Surfboard: Audio Feature Extraction for Modern Machine Learning

被引:9
作者
Lenain, Raphael [1 ]
Weston, Jack [1 ]
Shivkumar, Abhishek [1 ]
Fristed, Emil [1 ]
机构
[1] Novoic Ltd, London, England
来源
INTERSPEECH 2020 | 2020年
关键词
Audio processing; healthcare; machine learning (ML); mPower; Novoic; Parkinson's disease; signal processing; speech and language disorders; speech representations; Surfboard; AMYOTROPHIC-LATERAL-SCLEROSIS; PARKINSONS-DISEASE; ACOUSTIC ANALYSIS; LARGE-SAMPLE; SPEECH; VOICE; FREQUENCY;
D O I
10.21437/Interspeech.2020-2879
中图分类号
R36 [病理学]; R76 [耳鼻咽喉科学];
学科分类号
100104 ; 100213 ;
摘要
We introduce Surfboard, an open-source Python library for extracting audio features with application to the medical domain. Surfboard is written with the aim of addressing pain points of existing libraries and facilitating joint use with modern machine learning frameworks. The package can be accessed both programmatically in Python and via its command line interface, allowing it to be easily integrated within machine learning workflows. It builds on state-of-the-art audio analysis packages and offers multiprocessing support for processing large workloads. We review similar frameworks and describe Surfboard's architecture, including the clinical motivation for its features. Using the mPower dataset, we illustrate Surfboard's application to a Parkinson's disease classification task, high-lighting common pitfalls in existing research. The source code is opened up to the research community to facilitate future audio research in the clinical domain.
引用
收藏
页码:2917 / 2921
页数:5
相关论文
共 54 条
[1]  
Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
[2]   Cough Sound Analysis Can Rapidly Diagnose Childhood Pneumonia [J].
Abeyratne, Udantha R. ;
Swarnkar, Vinayak ;
Setyati, Amalia ;
Triasih, Rina .
ANNALS OF BIOMEDICAL ENGINEERING, 2013, 41 (11) :2448-2462
[3]  
[Anonymous], 1997, SOFTWARE
[4]  
[Anonymous], 2010, Computer software
[5]   An introduction to modern missing data analyses [J].
Baraldi, Amanda N. ;
Enders, Craig K. .
JOURNAL OF SCHOOL PSYCHOLOGY, 2010, 48 (01) :5-37
[6]   Fully automated assessment of the severity of Parkinson's disease from speech [J].
Bayestehtashk, Alireza ;
Asgari, Meysam ;
Shafran, Izhak ;
McNames, James .
COMPUTER SPEECH AND LANGUAGE, 2015, 29 (01) :172-185
[7]  
Bocklet T, 2013, INTERSPEECH, P1148
[8]  
Boersma P, 2017, PRAAT DOING PHONETIC
[9]   Connected Speech in Neurodegenerative Language Disorders: A Review [J].
Boschi, Veronica ;
Catricala, Eleonora ;
Consonni, Monica ;
Chesi, Cristiano ;
Moro, Andrea ;
Cappa, Stefano F. .
FRONTIERS IN PSYCHOLOGY, 2017, 8 :1-21
[10]   The mPower study, Parkinson disease mobile data collected using ResearchKit [J].
Bot, Brian M. ;
Suver, Christine ;
Neto, Elias Chaibub ;
Kellen, Michael ;
Klein, Arno ;
Bare, Christopher ;
Doerr, Megan ;
Pratap, Abhishek ;
Wilbanks, John ;
Dorsey, E. Ray ;
Friend, Stephen H. ;
Trister, Andrew D. .
SCIENTIFIC DATA, 2016, 3