{"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/javascript-convolutional-neural-networks-for","title":"JavaScript Convolutional Neural Networks for Keyword Spotting in the Browser: An Experimental Analysis","arxiv_id":"1810.12859","date":"2018-10-30","proceeding":null,"authors":["Jaejun Lee","Raphael Tang","Jimmy Lin"],"abstract":"Used for simple commands recognition on devices from smart routers to mobile\nphones, keyword spotting systems are everywhere. Ubiquitous as well are web\napplications, which have grown in popularity and complexity over the last\ndecade with significant improvements in usability under cross-platform\nconditions. However, despite their obvious advantage in natural language\ninteraction, voice-enabled web applications are still far and few between. In\nthis work, we attempt to bridge this gap by bringing keyword spotting\ncapabilities directly into the browser. To our knowledge, we are the first to\ndemonstrate a fully-functional implementation of convolutional neural networks\nin pure JavaScript that runs in any standards-compliant browser. We also apply\nnetwork slimming, a model compression technique, to explore the\naccuracy-efficiency tradeoffs, reporting latency measurements on a range of\ndevices and software. Overall, our robust, cross-device implementation for\nkeyword spotting realizes a new paradigm for serving neural network\napplications, and one of our slim models reduces latency by 66% with a minimal\ndecrease in accuracy of 4% from 94% to 90%.","url_abs":"http://arxiv.org/abs/1810.12859v1","url_pdf":"http://arxiv.org/pdf/1810.12859v1.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":"javascript-convolutional-neural-networks-for","repo_url":"https://github.com/castorini/honkling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"keyword-spotting","task_name":"Keyword Spotting"},{"task_slug":"model-compression","task_name":"Model Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}