{"title":"片上英语语音识别系统*","authors":"Liu Hong (刘鸿), Qian Yanmin (钱彦旻), Liu Jia (刘加)","doi":"10.1016/S1007-0214(11)70015-3","DOIUrl":null,"url":null,"abstract":"<div><p>An English speech recognition system was implemented on a chip, called speech system-on-chip (SoC). The SoC included an application specific integrated circuit with a vector accelerator to improve performance. The sub-word model based on a continuous density hidden Markov model recognition algorithm ran on a very cheap speech chip. The algorithm was a two-stage fixed-width beam-search baseline system with a variable beam-width pruning strategy and a frame-synchronous word-level pruning strategy to significantly reduce the recognition time. Tests show that this method reduces the recognition time nearly 6 fold and the memory size nearly 2 fold compared to the original system, with less than 1% accuracy degradation for a 600 word recognition task and recognition accuracy rate of about 98%.</p></div>","PeriodicalId":60306,"journal":{"name":"Tsinghua Science and Technology","volume":null,"pages":null},"PeriodicalIF":5.2000,"publicationDate":"2011-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S1007-0214(11)70015-3","citationCount":"8","resultStr":"{\"title\":\"English Speech Recognition System on Chip*\",\"authors\":\"Liu Hong (刘鸿), Qian Yanmin (钱彦旻), Liu Jia (刘加)\",\"doi\":\"10.1016/S1007-0214(11)70015-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>An English speech recognition system was implemented on a chip, called speech system-on-chip (SoC). The SoC included an application specific integrated circuit with a vector accelerator to improve performance. The sub-word model based on a continuous density hidden Markov model recognition algorithm ran on a very cheap speech chip. The algorithm was a two-stage fixed-width beam-search baseline system with a variable beam-width pruning strategy and a frame-synchronous word-level pruning strategy to significantly reduce the recognition time. Tests show that this method reduces the recognition time nearly 6 fold and the memory size nearly 2 fold compared to the original system, with less than 1% accuracy degradation for a 600 word recognition task and recognition accuracy rate of about 98%.</p></div>\",\"PeriodicalId\":60306,\"journal\":{\"name\":\"Tsinghua Science and Technology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.2000,\"publicationDate\":\"2011-02-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1016/S1007-0214(11)70015-3\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Tsinghua Science and Technology\",\"FirstCategoryId\":\"1093\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1007021411700153\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tsinghua Science and Technology","FirstCategoryId":"1093","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1007021411700153","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
An English speech recognition system was implemented on a chip, called speech system-on-chip (SoC). The SoC included an application specific integrated circuit with a vector accelerator to improve performance. The sub-word model based on a continuous density hidden Markov model recognition algorithm ran on a very cheap speech chip. The algorithm was a two-stage fixed-width beam-search baseline system with a variable beam-width pruning strategy and a frame-synchronous word-level pruning strategy to significantly reduce the recognition time. Tests show that this method reduces the recognition time nearly 6 fold and the memory size nearly 2 fold compared to the original system, with less than 1% accuracy degradation for a 600 word recognition task and recognition accuracy rate of about 98%.