Detection of Pathological Voice Using Cepstrum Vectors: A Deep Learning Approach.
Computerized detection of voice disorders has attracted considerable academic and clinical interest in the hope of providing an effective screening method for voice diseases before endoscopic confirmation. This study proposes a deep-learning-based approach to detect pathological voice and examines i...
| Publicado en: | Journal of Voice Vol. 33; no. 5; pp. 634 - 642 |
|---|---|
| Autores principales: | , , , , , , |
| Formato: | equations & formulas research tables/charts Journal Article |
| Publicado: |
Elsevier B.V.
Sep2019
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=138691894&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 138691894 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 08921997 H24 jtl: Journal of Voice issn: 08921997 maglogo: N pubinfo: dt: Sep2019 vid: 33 iid: 5 pid: 467 pub: Elsevier B.V. place: New York, New York artinfo: ui: 138691894 138691894 138691894 10.1016/j.jvoice.2018.02.003 138691894 ppf: 634 ppct: 8 formats: tig: atl: Detection of Pathological Voice Using Cepstrum Vectors: A Deep Learning Approach. aug: au: Fang, Shih-Hau Tsao, Yu Hsiao, Min-Jing Chen, Ji-Ying Lai, Ying-Hui Lin, Feng-Chuan Wang, Chi-Te affil: Department of Electric Engineering, Yuan Ze University, Taoyuan, Taiwan sug: subj: Voice Disorders Diagnosis Tertiary Health Care Human Retrospective Design Academic Medical Centers Machine Learning Algorithms Neural Networks (Computer) Massachusetts Male Female Validity Pilot Studies Male Female ab: Computerized detection of voice disorders has attracted considerable academic and clinical interest in the hope of providing an effective screening method for voice diseases before endoscopic confirmation. This study proposes a deep-learning-based approach to detect pathological voice and examines its performance and utility compared with other automatic classification algorithms. This study retrospectively collected 60 normal voice samples and 402 pathological voice samples of 8 common clinical voice disorders in a voice clinic of a tertiary teaching hospital. We extracted Mel frequency cepstral coefficients from 3-second samples of a sustained vowel. The performances of three machine learning algorithms, namely, deep neural network (DNN), support vector machine, and Gaussian mixture model, were evaluated based on a fivefold cross-validation. Collective cases from the voice disorder database of MEEI (Massachusetts Eye and Ear Infirmary) were used to verify the performance of the classification mechanisms. The experimental results demonstrated that DNN outperforms Gaussian mixture model and support vector machine. Its accuracy in detecting voice pathologies reached 94.26% and 90.52% in male and female subjects, based on three representative Mel frequency cepstral coefficient features. When applied to the MEEI database for validation, the DNN also achieved a higher accuracy (99.32%) than the other two classification algorithms. By stacking several layers of neurons with optimized weights, the proposed DNN algorithm can fully utilize the acoustic features and efficiently differentiate between normal and pathological voice samples. Based on this pilot study, future research may proceed to explore more application of DNN from laboratory and clinical perspectives. pubtype: Academic Journal doctype: equations & formulas research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|