Text Independent Classification of Normal and Pathological Voices Using MFCCs and GMM-UBM

被引:0
|
作者
Vikram, C. M. [1 ]
Umarani, K. [1 ]
机构
[1] SJCE, IT Dept, Mysore, Karnataka, India
来源
2013 IEEE CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES (ICT 2013) | 2013年
关键词
Gaussian mixture model (GMM); Mel-frequency cepstral coefficients(MFCCs); pathological voice detection; Universal background model(UBM); HEALTHY;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This paper proposes a text independent method for the classification of normal and pathological voices. If the classifier is text dependent i.e classifier is trained for a particular phoneme, then it may difficult for the patient to pronounce the particular phoneme. To overcome this difficulty, a text independent classification method is proposed, which uses Mel-Frequency Cepstral Coefficients (MFCCs) and Gaussian Mixture Model-Universal Background Model (GMM-UBM). The GMM-UBM model is trained with phonemes /a/, /e/,/u/ of normal and pathological voices. Hence the classifier is efficient to detect voices of different phonemes and classifies them into normal and pathological with a maximum accuracy of 85.63%. It has been noticed that, accuracy of classification can be improved by increasing the number of MFCCs, i.e the classification accuracy is 72.45% for 12 MFCCs, where as 85.63% for 24 MFCCs.
引用
收藏
页码:1215 / 1220
页数:6
相关论文
共 50 条
  • [11] TEXT-INDEPENDENT MFCCS VECTORS CLASSIFICATION IMPROVEMENT USING LOCAL ICA
    Rouigueb, A.
    Chitroub, S.
    Bouridane, A.
    2013 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2013,
  • [12] GMM-UBM based Person Verification using footfall signatures for Smart Home Applications
    Anchal, Sahil
    Mukhopadhyay, Bodhibrata
    Parvatini, Manohar
    Kar, Subrat
    2019 7TH IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (IEEE GLOBALSIP), 2019,
  • [13] Phoneme Independent Pathological Voice Detection Using Wavelet Based MFCCs, GMM-SVM Hybrid Classifier
    Vikram, C. M.
    Umarani, K.
    2013 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI), 2013, : 929 - 934
  • [14] Noise Robust Speaker Verification using GMM-UBM Multi-Condition Training
    Mekonnen, Bezawit Wubishet
    Dufera, Bisrat Derebssa
    PROCEEDINGS OF THE 2015 12TH IEEE AFRICON INTERNATIONAL CONFERENCE - GREEN INNOVATION FOR AFRICAN RENAISSANCE (AFRICON), 2015,
  • [15] Human Action Recognition based on GMM-UBM supervector using SVM with non-linear GMM KL and GUMI
    Bui, Nam N.
    Kim, Young J.
    SEVENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2015), 2015, 9631
  • [16] Discrimination Between Pathological and Normal Voices Using GMM-SVM Approach
    Wang, Xiang
    Zhang, Jianping
    Yan, Yonghong
    JOURNAL OF VOICE, 2011, 25 (01) : 38 - 43
  • [17] Speech Features Evaluation for Small Set Automatic Speaker Verification Using GMM-UBM System
    Rakhmanenko, Ivan
    Meshcheryakov, Roman
    SPEECH AND COMPUTER, 2016, 9811 : 645 - 650
  • [18] Combining selection tree with observation reordering pruning for efficient speaker identification using GMM-UBM
    Xiong, ZY
    Zheng, TF
    Song, ZJ
    Wu, WH
    2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 625 - 628
  • [19] Arabic Dialect Identification based on Motif Discovery Using GMM-UBM with Different Motif Lengths
    Moftah, Mohsen
    Fakhr, Mohammed Waleed
    El Ramly, Salwa
    2018 2ND INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE AND SPEECH PROCESSING (ICNLSP), 2018, : 177 - 182
  • [20] New transformed features generated by deep bottleneck extractor and a GMM-UBM classifier for speaker age and gender classification
    Abu Mallouh, Arafat
    Qawaqneh, Zakariya
    Barkana, Buket D.
    NEURAL COMPUTING & APPLICATIONS, 2018, 30 (08): : 2581 - 2593