Automatic quality control and enhancement for voice-based remote Parkinson's disease detection

Amir Hossein Poorjam; Mathew Shaji Kavalekalam; Liming Shi; Jordan P. Raykov; Jesper Rindom Jensen; Max A. Little; Mads Græsbøll Christensen

doi:10.1016/j.specom.2020.12.007

Automatic quality control and enhancement for voice-based remote Parkinson's disease detection

Amir Hossein Poorjam^*, Mathew Shaji Kavalekalam, Liming Shi, Jordan P. Raykov, Jesper Rindom Jensen, Max A. Little, Mads Græsbøll Christensen

^*Corresponding author for this work

College of Engineering and Physical Sciences

Aalborg Universitet

Research output: Contribution to journal › Article › peer-review

23 Citations (SciVal)

Abstract

The performance of voice-based Parkinson's disease (PD) detection systems degrades when there is an acoustic mismatch between training and operating conditions caused mainly by degradation in test signals. In this paper, we address this mismatch by considering three types of degradation commonly encountered in remote voice analysis, namely background noise, reverberation and nonlinear distortion, and investigate how these degradations influence the performance of a PD detection system. Given that the specific degradation is known, we explore the effectiveness of a variety of enhancement algorithms in compensating this mismatch and improving the PD detection accuracy. Then, we propose two approaches to automatically control the quality of recordings by identifying the presence and type of short-term and long-term degradations and protocol violations in voice signals. Finally, we experiment with using the proposed quality control methods to inform the choice of enhancement algorithm. Experimental results using the voice recordings of the mPower mobile PD data set under different degradation conditions show the effectiveness of the quality control approaches in selecting an appropriate enhancement method and, consequently, in improving the PD detection accuracy. This study is a step towards the development of a remote PD detection system capable of operating in unseen acoustic environments.

Original language	English
Pages (from-to)	1-16
Number of pages	16
Journal	Speech Communication
Volume	127
Early online date	30 Dec 2020
DOIs	https://doi.org/10.1016/j.specom.2020.12.007
Publication status	Published - Mar 2021

Bibliographical note

Funding Information:
This work was funded by Independent Research Fund Denmark : DFF 4184-00056 .

Funding

This work was funded by Independent Research Fund Denmark : DFF 4184-00056 . Jesper Rindom Jensen (S’09–M’12) was born in Ringkøbing, Denmark in August 1984. He received the M.Sc. degree cum laude in 2009 from Aalborg University in Denmark. In 2012, he received the Ph.D. degree from Aalborg University. Currently, he is a Associate Professor at the Department of Architecture, Design and Media Technology (CREATE) at Aalborg University in Denmark. Before this, he was with the Department of Electronic Systems at Aalborg University, and in addition to this he has been Visiting Researcher at the University of Quebec, INRS-EMT, in Montreal, Quebec, Canada, at the Friedrich-Alexander Universität Erlangen-Nürnberg in Erlangen, Germany, and at the University of Surrey, UK. At Aalborg University, he is also a member of the Audio Analysis Lab since its foundation in 2012. His research interests include signal processing theory and methods for, e.g., robot and drone audition, and microphone arrays. Examples of more specific research interests within this scope are enhancement, separation, localization, tracking, parametric analysis, and modeling. He has published more than 80 papers on these topics in top-tier, peer-reviewed conference proceedings and journals. Moreover, he is the co-author of two books, namely, ”Speech Enhancement – A Signal Subspace Perspective” and ”Signal Enhancement with Variable Span Linear Filters”. Dr. Jensen has received a highly competitive postdoc grant from the Danish Independent Research Council, has been selected as an AAU Talent at Aalborg University (awarded to young research talents), and has received several travel grants from private foundations. Furthermore, he is an Associate Editor of the EURASIP Journal on Audio, Speech, and Music Processing, is a member of the IEEE Audio and Acoustic Signal Processing Technical Committee, is an Affiliate Member of the IEEE Signal Processing Theory and Methods Technical Committee, and is a Member of the IEEE. Mads Græsbøll Christensen (S’00–M’05–SM’11) received the M.Sc. and Ph.D. degrees from Aalborg University (AAU), Aalborg, Denmark, in 2002 and 2005, respectively. He is currently with the Department of Architecture, Design and Media Technology, AAU, as a Professor in Audio Processing and is the Head and Founder of the Audio Analysis Lab. He was formerly with the Department of Electronic Systems, AAU, and held visiting positions with Philips Research Labs, ENST, University of California, Santa Barbara, and Columbia University. He has authored or coauthored three books and more than 200 papers in peer-reviewed conference proceedings and journals. He has given multiple tutorials at the European Signal Processing Conference, the IEEE International Conference on Acoustics, Speech, and Signal Processing, and the Annual Conference of the International Speech Communication Association and a keynote talk at the International Workshop on Acoustic Signal Enhancement. His research interests include audio and acoustic signal processing, where he has worked on topics such as microphone arrays, noise reduction, signal modeling, speech analysis, audio classification, and audio coding. Dr. Christensen has received several awards, including Best Paper Awards, the Spar Nord Foundation’s Research Prize, a Danish Independent Research Council Young Researcher’s Award, the Statoil Prize, the EURASIP Early Career Award, and an IEEE Signal Processing Society Best Paper Award. He is a beneficiary of major grants from the Independent Research Fund Denmark, the Villum Foundation, and Innovation Fund Denmark. He serves as the Editor-in-Chief of the EURASIP Journal on Audio, Speech, and Music Processing and as Senior Area Editor for the IEEE Signal Processing Letters, and he has previously served as an Associate Editor for the IEEE/ACM Transactions on Audio, Speech, and Language Processing and the IEEE Signal Processing Letters. He is a member of the IEEE Audio and Acoustic Signal Processing Technical Committee and a Founding Member of the EURASIP Special Area Team in Acoustic, Speech and Music Signal Processing. He is a member of the EURASIP and the Danish Academy of Technical Sciences.

Keywords

Acoustic mismatch
Parkinson's disease detection
Quality control
Speech enhancement

Access to Document

10.1016/j.specom.2020.12.007

Cite this

@article{a2fdc7c4efde46a38eaf92d4e0d543ed,

title = "Automatic quality control and enhancement for voice-based remote Parkinson's disease detection",

abstract = "The performance of voice-based Parkinson's disease (PD) detection systems degrades when there is an acoustic mismatch between training and operating conditions caused mainly by degradation in test signals. In this paper, we address this mismatch by considering three types of degradation commonly encountered in remote voice analysis, namely background noise, reverberation and nonlinear distortion, and investigate how these degradations influence the performance of a PD detection system. Given that the specific degradation is known, we explore the effectiveness of a variety of enhancement algorithms in compensating this mismatch and improving the PD detection accuracy. Then, we propose two approaches to automatically control the quality of recordings by identifying the presence and type of short-term and long-term degradations and protocol violations in voice signals. Finally, we experiment with using the proposed quality control methods to inform the choice of enhancement algorithm. Experimental results using the voice recordings of the mPower mobile PD data set under different degradation conditions show the effectiveness of the quality control approaches in selecting an appropriate enhancement method and, consequently, in improving the PD detection accuracy. This study is a step towards the development of a remote PD detection system capable of operating in unseen acoustic environments.",

keywords = "Acoustic mismatch, Parkinson's disease detection, Quality control, Speech enhancement",

author = "Poorjam, {Amir Hossein} and Kavalekalam, {Mathew Shaji} and Liming Shi and Raykov, {Jordan P.} and Jensen, {Jesper Rindom} and Little, {Max A.} and Christensen, {Mads Gr{\ae}sb{\o}ll}",

note = "Funding Information: This work was funded by Independent Research Fund Denmark : DFF 4184-00056 . ",

year = "2021",

month = mar,

doi = "10.1016/j.specom.2020.12.007",

language = "English",

volume = "127",

pages = "1--16",

journal = "Speech Communication",

issn = "0167-6393",

publisher = "Elsevier",

}

TY - JOUR

T1 - Automatic quality control and enhancement for voice-based remote Parkinson's disease detection

AU - Poorjam, Amir Hossein

AU - Kavalekalam, Mathew Shaji

AU - Shi, Liming

AU - Raykov, Jordan P.

AU - Jensen, Jesper Rindom

AU - Little, Max A.

AU - Christensen, Mads Græsbøll

N1 - Funding Information: This work was funded by Independent Research Fund Denmark : DFF 4184-00056 .

PY - 2021/3

Y1 - 2021/3

N2 - The performance of voice-based Parkinson's disease (PD) detection systems degrades when there is an acoustic mismatch between training and operating conditions caused mainly by degradation in test signals. In this paper, we address this mismatch by considering three types of degradation commonly encountered in remote voice analysis, namely background noise, reverberation and nonlinear distortion, and investigate how these degradations influence the performance of a PD detection system. Given that the specific degradation is known, we explore the effectiveness of a variety of enhancement algorithms in compensating this mismatch and improving the PD detection accuracy. Then, we propose two approaches to automatically control the quality of recordings by identifying the presence and type of short-term and long-term degradations and protocol violations in voice signals. Finally, we experiment with using the proposed quality control methods to inform the choice of enhancement algorithm. Experimental results using the voice recordings of the mPower mobile PD data set under different degradation conditions show the effectiveness of the quality control approaches in selecting an appropriate enhancement method and, consequently, in improving the PD detection accuracy. This study is a step towards the development of a remote PD detection system capable of operating in unseen acoustic environments.

AB - The performance of voice-based Parkinson's disease (PD) detection systems degrades when there is an acoustic mismatch between training and operating conditions caused mainly by degradation in test signals. In this paper, we address this mismatch by considering three types of degradation commonly encountered in remote voice analysis, namely background noise, reverberation and nonlinear distortion, and investigate how these degradations influence the performance of a PD detection system. Given that the specific degradation is known, we explore the effectiveness of a variety of enhancement algorithms in compensating this mismatch and improving the PD detection accuracy. Then, we propose two approaches to automatically control the quality of recordings by identifying the presence and type of short-term and long-term degradations and protocol violations in voice signals. Finally, we experiment with using the proposed quality control methods to inform the choice of enhancement algorithm. Experimental results using the voice recordings of the mPower mobile PD data set under different degradation conditions show the effectiveness of the quality control approaches in selecting an appropriate enhancement method and, consequently, in improving the PD detection accuracy. This study is a step towards the development of a remote PD detection system capable of operating in unseen acoustic environments.

KW - Acoustic mismatch

KW - Parkinson's disease detection

KW - Quality control

KW - Speech enhancement

UR - http://www.scopus.com/inward/record.url?scp=85099006185&partnerID=8YFLogxK

UR - https://www.sciencedirect.com/science/article/pii/S0167639320303113?via%3Dihub

U2 - 10.1016/j.specom.2020.12.007

DO - 10.1016/j.specom.2020.12.007

M3 - Article

AN - SCOPUS:85099006185

SN - 0167-6393

VL - 127

SP - 1

EP - 16

JO - Speech Communication

JF - Speech Communication

ER -

Automatic quality control and enhancement for voice-based remote Parkinson's disease detection

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Automatic Quality Control and Enhancement for Voice-Based Remote Parkinson’s Disease Detection

Cite this