基于ARM7-TDMI内核和MSAC协处理器的语音识别SoC

2009 IEEE International SOC Conference (SOCC) Pub Date : 2009-09-01 DOI:10.1109/SOCCON.2009.5398052

H. Geng, Weiqian Liang, Ming Dong

{"title":"基于ARM7-TDMI内核和MSAC协处理器的语音识别SoC","authors":"H. Geng, Weiqian Liang, Ming Dong","doi":"10.1109/SOCCON.2009.5398052","DOIUrl":null,"url":null,"abstract":"Most of the present high-performance speech recognition systems are based on CHMM (Continuous Hidden Markov Model) algorithm, however, for embedded systems, it involves much computational cost. This paper solves this problem by proposing a SoC composed of ARM7TDMI, and a co-processor MSAC (Multiplier Square Accumulate Calculation) used to calculate the Mahalanobis distance. Testing with 358-state 3-mixture 27-feature HMM model on Actel ProASIC series FPGA M7A3P1000, the SoC at 24MHZ reaches 1.54 times real-time, and its power consumption is 0.56 mW/MHz.","PeriodicalId":303505,"journal":{"name":"2009 IEEE International SOC Conference (SOCC)","volume":"171 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"A speech recognition SoC based on ARM7-TDMI core and a MSAC co-processor\",\"authors\":\"H. Geng, Weiqian Liang, Ming Dong\",\"doi\":\"10.1109/SOCCON.2009.5398052\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Most of the present high-performance speech recognition systems are based on CHMM (Continuous Hidden Markov Model) algorithm, however, for embedded systems, it involves much computational cost. This paper solves this problem by proposing a SoC composed of ARM7TDMI, and a co-processor MSAC (Multiplier Square Accumulate Calculation) used to calculate the Mahalanobis distance. Testing with 358-state 3-mixture 27-feature HMM model on Actel ProASIC series FPGA M7A3P1000, the SoC at 24MHZ reaches 1.54 times real-time, and its power consumption is 0.56 mW/MHz.\",\"PeriodicalId\":303505,\"journal\":{\"name\":\"2009 IEEE International SOC Conference (SOCC)\",\"volume\":\"171 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2009-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2009 IEEE International SOC Conference (SOCC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SOCCON.2009.5398052\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 IEEE International SOC Conference (SOCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SOCCON.2009.5398052","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 4

摘要

目前大多数高性能语音识别系统都是基于连续隐马尔可夫模型(CHMM)算法，但对于嵌入式系统来说，该算法的计算量很大。为了解决这一问题，本文提出了一种由ARM7TDMI和一个用于计算马氏距离的协处理器MSAC (Multiplier Square Accumulate Calculation)组成的SoC。在Actel ProASIC系列FPGA M7A3P1000上对358状态3混合27特征HMM模型进行测试，SoC在24MHZ时实时性达到1.54倍，功耗为0.56 mW/MHz。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

A speech recognition SoC based on ARM7-TDMI core and a MSAC co-processor

Most of the present high-performance speech recognition systems are based on CHMM (Continuous Hidden Markov Model) algorithm, however, for embedded systems, it involves much computational cost. This paper solves this problem by proposing a SoC composed of ARM7TDMI, and a co-processor MSAC (Multiplier Square Accumulate Calculation) used to calculate the Mahalanobis distance. Testing with 358-state 3-mixture 27-feature HMM model on Actel ProASIC series FPGA M7A3P1000, the SoC at 24MHZ reaches 1.54 times real-time, and its power consumption is 0.56 mW/MHz.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2009 IEEE International SOC Conference (SOCC)

自引率

0.00%

发文量