TY - JOUR
T1 - Machine Listening for Heart Status Monitoring
T2 - Introducing and Benchmarking HSS - The Heart Sounds Shenzhen Corpus
AU - Dong, Fengquan
AU - Qian, Kun
AU - Ren, Zhao
AU - Baird, Alice
AU - Li, Xinjian
AU - Dai, Zhenyu
AU - Dong, Bo
AU - Metze, Florian
AU - Yamamoto, Yoshiharu
AU - Schuller, Bjorn W.
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2020/7
Y1 - 2020/7
N2 - Auscultation of the heart is a widely studied technique, which requires precise hearing from practitioners as a means of distinguishing subtle differences in heart-beat rhythm. This technique is popular due to its non-invasive nature, and can be an early diagnosis aid for a range of cardiac conditions. Machine listening approaches can support this process, monitoring continuously and allowing for a representation of both mild and chronic heart conditions. Despite this potential, relevant databases and benchmark studies are scarce. In this paper, we introduce our publicly accessible database, the Heart Sounds Shenzhen Corpus (HSS), which was first released during the recent INTERSPEECH 2018 ComParE Heart Sound sub-challenge. Additionally, we provide a survey of machine learning work in the area of heart sound recognition, as well as a benchmark for HSS utilising standard acoustic features and machine learning models. At best our support vector machine with Log Mel features achieves 49.7% unweighted average recall on a three category task (normal, mild, moderate/severe).
AB - Auscultation of the heart is a widely studied technique, which requires precise hearing from practitioners as a means of distinguishing subtle differences in heart-beat rhythm. This technique is popular due to its non-invasive nature, and can be an early diagnosis aid for a range of cardiac conditions. Machine listening approaches can support this process, monitoring continuously and allowing for a representation of both mild and chronic heart conditions. Despite this potential, relevant databases and benchmark studies are scarce. In this paper, we introduce our publicly accessible database, the Heart Sounds Shenzhen Corpus (HSS), which was first released during the recent INTERSPEECH 2018 ComParE Heart Sound sub-challenge. Additionally, we provide a survey of machine learning work in the area of heart sound recognition, as well as a benchmark for HSS utilising standard acoustic features and machine learning models. At best our support vector machine with Log Mel features achieves 49.7% unweighted average recall on a three category task (normal, mild, moderate/severe).
KW - Heart sound
KW - artificial intelligence
KW - cardiovascular disease
KW - healthcare
KW - machine listening
UR - http://www.scopus.com/inward/record.url?scp=85087801129&partnerID=8YFLogxK
U2 - 10.1109/JBHI.2019.2955281
DO - 10.1109/JBHI.2019.2955281
M3 - Article
C2 - 31765322
AN - SCOPUS:85087801129
SN - 2168-2194
VL - 24
SP - 2082
EP - 2092
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
IS - 7
M1 - 8910340
ER -
