›› 2012, Vol. ›› Issue (03): 771-775.

• 论文 • 上一篇    下一篇

基于动态点阵匹配算法的二阶关键词识别

刘晓明, 冯晓荣, 班超帆   

  1. 重庆大学 通信工程学院, 重庆 400030
  • 收稿日期:2011-01-11 出版日期:2012-05-01
  • 通讯作者: 冯晓荣(1987-),女,硕士研究生.研究方向:信号与信息处理,语音编码,语音信号识别. E-mail:fxrsmile@163.com E-mail:fxrsmile@163.com
  • 基金资助:
    国家自然科学基金项目(51035008).

Dynamic match phone-lattice algorithm for second order keyword spotting

LIU Xiao-ming, FENG Xiao-rong, BAN Chao-fan   

  1. School of Telecommunication Engineering, Chongqing University, Chongqing 400030, China
  • Received:2011-01-11 Online:2012-05-01

摘要: 为了避免关键词权值估计错误,提出了基于上下文相关最大后验概率准则(CDMAP)的改进二阶KWS模型,有效地解决了关键词权值对参数估计的负面影响。同时,采用动态点阵匹配算法(DMPLS)进行错误补偿,解决了由连续语音识别器产生的插入、删除和替换错误而导致识别准确率下降的问题,提高了系统的检出率和鲁棒性。实验结果表明,该模型不仅在较低误警率的条件下检出率得到很大的改善,而且系统鲁棒性也有明显的增强。

关键词: 通信技术, 关键词权值, 动态点阵匹配, 关键词检出

Abstract: In order to solve the problem of estimation error of keyword weight, an improved model of second KWS is proposed. This model is based on the Context-Dependent Maximum a Posteriori Probability (CDMAP) method. Meanwhile, a dynamic match phone-lattice algorithm is introduced. This algorithm can efficiently solve the problem of inherent phone recognition error, which adversely affects the recognition accuracy. Experiment results show that the system performance is greatly enhanced by the dynamic match phone-lattice algorithm for both robustness and detection accuracy.

Key words: communication, keyword weighting, dynamic match phone-lattice, keyword detection

中图分类号: 

  • TN912.34
[1] 刘柏森,卢志茂,申丽然,等.基于希尔伯特-黄变换的低信噪比语音端点检测[J]. 吉林大学学报:工学版,2011,41(3):844-848. Liu Bai-sen, Lu Zhi-mao Shen Li-ran,et al. Speech endpoint detection based on Hilbert transformation[J]. Journal of Jilin University(Engineering and Technology Edition), 2011,41(3):844-848.
[2] Zhang G L,Sun H,Zheng F,et al. Robust speech recognition directed by extended template matching in dialogue system[C]//The 5th World Congress on Intelligent Control and Automation(WClCA), Hangzhou, China,2004:14-18.
[3] Leida E, Rose R. Utterance verification in continuous speech recognition: Decoding and training procedures[J]. IEEE Trans on Speech and Audio Processing, 2000,8(2):126-139.
[4] 张鹏远, 韩疆, 颜永红. 关键词检测系统中基于音素网格的置信度计算[J].电子与信息学报,2007,29(9):2063-2066. Zhang Peng-yuan, Han Jiang, Yan Yong-hong. Phoneme lattice based confidence measures in keyword spotting[J]. Journal of Electronics & Information Technology,2007,29(9):2063-2066.
[5] Zheng T F,Li J,Song Z J,et al. A two-step keyword spotting method based on context-dependent a posteriori probability[C]//2004 International Symposium on Chinese Spoken Language, 2004:281-284.
[6] Luqman M M, Delalandre M, Brouard T, et al. Employing fuzzy intervals and loop-based methodology for designing structural signature: an application to symbol recognition[C]//Lecture Notes in Computer Science,2009:22-31.
[7] Yu P, Chen K J, Ma C Y, et al. Vocabulary-independent indexing of spontaneous speech[J]. IEEE Transaction on Speech and Audio Processing, 2009,13(5):635-643.
[8] Abdou S, Scordilis M. Beam search pruning in speech recognition using a posterior probability-based confidence measure[J]. Speech Communication, 2004,42(3):409-428.
[9] Thambiratnam K, Sridharan S. Dynamic match phone-lattice searches for very fast and accurate unrestricted vocabulary keyword spotting[C]//IEEE International Conference on Acoustics, Speech, and Signal Processing,2005:465-468.
[10] Pinto J, Yegnanarayana B, Hermansky H, et al. Exploiting contextual information for improved phoneme recognition[C]//In Proc IEEE Conf Acoust, Speech, Signal Process, Las Vegas, NV,2008:4449-4452.
[1] 周彦果,张海林,陈瑞瑞,周韬. 协作网络中采用双层博弈的资源分配方案[J]. 吉林大学学报(工学版), 2018, 48(6): 1879-1886.
[2] 孙晓颖, 扈泽正, 杨锦鹏. 基于分层贝叶斯网络的车辆发动机系统电磁脉冲敏感度评估[J]. 吉林大学学报(工学版), 2018, 48(4): 1254-1264.
[3] 董颖, 崔梦瑶, 吴昊, 王雨后. 基于能量预测的分簇可充电无线传感器网络充电调度[J]. 吉林大学学报(工学版), 2018, 48(4): 1265-1273.
[4] 牟宗磊, 宋萍, 翟亚宇, 陈晓笑. 分布式测试系统同步触发脉冲传输时延的高精度测量方法[J]. 吉林大学学报(工学版), 2018, 48(4): 1274-1281.
[5] 丁宁, 常玉春, 赵健博, 王超, 杨小天. 基于USB 3.0的高速CMOS图像传感器数据采集系统[J]. 吉林大学学报(工学版), 2018, 48(4): 1298-1304.
[6] 陈瑞瑞, 张海林. 三维毫米波通信系统的性能分析[J]. 吉林大学学报(工学版), 2018, 48(2): 605-609.
[7] 张超逸, 李金海, 阎跃鹏. 双门限唐检测改进算法[J]. 吉林大学学报(工学版), 2018, 48(2): 610-617.
[8] 关济实, 石要武, 邱建文, 单泽彪, 史红伟. α稳定分布特征指数估计算法[J]. 吉林大学学报(工学版), 2018, 48(2): 618-624.
[9] 李炜, 李亚洁. 基于离散事件触发通信机制的非均匀传输网络化控制系统故障调节与通信满意协同设计[J]. 吉林大学学报(工学版), 2018, 48(1): 245-258.
[10] 孙晓颖, 王震, 杨锦鹏, 扈泽正, 陈建. 基于贝叶斯网络的电子节气门电磁敏感度评估[J]. 吉林大学学报(工学版), 2018, 48(1): 281-289.
[11] 武伟, 王世刚, 赵岩, 韦健, 钟诚. 蜂窝式立体元图像阵列的生成[J]. 吉林大学学报(工学版), 2018, 48(1): 290-294.
[12] 袁建国, 张锡若, 邱飘玉, 王永, 庞宇, 林金朝. OFDM系统中利用循环前缀的非迭代相位噪声抑制算法[J]. 吉林大学学报(工学版), 2018, 48(1): 295-300.
[13] 王金鹏, 曹帆, 贺晓阳, 邹念育. 基于多址干扰和蜂窝间互扰分布的多载波系统联合接收方法[J]. 吉林大学学报(工学版), 2018, 48(1): 301-305.
[14] 石文孝, 孙浩然, 王少博. 无线Mesh网络信道分配与路由度量联合优化算法[J]. 吉林大学学报(工学版), 2017, 47(6): 1918-1925.
[15] 姜来为, 沙学军, 吴宣利, 张乃通. LTE-A异构网络中新的用户选择接入和资源分配联合方法[J]. 吉林大学学报(工学版), 2017, 47(6): 1926-1932.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!