Proceedings of the IEEK Conference (대한전자공학회:학술대회논문집)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Performance Assessment of Several Established Pitch Detection Algorithms in Voices of Benign Vocal Fold Lesions

양성후두 질환 음성에 대한 여러 기존 피치검출 알고리즘의 성능 평가

  • Jang, Seung-Jin (Dept. of Biomedical Engineering, College of Health & Science, Yonsei University) ;
  • Choi, Seong-Hee (Div. of Otolaryngology-Head and Neck Surgery, Dept. of Surgery, University of Wisconsin-Maidison) ;
  • Kim, Hyo-Min (Dept. of Biomedical Engineering, College of Health & Science, Yonsei University) ;
  • Choi, Hong-Shik (Dept. of Otolaryngology, College of Medicine, Yonsei University) ;
  • Yoon, Young-Ro (Dept. of Biomedical Engineering, College of Health & Science, Yonsei University)
  • 장승진 (연세대학교, 보건과학대학 의공학과) ;
  • 최성희 (위스콘신대학 이비인후/두경부 전문외과) ;
  • 김효민 (연세대학교, 보건과학대학 의공학과) ;
  • 최홍식 (연세대학교 의학대학 이비인후과) ;
  • 윤영로 (연세대학교, 보건과학대학 의공학과)
  • Published : 2007.07.11
Download PDF
⟨ Previous Next ⟩

Abstract

Robust pitch estimation is an important study in many areas of speech processing. In voice pathology, diverse statistics extracted form pitch were commonly used to test voice quality. In this study, we compared several established pitch detection algorithms (PDAs) for verification of adequacy of the PDAs. In the database of total pathological voices of 99 and normal voices of 30, an analysis of errors related with pitch detection was evaluated between pathological and normal voices, or among the types of pathological voices such as benign vocal fold lesions; polyp, nodule, and cysts. Consequently, it is required to survey the severity of tested voice in order to obtain accurate pitch estimates.

Keywords