A robust speech endpoint detection algorithm based on wavelet packet and energy entropy

The robust speech endpoint detection is important in many areas of speech processing. In this work, a robust speech endpoint detection algorithm is proposed based on wavelet packet and energy entropy. The proposed method is tested using speech utterances under four different background noise: White, Pink, Babble and Volvo with different SNR (-5db, 0db, 10db, 20db). The results are compared with traditional short-time energy plus short-time zero crossing rate method. The experiment results indicate that the presented algorithm achieve higher endpoint detection accuracies than traditional method. The correct detection rates reach up to 97.5% for noise-free speech, and range from 80.72% to 93.87% according to different types of background noise.

[1]  Runzhi Li,et al.  Neighboring Digits Pattern Training Method in Quickly-spoken Connected Mandarin Digits Speech Recognition , 2011, J. Multim..

[2]  Jennifer Golbeck,et al.  Generating Predictive Movie Recommendations from Trust in Social Networks , 2006, iTrust.

[3]  Farshad Almasganj,et al.  Speech/non-speech segments detection based on chaotic and prosodic features , 2008, INTERSPEECH.

[4]  Cheng Xu,et al.  An Improved Speech Enhancement Method based on Teager Energy Operator and Perceptual Wavelet Packet Decomposition , 2011, J. Multim..

[5]  Alfred Mertins,et al.  Automatic speech recognition and speech variability: A review , 2007, Speech Commun..

[6]  Xiaoguang Hu,et al.  An intelligent fault diagnosis method of high voltage circuit breaker based on improved EMD energy entropy and multi-class support vector machine , 2011 .

[7]  Muhammad Ghulam,et al.  Effects of Syllable Language Model on Distinctive Phonetic Features (DPFs) based Phoneme Recognition Performance , 2010, J. Multim..

[8]  Wang Biao.  An improved speech endpoint detection method research , 2012 .

[9]  Diego H. Milone,et al.  Genetic wavelet packets for speech recognition , 2013, Expert Syst. Appl..

[10]  Yu Yang,et al.  A Novel Robust Zero-Watermarking Scheme Based on Discrete Wavelet Transform , 2012, J. Multim..

[11]  Rubo Zhang,et al.  Speech-stream detection with low signal-to-noise ratios based on empirical mode decomposition and fourth-order statistics , 2007, Second International Multi-Symposiums on Computer and Computational Sciences (IMSCCS 2007).

[12]  Weiqiang Zhang,et al.  Time-Frequency Cepstral Features and Combining Discriminative Training for Phonotactic Language Recognition , 2011, J. Comput..

[13]  Hong Hao,et al.  Experimental study on subsea pipeline bedding condition assessment using wavelet packet transform , 2013 .

[14]  M. Bilginer Gülmezoglu,et al.  The common vector approach and its comparison with other subspace methods in case of sufficient data , 2007, Comput. Speech Lang..

[15]  Jennifer Golbeck,et al.  Investigating interactions of trust and interest similarity , 2007, Decis. Support Syst..

[16]  Pan Rong,et al.  Optimum selection algorithm of Web information reconstruction model and its improvement , 2009 .

[17]  Zhen Ren,et al.  Power quality disturbance identification using wavelet packet energy entropy and weighted support vector machines , 2008, Expert Syst. Appl..

[18]  Chia-Hsiang Chen,et al.  Robust voice activity detection algorithm based on the perceptual wavelet packet transform , 2005, 2005 International Symposium on Intelligent Signal Processing and Communication Systems.

[19]  Chia-Feng Juang,et al.  Speech detection in noisy environments by wavelet energy-based recurrent neural fuzzy network , 2009, Expert Syst. Appl..

[20]  Biswaranjan Behera.  Wavelet packets associated with nonuniform multiresolution analyses , 2007 .

[21]  Gong Zheng-hu,et al.  Two New Hybrid-type Data Dissemination Algorithms forLarge-Scale Wireless Sensor Networks , 2007 .

[22]  Hu Guangshu,et al.  An Incremental Support Vector Machine based Speech Activity Detection Algorithm , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[23]  Francesco Beritelli,et al.  Adaptive V/UV speech detection based on acoustic noise estimation and classification , 2007 .