Journal of South China University of Technology (Natural Science Edition) ›› 2011, Vol. 39 ›› Issue (2): 20-25,31.doi: 10.3969/j.issn.1000-565X.2011.02.004

• Electronics, Communication & Automation Technology • Previous Articles     Next Articles

Two-Stage Decision-Based Detection of Non-Lexical Audio Events in Spontaneous Vocalization

He Qian-hua Li Yan-xiong Li Tao Zhang Hong Yang Ji-chen   

  1. South China university of technology, electronic and information institute, guangdong guangzhou 51064
  • Received:2010-04-16 Revised:2010-06-17 Online:2011-02-25 Published:2011-01-02
  • Contact: 贺前华(1965-)，男，教授，博士生导师，主要从事语音及音频信号处理、嵌入式系统研究 E-mail:eeqhhe@scut.edu.cn
  • About author:贺前华(1965-)，男，教授，博士生导师，主要从事语音及音频信号处理、嵌入式系统研究
  • Supported by:

    国家自然科学基金资助项目(60972132)；广东省自然科学基金资助项目(10451064101004651，9351064101000003)

PDF

1370

Abstract:

In order to effectively utilize non-lexical audio events to analyze the semantics of conversational speech,the characteristic differences among the audio events frequently occurring in spontaneous vocalization are analyzed,and a two-stage decision-based method to detect non-lexical audio events in spontaneous vocalization is proposed.In this method,the characteristics of audio events are used to construct signal segments of audio events： the thre-shold decision is used to detect longer applause（the first-stage decision）,and statistical models are employed to detect other audio events（the second-stage decision）.Experimental results show that the average precision,the recall rate and the F1-measure of the proposed method for three non-lexical audio events（i.e.filled pause,laughter and applause） are respectively 87.3%,93.8% and 90.4%;and that,as compared with the existing method,the proposed method is of an average F1-measure increase by 7.5% and it helps to determine the boundaries of non-lexical audio events with higher accuracy.

Key words: Non-lexical events, threshold decision, statistical model detection, spontaneous speech, speech processing