Characteristics-based effective applause detection for meeting speech

• Published in: Signal processing 2009-08, Vol.89 (8), p.1625-1633
• Main Authors: Li, Yan-Xiong, He, Qian-Hua, Kwong, Sam, Li, Tao, Yang, Ji-Chen
• Format: Article
• Language: English
• Subjects: Algorithms; Applause characteristics; Applause detection; Applied sciences; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; Inference; Information theory; Information, signal and communications theory; Mathematical models; Meeting speech; Meetings; Recall; Segments; Signal and communications theory; Signal processing; Signal representation. Spectral analysis; Signal, noise; Speech; Speech processing; Spontaneous speech recognition; Streams; Telecommunications and information theory
• ISSN: 0165-1684; 1872-7557
• DOI: 10.1016/j.sigpro.2009.03.001

Applause frequently occurs in multi-participants meeting speech. In fact, detecting applause is quite important for meeting speech recognition, semantic inference, highlight extraction, etc. In this paper, we will first study the characteristic differences between applause and speech, such as duration, pitch, spectrogram and occurrence locations. Then, an effective algorithm based on these characteristics is proposed for detecting applause in meeting speech stream. In the algorithm, the non-silence signal segments are first extracted by using voice activity detection. Afterward, applause segments are detected from the non-silence signal segments based on the characteristic differences between applause and speech without using any complex statistical models, such as hidden Markov models. The proposed algorithm can accurately determine the boundaries of applause in meeting speech stream, and is also computationally efficient. In addition, it can extract applause sub-segments from the mixed segments. Experimental evaluations show that the proposed algorithm can achieve satisfactory results in detecting applause of the meeting speech. Precision rate, recall rate, and F1-measure are 94.34%, 98.04%, and 96.15%, respectively. When compared with the traditional algorithm under the same experimental conditions, 3.62% improvement in F1-measure is achieved, and about 35.78% of computational time is saved.