지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2019.2
- 수록면
- 39 - 47 (9page)
- DOI
- 10.5143/JESK.2019.38.1.39
이용수
초록· 키워드
오류제보하기
Objective: This study aims the sound quality analysis of baby crying sound to understand the sound characteristics of baby crying.
Background: Baby crying may be the fundamental communication method between babies and adults. Thus, baby crying can represent various emotion, request, condition, or alarm. Due to those features, a number of studies are reported that medical diagnosis based on baby crying analysis are possible. Recently, unfortunate accident that baby is left in a car leading to sometimes death is often reported, so automatic detection of baby crying is also tried. However, there is few study showing the timefrequency analysis of baby crying which illustrates the intuitive understanding the characteristics of baby crying. Therefore, clear demonstration for the sound analysis for baby crying needs to be investigated.
Method: 10 baby crying sounds are used for time-frequency analysis. For Fast Fourier Transform (FFT), Hann window is utilized, and 50% overlap is applied. Fundamental frequency of baby crying is found, and the magnitudes of harmonics are detected and tabled. Also, different crying patterns are compared with a typical crying sound with the same baby. Lastly, various sound sources, man and woman"s voice and an instrument, are investigated and compared.
Results: Baby crying has certain characteristics which show the 1st fundamental component around below 500Hz, and 1~3kHz components tend to be amplified. In addition, different crying patterns show distinguishable sound characteristics.
Conclusion: Baby crying is unique in terms of the sound characteristics which show human ears sensitivity.
Application: The results can assist the study in the field of medical application for diagnosis of baby conditions or baby safety method detecting baby crying sound.
Background: Baby crying may be the fundamental communication method between babies and adults. Thus, baby crying can represent various emotion, request, condition, or alarm. Due to those features, a number of studies are reported that medical diagnosis based on baby crying analysis are possible. Recently, unfortunate accident that baby is left in a car leading to sometimes death is often reported, so automatic detection of baby crying is also tried. However, there is few study showing the timefrequency analysis of baby crying which illustrates the intuitive understanding the characteristics of baby crying. Therefore, clear demonstration for the sound analysis for baby crying needs to be investigated.
Method: 10 baby crying sounds are used for time-frequency analysis. For Fast Fourier Transform (FFT), Hann window is utilized, and 50% overlap is applied. Fundamental frequency of baby crying is found, and the magnitudes of harmonics are detected and tabled. Also, different crying patterns are compared with a typical crying sound with the same baby. Lastly, various sound sources, man and woman"s voice and an instrument, are investigated and compared.
Results: Baby crying has certain characteristics which show the 1st fundamental component around below 500Hz, and 1~3kHz components tend to be amplified. In addition, different crying patterns show distinguishable sound characteristics.
Conclusion: Baby crying is unique in terms of the sound characteristics which show human ears sensitivity.
Application: The results can assist the study in the field of medical application for diagnosis of baby conditions or baby safety method detecting baby crying sound.
목차
1. Introduction
2. Method
3. Results & Discussion
4. Conclusion
References
참고문헌 (10)
참고문헌 신청
Cohen, R. / 2012 / Infant Cry Analysis and Detection / 2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel 1(5):1~5
김봉현 / 2008 / 울음소리의 주파수 대역폭 분석을 이용한 소아호흡기 질환 진단에 관한 연구 / 한국통신학회논문지B 33(12):1123~1130
Kinsler, L. E. / 1999 / Fundamentals of Acoustics / John Wiley and Sons, Inc
Linda L. LaGasse / 2005 / Assessment of infant cry: Acoustic cry analysis and parental perception / Mental Retardation and Developmental Disabilities Research Reviews 11(1):83~93
Lavner, Y. / 2016 / Baby Cry Detection in Domestic Environment Using Deep Learning / 2016 IEEE International Conference on the Science of Electrical Engineering (ICSEE) :1~5
김봉현 / 2008 / 울음소리의 주파수 대역폭 분석을 이용한 소아호흡기 질환 진단에 관한 연구 / 한국통신학회논문지B 33(12):1123~1130
Kinsler, L. E. / 1999 / Fundamentals of Acoustics / John Wiley and Sons, Inc
Linda L. LaGasse / 2005 / Assessment of infant cry: Acoustic cry analysis and parental perception / Mental Retardation and Developmental Disabilities Research Reviews 11(1):83~93
Lavner, Y. / 2016 / Baby Cry Detection in Domestic Environment Using Deep Learning / 2016 IEEE International Conference on the Science of Electrical Engineering (ICSEE) :1~5
이 논문의 저자 정보
이 논문과 함께 이용한 논문
스펙트로그램의 대조 학습을 이용한 기침 소리 분류
임현진
,
문기성
,
권선영
한국정보과학회 학술발표논문집
2021
.12
KoBART를 활용한 한국어 혐오 발언 분류
이상민
,
정영섭
한국정보과학회 학술발표논문집
2021
.06
호흡기 질환 방역과 치료를 위한 딥러닝 기반 기침인식카메라
이경태
,
김성후
,
남현욱
외 2명
한국소음진동공학회 학술대회논문집
2020
.11
딥러닝을 활용한 자산분배 시스템
김성수
,
김종인
,
정기철
한국산업정보학회논문지
2019
.02
멀티모달 딥러닝을 위한 기침 소리와 가속도 데이터의 결합 표현
강재식
,
백문기
,
최형탁
외 1명
한국통신학회 학술대회논문집
2019
.06
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2019-530-000465223