasking- and mapping-based deep learning approaches to speech enhancement. A\nrecently proposed deep learning approach toa prioriSNR estimation, called\nDeepXi, was able to produce enhanced speech at a higher quality and\nintelligibility than current masking- and mapping-based approaches. Motivated\nby this, we investigate Deep Xi as a front-end for robust ASR. Deep Xi is\nevaluated using real-world non-stationary and coloured noise sources at\nmultiple SNR levels. Our experimental investigation shows that DeepXi as a\nfront-end is able to produce a lower word error rate than recent masking- and\nmapping-based deep learning front-ends. The results presented in this work show\nthat Deep Xi is a viable front-end, and is able to significantly increase the\nrobustness of an ASR system. Availability: Deep Xi is available\nat:https://github.com/anicolson/DeepXi","url_abs":"http://arxiv.org/abs/1906.07319v2","url_pdf":"http://arxiv.org/pdf/1906.07319v2.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":"deep-xi-as-a-front-end-for-robust-automatic","repo_url":"https://github.com/anicolson/DeepXi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MPL-2.0"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}