본문 바로가기
KERD
논문KCI 등재

켑스트럼 변수와 랜덤포레스트 알고리듬을 이용한 MTD(근긴장성 발성장애) 여성화자 음성과 정상음성 분류

Classification of muscle tension dysphonia (MTD) female speech and normal speech using cepstrum variables and random forest algorithm

성철재|심희정|윤주원
한국음성학회 (The Korean Society of Speech Sciences)|2020.12|말소리와 음성과학 (Phonetics and Speech Sciences)|제12권 제4호|pp. 91-98|DOI https://doi.org/10.13064/KSSS.2020.12.4.091

2

조회

0

다운로드

1

인용

0

참고문헌

키워드

machine learningRandom Forestmuscle tension dysphonia (MTD)cepstral peak prominence (CPP)CPP_F0sentence reading task
주제분류학제간연구

초록

This study investigated the acoustic characteristics of sustained vowel /a/ and sentence utterance produced by patients with muscle tension dysphonia (MTD) using cepstrum-based acoustic variables. 36 women diagnosed with MTD and the same number of women with normal voice participated in the study and the data were recorded and measured by ADSV™. The results demonstrated that cepstral peak prominence (CPP) and CPP_F0 among all of the variables were statistically significantly lower than those of control group. When it comes to the GRBAS scale, overall severity (G) was most prominent, and roughness (R), breathiness (B), and strain (S) indices followed in order in the voice quality of MTD patients. As these characteristics increased, a statistically significant negative correlation was observed in CPP. We tried to classify MTD and control group using CPP and CPP_F0 variables. As a result of statistic modeling with a Random Forest machine learning algorithm, much higher classification accuracy (100% in training data and 83.3% in test data) was found in the sentence reading task, with CPP being proved to be playing a more crucial role in both vowel and sentence reading tasks.

Abstract

This study investigated the acoustic characteristics of sustained vowel /a/ and sentence utterance produced by patients with muscle tension dysphonia (MTD) using cepstrum-based acoustic variables. 36 women diagnosed with MTD and the same number of women with normal voice participated in the study and the data were recorded and measured by ADSV™. The results demonstrated that cepstral peak prominence (CPP) and CPP_F0 among all of the variables were statistically significantly lower than those of control group. When it comes to the GRBAS scale, overall severity (G) was most prominent, and roughness (R), breathiness (B), and strain (S) indices followed in order in the voice quality of MTD patients. As these characteristics increased, a statistically significant negative correlation was observed in CPP. We tried to classify MTD and control group using CPP and CPP_F0 variables. As a result of statistic modeling with a Random Forest machine learning algorithm, much higher classification accuracy (100% in training data and 83.3% in test data) was found in the sentence reading task, with CPP being proved to be playing a more crucial role in both vowel and sentence reading tasks.

참고문헌 (31)

  1. Alharbi, G. G., "Spectral", cepstral analyses of phonation in Parkinson’s disease before and after voice treatment: A preliminary study, 2019, pp.71(5-6), 275~285
  2. Altman, K. W., "Current and emerging concepts in muscle tension dysphonia : A 30-month review", Journal of Voice, 19(2), pp.261~267 (2005)
  3. Awan, S. N., "Toward the development of an objective index of dysphonia severity : A four-factor acoustic model", Clinical Linguistics & Phonetics, 20(1), pp.35~49 (2006)
  4. Awan, S. N., "Outcomes measurement in voice disorders: Application of an acoustic index of dysphonia severity", Journal of Speech, Language & Hearing Research, 52(2), pp.482~499 (2009)
  5. Awan, S. N., "Exploring the relationship between spectral and cepstral measures of voice and the Voice Handicap Index(VHI)", Journal of Voice, 28(4), pp.430~439 (2014)
  6. Awan, S. N., "Validation of the cepstral spectral index of dysphonia(CSID)as a screening tool for voice disorders : Development of clinical cutoff scores", Journal of Voice, 30(2), pp.130~144 (2016)
  7. Breiman, L., "Random forests", Machine Learning, 45(1), pp.5~32 (2001)
  8. 최성희, "한국 정상 화자의 캡스트럼과 스펙트럼 측정치의 성별과 발화 과제 효과", Audiology and Speech Research, 12(3), pp.157~163 (2016), 한국청각언어재활학회
  9. Heman-Ackah, Y. D., "The relationship between cepstral peak prominence and selected parameters of dysphonia", Journal of Voice, 16(1), pp.20~27 (2002)
  10. Heman-Ackah, Y., "Cepstral peak prominence: A more reliable measure of dysphonia", Annals of Otology, Rhinogogy & Laryngology, 112(4), pp.324~333 (2003)
  11. Hillenbrand, J., "Acoustic correlates of breathy vocal quality: Dysphonic voices and continuous speech", Journal of Speech, Language, and Hearing Research, 39(2), pp.311~321 (1996)
  12. Hillenbrand, J., "Acoustic correlates of breathy vocal quality", Journal of Speech, Language, and Hearing Research, 37(4), pp.769~778 (1994)
  13. Jalalinajafabadi, F., "Perceptual evaluation of voice quality and its correlation with acoustic measurement", Proceedings of the 2013 European Modelling Symposium, pp.283~286 (2013)
  14. 김근효, "ADSV, SpeechTool, Praat 간의 CPP 특성 연구", 언어치료연구, 26(3), pp.99~111 (2017), 한국언어치료학회[DOI]
  15. 김난숙, "과소비성(Hyponasality) 집단의 음향 특성과 분류 변인", 언어학, (78), pp.31~61 (2017), 사단법인 한국언어학회[DOI]
  16. Koufman, J. A., "Vocal fatigue and dysphonia in the professional voice user : Bogart-bacall syndrome", The Laryngoscope, 98(5), pp.493~498 (1988)
  17. Kumar, B., "Cepstral analysis of voice in persons with vocal nodules", Journal of Voice, 24(6), pp.651~653 (2010)
  18. Lowell, S. Y., "Spectral- and cepstral-based acoustic features of dysphonic, strained voice quality", Annals of Otology, Rhinology &Laryngology, 121(8), pp.539~548 (2012)
  19. 노승호, "스펙트로그램을 이용한 내전형 연축성 발성 장애와 근긴장성 발성 장애의 감별", 대한후두음성언어의학회지, 28(2), pp.100~105 (2017), 대한후두음성언어의학회[DOI]
  20. Park, J. H., "A study on aspects of vocal cord vibration and acoustic characteristics according to types of muscle tension dysphonia", Master, pp.2011
  21. Peterson, E. A., "Toward validation of the cepstral spectral index of dysphonia (CSID) as an objective treatment outcomes measure", Journal of Voice, 27(4), pp.401~410 (2013)
  22. Pyo, H. Y., "A study for the development of Korean voice assessment model for the patients with voice disorders : A qualitative study", Phonetics and Speech Sciences, 14(2), pp.7~22 (2007)
  23. Rubin, J. S., "Diagnosis and treatment of voice disorders" (2006), Plural
  24. Seo, I., "Acoustic measures of voice quality and phonation types across speech conditions in dysarthria", Doctor, pp.2014
  25. 서인효, "정상성인 화자의 속삭임성에 대한 켑스트럼 및 스펙트럼 분석: 예비연구", 언어치료연구, 24(4), pp.259~266 (2015), 한국언어치료학회[DOI]
  26. 서인효, "연결발화에서 마비말화자의 음질 특성", 말소리와 음성과학, 5(4), pp.33~41 (2013), 한국음성학회[DOI]
  27. Shim, H. J., "Cepstral, spectral and time-based analysis of voices of esophageal speakers", Folia Phoniatrica et Logopaedica, 67(2), pp.90~96 (2015)
  28. 심희정, "내전형연축성 발성장애 음성에 대한 켑스트럼과 스펙트럼 분석", 말소리와 음성과학, 8(2), pp.73~80 (2016), 한국음성학회[DOI]
  29. 신희백, "명료발화와 보통발화에서 파킨슨병환자 음성의 켑스트럼 및 스펙트럼 분석", 말소리와 음성과학, 10(2), pp.77~84 (2018), 한국음성학회[DOI]
  30. Watts, C., "Use of spectral", cepstral analyses for differentiating normal from hypofunctional voices in sustained vowel and continuous speech contexts, 2011, pp.54(6), 1525~1537
  31. 유미옥, "모음과 연결발화에서 캡스트럼 음향 지표의 정상 및 음성장애 예측", Communication Sciences and Disorders, 23(4), pp.1055~1064 (2018), 한국언어청각임상학회[DOI]

관련 논문AI추천

내전형연축성 발성장애 음성에 대한 켑스트럼과 스펙트럼 분석정훈, 고도흥, 심희정, 최병흔, 허정화, Lee, Sue Ann한국음성학회 · 말소리와 음성과학2016 · 제8권 제2호음성 신호 분류에 따른 장애 음성의 변동률 분석, 비선형 동적 분석, 캡스트럼 분석의 유용성최성희, 최철희한국음성학회 · 말소리와 음성과학2014 · 제6권 제3호기식성 음성 장애 환자들의 음향학적 특성과 분류 변인(결절, 용종환자를 중심으로)성철재, 이인애사단법인 한국언어학회 · 언어학2020 · 제88호모음연장발성의 변동률 분석과 연속발화의 켑스트럼 분석 간의 연관성김지성, 이동욱대한후두음성언어의학회 · 대한후두음성언어의학회지2025 · 제36권 제3호노인성 음성장애에 대한 켑스트럼 분석에서의 무성음 분절 영향권순복, 김근효, 박희준, 배인호, 이연우, 이창윤대한이비인후과학회 부산,울산,경남 지부회 · 임상이비인후과2019 · 제30권 제1호기능성 음성장애의 진단을 위한 음향학적, 청지각적 평가권순복, 김근효, 박희준, 배인호, 이병주, 이연우, 이재석, 이창윤대한이비인후과학회 부산,울산,경남 지부회 · 임상이비인후과2018 · 제29권 제2호

이 간행물의 다른 논문 (10건)

한국어 서울 방언의 평음과 격음 변별 지각에서 연령과 성별에 따른 차이김제홍, 남기춘, 최지연, 안주희, 김소안pp. 1-8The effects of length of residence (LOR) on voice onset time (VOT)김미령pp. 9-17An evaluation of Korean students' pronunciation of an English passage by a speech recognition application and two human raters양병곤pp. 19-25KFL중국인학습자들의 한국어 동형다의 종결어미 발화문에 대한 원어민화자의 지각 평가 양상윤영숙pp. 27-36담화표지 ‘아’, ‘어’, ‘음’의 성별과 연령별 사용 양상송영숙, 심지수, 오재혁pp. 37-46
원문 보기