作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2006, Vol. 32 ›› Issue (21): 197-199. doi: 10.3969/j.issn.1000-3428.2006.21.069

• 人工智能及识别技术 • 上一篇    下一篇

语音识别SoC UniLite的系统设计

杨之佐1,董 明1,刘 加1,刘润生1,孙旭东2   

  1. (1. 清华大学电子工程系,北京 100084;2. 中航一集团沈阳飞机设计研究所,沈阳 110035)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2006-11-05 发布日期:2006-11-05

System Design of Speech Recognition SoC UniLite

YANG Zhizuo1, DONG Ming1, LIU Jia1, LIU Runsheng1, SUN Xudong2   

  1. (1. Department of Electronic Engineering, Tsinghua University, Beijing 100084; 2. China Aviation Shenyang Aircraft Design & Research Institute, Shenyang 110035)
  • Received:1900-01-01 Revised:1900-01-01 Online:2006-11-05 Published:2006-11-05

摘要:

UniLite系统以DSP为核心,集成了片内存储器、AD/DA通道和多种的输入输出端口,有效控制了系统的成本和功耗,在有限的RAM空间上实现了高性能非特定人语音识别以及语音编解码的功能。系统采用连续隐含马尔科夫(CHMM)算法,运用了分阶段提取特征、束搜索等策略,在保证系统识别性能的同时大大降低了内存消耗,提高了识别速度,识别率在98.5%以上,识别时间在0.5倍实时 以下。

关键词: 嵌入式系统, 语音识别, DSP, SoC设计

Abstract: The UniLite chip is realized around an architecture which is composed of a 16-bit DSP core, on-chip memory, an ADC/DAC channel as well as other common I/O interfaces. High performance speaker independent speech recognition and speech coding are implemented on limited RAM memory. This results in low power consumption and reduction in cost. The system is based on continuous hidden Markov model. Two-pass feature extraction and beam search strategy are also employed to reduce the consumption of the RAM and enhance the recognition rate. Test shows that the UniLite system provides recognition accurate as high as 98.5% and requires less than 0.5 real time.

Key words: Embedded system, Speech recognition, DSP, SoC design

中图分类号: