Literature DB >> 35399790

Continuous Speech for Improved Learning Pathological Voice Disorders.

Syu-Siang Wang1, Chi-Te Wang1,2, Chih-Chung Lai1, Yu Tsao3, Shih-Hau Fang1.   

Abstract

Goal: Numerous studies had successfully differentiated normal and abnormal voice samples. Nevertheless, further classification had rarely been attempted. This study proposes a novel approach, using continuous Mandarin speech instead of a single vowel, to classify four common voice disorders (i.e. functional dysphonia, neoplasm, phonotrauma, and vocal palsy).
Methods: In the proposed framework, acoustic signals are transformed into mel-frequency cepstral coefficients, and a bi-directional long-short term memory network (BiLSTM) is adopted to model the sequential features. The experiments were conducted on a large-scale database, wherein 1,045 continuous speech were collected by the speech clinic of a hospital from 2012 to 2019.
Results: Experimental results demonstrated that the proposed framework yields significant accuracy and unweighted average recall improvements of 78.12-89.27% and 50.92-80.68%, respectively, compared with systems that use a single vowel. Conclusions: The results are consistent with other machine learning algorithms, including gated recurrent units, random forest, deep neural networks, and LSTM.The sensitivities for each disorder were also analyzed, and the model capabilities were visualized via principal component analysis. An alternative experiment based on a balanced dataset again confirms the advantages of using continuous speech for learning voice disorders.

Entities:  

Keywords:  Acoustic signal; artificial intelligence; diseases classification; pathological voice

Year:  2022        PMID: 35399790      PMCID: PMC8940190          DOI: 10.1109/OJEMB.2022.3151233

Source DB:  PubMed          Journal:  IEEE Open J Eng Med Biol        ISSN: 2644-1276


  14 in total

1.  Automatic Voice Pathology Detection With Running Speech by Using Estimation of Auditory Spectrum and Cepstral Coefficients Based on the All-Pole Model.

Authors:  Zulfiqar Ali; Irraivan Elamvazuthi; Mansour Alsulaiman; Ghulam Muhammad
Journal:  J Voice       Date:  2015-10-27       Impact factor: 2.009

2.  Using modulation spectra for voice pathology detection and classification.

Authors:  Maria Markaki; Yannis Stylianou
Journal:  Conf Proc IEEE Eng Med Biol Soc       Date:  2009

3.  Automatic detection of pathological voices using complexity measures, noise parameters, and mel-cepstral coefficients.

Authors:  Julián D Arias-Londoño; Juan I Godino-Llorente; Nicolás Sáenz-Lechón; Víctor Osma-Ruiz; Germán Castellanos-Domínguez
Journal:  IEEE Trans Biomed Eng       Date:  2011-02       Impact factor: 4.538

4.  Investigation of Voice Pathology Detection and Classification on Different Frequency Regions Using Correlation Functions.

Authors:  Ahmed Al-Nasheri; Ghulam Muhammad; Mansour Alsulaiman; Zulfiqar Ali
Journal:  J Voice       Date:  2016-03-15       Impact factor: 2.009

5.  Detection of Pathological Voice Using Cepstrum Vectors: A Deep Learning Approach.

Authors:  Shih-Hau Fang; Yu Tsao; Min-Jing Hsiao; Ji-Ying Chen; Ying-Hui Lai; Feng-Chuan Lin; Chi-Te Wang
Journal:  J Voice       Date:  2018-03-19       Impact factor: 2.009

6.  A Mandarin Chinese Reading Passage for Eliciting Significant Vocal Range Variations.

Authors:  You-Zhen Yen; Chia-Hsin Wu; Roger W Chan
Journal:  J Speech Lang Hear Res       Date:  2021-04-05       Impact factor: 2.297

7.  Discrimination of "hot potato voice" caused by upper airway obstruction utilizing a support vector machine.

Authors:  Shintaro Fujimura; Tsuyoshi Kojima; Yusuke Okanoue; Kazuhiko Shoji; Masato Inoue; Ryusuke Hori
Journal:  Laryngoscope       Date:  2018-11-28       Impact factor: 3.325

8.  Prevalence of voice disorders in teachers and the general population.

Authors:  Nelson Roy; Ray M Merrill; Susan Thibeault; Rahul A Parsa; Steven D Gray; Elaine M Smith
Journal:  J Speech Lang Hear Res       Date:  2004-04       Impact factor: 2.297

9.  Demographic and Symptomatic Features of Voice Disorders and Their Potential Application in Classification Using Machine Learning Algorithms.

Authors:  Sheng-Yang Tsui; Yu Tsao; Chii-Wann Lin; Shih-Hau Fang; Feng-Chuan Lin; Chi-Te Wang
Journal:  Folia Phoniatr Logop       Date:  2018-09-05       Impact factor: 0.849

10.  Development of the Arabic Voice Pathology Database and Its Evaluation by Using Speech Features and Machine Learning Algorithms.

Authors:  Tamer A Mesallam; Mohamed Farahat; Khalid H Malki; Mansour Alsulaiman; Zulfiqar Ali; Ahmed Al-Nasheri; Ghulam Muhammad
Journal:  J Healthc Eng       Date:  2017-10-19       Impact factor: 2.682

View more
  1 in total

1.  Using SincNet for Learning Pathological Voice Disorders.

Authors:  Chao-Hsiang Hung; Syu-Siang Wang; Chi-Te Wang; Shih-Hau Fang
Journal:  Sensors (Basel)       Date:  2022-09-02       Impact factor: 3.847

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.