기식성 음성 장애 환자들의 음향학적 특성과 분류 변인(결절, 용종환자를 중심으로)
Acoustic characteristics and classification variables of patients with Breathy Voice
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Incomplete phonation of vocal cords seems to cause breathy voice. Vocal nodules and vocal polyps are typical functional speech disorders. This study aimed to find the acoustic parameters useful for discriminating these two groups. In this study, 56 subjects diagnosed with speech disorders (27 vocal nodules, 29 vocal polyps) were recruited, and the MDVP (Multidimensional Voice Program) played within CSL (Computerized Speech Lab. Kay Elemetrics Co., Model No. 4300) was used for recording sustained vowel /a/. Praat (ver. 6.0.48) was used for acoustic analysis. Mann-Whitney U test showed that the MDVP parameters (excluding frequency-relevant variables) had no effect on discriminating two groups (vocal nodules vs. vocal polyps). However, when it comes to the cepstral parameters measured by Praat, there was statistically significant differences between groups: RNR (p<.o5), cepsPeak (p<.o5), quefrency (p<.o5), and CPP(p) <.o5) and cepslntercept (p<.o5). With respect to the relative rank of variable importance, quefrency has the highest rank, and cepslntercept and CPP followed in order. As a result of classification by the logistic regression model using these three variables, the overall classification accuracy for the training data was 81.4%, 94.4% for the vocal nodule group, and 68.4% for the vocal polyp group. In test data, nodules were 100% and vocal fold polyps were 30%. Although the overall classification accuracy was 65%, the classification accuracy of the polyps was too low, making it difficult to trust the model. In the case of the svm (support vector machine) model, the overall classification ratio of the training data was 94.6% (nodules (17/18)=94.4%, polyps (18/19)=94.7%). The overall classification accuracy of the test data was found to be 68.4% (nodule (6/9) = 66.7%. Polyp (7/10) = 70%).). It was found that, therefore, the performance of the svm was higher and more stable.
Abstract
Incomplete phonation of vocal cords seems to cause breathy voice. Vocal nodules and vocal polyps are typical functional speech disorders. This study aimed to find the acoustic parameters useful for discriminating these two groups. In this study, 56 subjects diagnosed with speech disorders (27 vocal nodules, 29 vocal polyps) were recruited, and the MDVP (Multidimensional Voice Program) played within CSL (Computerized Speech Lab. Kay Elemetrics Co., Model No. 4300) was used for recording sustained vowel /a/. Praat (ver. 6.0.48) was used for acoustic analysis. Mann-Whitney U test showed that the MDVP parameters (excluding frequency-relevant variables) had no effect on discriminating two groups (vocal nodules vs. vocal polyps). However, when it comes to the cepstral parameters measured by Praat, there was statistically significant differences between groups: RNR (p<.o5), cepsPeak (p<.o5), quefrency (p<.o5), and CPP(p) <.o5) and cepslntercept (p<.o5). With respect to the relative rank of variable importance, quefrency has the highest rank, and cepslntercept and CPP followed in order. As a result of classification by the logistic regression model using these three variables, the overall classification accuracy for the training data was 81.4%, 94.4% for the vocal nodule group, and 68.4% for the vocal polyp group. In test data, nodules were 100% and vocal fold polyps were 30%. Although the overall classification accuracy was 65%, the classification accuracy of the polyps was too low, making it difficult to trust the model. In the case of the svm (support vector machine) model, the overall classification ratio of the training data was 94.6% (nodules (17/18)=94.4%, polyps (18/19)=94.7%). The overall classification accuracy of the test data was found to be 68.4% (nodule (6/9) = 66.7%. Polyp (7/10) = 70%).). It was found that, therefore, the performance of the svm was higher and more stable.
참고문헌 (37)
- 강영애, "성대마비로 인한 기식 음성에 대한 Cepstral 분석", 말소리와 음성과학, 4(2), pp.89~94 (2012), 한국음성학회[DOI]
- 권순복, "양성후두질환 환자의 음성에 대한 음향학적 특징에 관한 연구", 특수교육재활과학연구, 47(2), pp.85~100 (2008), 특수교육재활과학연구소
- 김난숙, "과소비성(Hyponasality) 집단의 음향 특성과 분류 변인", 언어학, (78), pp.31~61 (2017), 사단법인 한국언어학회[DOI]
- 김영모, "후두 미세수술 전후의 음성기능분석", 대한이비인후과학회지, 42, pp.1174~1178 (1999)
- 나희, "성대 결절 환자의 성문 상부 움직임 및 성대 진동 양상에 관한 연구", Communication Sciences and Disorders, 15(3), pp.444~456 (2010), 한국언어청각임상학회
- 남순열, "후두 미세 수술 전후 성대 양성 병변 환자의 음성분석", Korean J Otolaryngol, 41(7), pp.925~928 (1998)
- 박수현, "후두 결절 및후두 폴립의 수술 전 후 음향학적 지표에 대한 연구", 대한이비인후과학회지, 42, pp.634~638 (1999)
- 서인효, "연결발화에서 마비말화자의 음질 특성", 말소리와 음성과학, 5(4), pp.33~41 (2013), 한국음성학회[DOI]
- 서인효, "성대 양성점막 질환에서 수술 전후 음질변화를 객관적으로 반영하는 음향지표 분석", 대한이비인후-두경부외과학회지, 59(11), pp.775~779 (2016), 대한이비인후과학회[DOI]
- AMOS를 이용한 알기 쉬운 통계분석: 기술통계에서 방정식모형까지, "SPSS", pp.2014, 성태제
- 왕수건, "각종 후두질환에서 음성치료의효과", 대한음성언어의학회지, 10(1), pp.17~23 (1999)
- 이인애, "기능적 음성장애인의 발성역치압력과 발성역치기류 특성 연구", 말소리와 음성과학, 5(1), pp.63~69 (2013), 한국음성학회
- 이현정, "호감(likable) 발화의 말소리 운율 특징 - 공용 미디어 자료를 대상으로 -", 언어학, (83), pp.119~148 (2019), 사단법인 한국언어학회[DOI]
- 최성희, "음성 신호 분류에 따른 장애 음성의 변동률 분석, 비선형 동적 분석, 캡스트럼 분석의 유용성", 말소리와 음성과학, 6(3), pp.63~72 (2014), 한국음성학회[DOI]
- 황연신, "후두미세수술 전후", 아, 말소리, pp.2008, 1(67)[DOI]
- 황영진, "음성과 음성장애" (2007), 시그마프레스
- 한원규, "후두미세수술 전후 성대용종의 크기 및 위치가 음성의 질의 변화에 미치는 영향", 대한후두음성언어의학회지, 27(2), pp.102~107 (2016)
- Bastian, R. W., "Benign vocal fold mucosal disorders", ~ (1998)
- Chang, C., "LIBSVM: A library for support vector machines", Machine Learning, 2(3), pp.27.1~27.27 (2011)[DOI]
- Chatterjee, S., "Regression analysis by example" (2006), Wiley-Interscience
- Cho, K. J., "Analysis of factors influencing voice quality and therapeutic approaches in vocal polyp patients", Eur Arch Otorhinolaryngol, 268, pp.1321~1327 (2011)
- Cortes, C., "Support-vector networks", Machine Learning, 20(3), pp.273~ (1995)
- Hillenbrand, J., "Acoustic correlates of breathy vocal quality:dysphonic voice and continuous speech", Journal of speech, Language, and Hearing Research, 39(2), pp.311~321 (1996)
- Hillenbrand, J., "Acoustic correlates of breathy vocal quality", Journal of speech, Language, and Hearing Research, 37, pp.769~778 (1994)
- Jack, J. J., "Objective Acoustic Analysis of Pathological Voices from Patients with Vocal Nodules and Polyps", Folia Phoniatrica et Logopaedica, 61, pp.342~349 (2009)
- Jannetts S, "Cepstral Analysis of Hypokinetic and Ataxic Voices:Correlations With Perceptual and Other Acoustic Measures", Journal of Voice, 28(6), pp.673~680 (2014)
- Klatt, D. H., "Analysis, synthesis, and perception of voice quality variation among female and male talkers", Journal of the Acoustical Society of America, 87, pp.820~857 (1990)
- Kleinbaum, G., "Analysis of Matched Data Using Logistic Regression in Logistic regression", pp.389~428 (2010), Springer
- Kumar, B. R., "Cepstral analysis of voice in persons with vocal nodules", Journal of Voice, 24(6), pp.651~653 (2009)
- Rosner, B., "Fundamentals of biostatistics" (2006), Duxbury Press
- Sanada, T., "Relationships between the degree of lesion and that of vocal dysfunction in vocal fold polyp", Nihon Jibiinkoka Gakkai Kaiho, 93, pp.388~392 (1990)
- Stemple, J. C., "Clinical voice pathology: Theory and management" (2000), Singular
- Theil, H., "A Rank Invariant Method of Linear and Polynomial Regression Analysis, i, ii, iii", Proceedings of the Koninklijke Nederlandse Akademie Wetenschappen, Series A Mathematical Sciences, 53, pp.386~392 (1950)
- Vapnik, V., "The nature of statistical learning theory" (2000), Springer-Verlag
- Wolfe, V., "Acoustic prediction of severity in commonly occurring voice problems, Journal of Speech", Language & Hearing Research, 38, pp.273~279 (1995)
- Zhuang, P., "Phonation threshold flow measurements in normal and pathological phonation", Laryngoscope, 119(4), pp.811~815 (2009)
- Zraick, R. I., "Adult normative data for the KayPENTAX Phonatory Aerodynamic System Model 6600", Journal of Voice, 26(2), pp.164~176 (2012)