Quality Control of Voice Recordings in Remote Parkinson’S Disease Monitoring Using the Infinite Hidden Markov Model

Amir Hossein Poorjam, Yordan P. Raykov, Reham Badawy, Jesper Rindom Jensen, Mads Grasboll Christensen, Max A. Little

Research output: Contribution to journalConference article

Abstract

The performance of voice-based systems for remote monitoring of Parkinson’s disease is highly dependent on the degree of adherence of the recordings to the test protocols, which probe for specific symptoms. Identifying segments of the signal that adhere to the protocol assumptions is typically performed manually by experts. This process is costly, time consuming, and often infeasible for large-scale data sets. In this paper, we propose a method to automatically identify the segments of signals that violate the test protocol with a high accuracy. In our approach, the signal is first split into variable duration segments by fitting an infinite hidden Markov model (iHMM) to the frames of the signals in the mel-frequency cepstral domain. The complexity of the iHMM is capable of growing jointly with the data allowing us to infer a potentially large (asymptotically infinite) number of different phenomena segmented into different hidden states. Then, we identify the segments that adhere to the test protocol by applying a multinomial naive Bayes classifier to the state indicators of segments. The experimental results show that even by using a small amount of training data, we can achieve around 96% accuracy in identifying short-term protocol violations with a 0.2 s resolution.
Original languageEnglish
Pages (from-to)805-809
Number of pages5
JournalICASSP 2019
Volume2019-May
DOIs
Publication statusPublished - 17 Apr 2019
EventICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Brighton, United Kingdom
Duration: 12 May 201917 May 2019

Fingerprint

Hidden Markov models
Quality control
Monitoring
Classifiers

Bibliographical note

© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Keywords

  • Bayesian Nonparametric
  • Parkinson's disease
  • infinite HMM
  • quality control
  • segmentation

Cite this

Poorjam, A. H., Raykov, Y. P., Badawy, R., Jensen, J. R., Christensen, M. G., & Little, M. A. (2019). Quality Control of Voice Recordings in Remote Parkinson’S Disease Monitoring Using the Infinite Hidden Markov Model. ICASSP 2019, 2019-May, 805-809. https://doi.org/10.1109/ICASSP.2019.8682523
Poorjam, Amir Hossein ; Raykov, Yordan P. ; Badawy, Reham ; Jensen, Jesper Rindom ; Christensen, Mads Grasboll ; Little, Max A. / Quality Control of Voice Recordings in Remote Parkinson’S Disease Monitoring Using the Infinite Hidden Markov Model. In: ICASSP 2019. 2019 ; Vol. 2019-May. pp. 805-809.
@article{45225e108021461c8aae0cdc27bffd18,
title = "Quality Control of Voice Recordings in Remote Parkinson’S Disease Monitoring Using the Infinite Hidden Markov Model",
abstract = "The performance of voice-based systems for remote monitoring of Parkinson’s disease is highly dependent on the degree of adherence of the recordings to the test protocols, which probe for specific symptoms. Identifying segments of the signal that adhere to the protocol assumptions is typically performed manually by experts. This process is costly, time consuming, and often infeasible for large-scale data sets. In this paper, we propose a method to automatically identify the segments of signals that violate the test protocol with a high accuracy. In our approach, the signal is first split into variable duration segments by fitting an infinite hidden Markov model (iHMM) to the frames of the signals in the mel-frequency cepstral domain. The complexity of the iHMM is capable of growing jointly with the data allowing us to infer a potentially large (asymptotically infinite) number of different phenomena segmented into different hidden states. Then, we identify the segments that adhere to the test protocol by applying a multinomial naive Bayes classifier to the state indicators of segments. The experimental results show that even by using a small amount of training data, we can achieve around 96{\%} accuracy in identifying short-term protocol violations with a 0.2 s resolution.",
keywords = "Bayesian Nonparametric, Parkinson's disease, infinite HMM, quality control, segmentation",
author = "Poorjam, {Amir Hossein} and Raykov, {Yordan P.} and Reham Badawy and Jensen, {Jesper Rindom} and Christensen, {Mads Grasboll} and Little, {Max A.}",
note = "{\circledC} 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2019",
month = "4",
day = "17",
doi = "10.1109/ICASSP.2019.8682523",
language = "English",
volume = "2019-May",
pages = "805--809",

}

Poorjam, AH, Raykov, YP, Badawy, R, Jensen, JR, Christensen, MG & Little, MA 2019, 'Quality Control of Voice Recordings in Remote Parkinson’S Disease Monitoring Using the Infinite Hidden Markov Model', ICASSP 2019, vol. 2019-May, pp. 805-809. https://doi.org/10.1109/ICASSP.2019.8682523

Quality Control of Voice Recordings in Remote Parkinson’S Disease Monitoring Using the Infinite Hidden Markov Model. / Poorjam, Amir Hossein; Raykov, Yordan P.; Badawy, Reham; Jensen, Jesper Rindom; Christensen, Mads Grasboll; Little, Max A.

In: ICASSP 2019, Vol. 2019-May, 17.04.2019, p. 805-809.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Quality Control of Voice Recordings in Remote Parkinson’S Disease Monitoring Using the Infinite Hidden Markov Model

AU - Poorjam, Amir Hossein

AU - Raykov, Yordan P.

AU - Badawy, Reham

AU - Jensen, Jesper Rindom

AU - Christensen, Mads Grasboll

AU - Little, Max A.

N1 - © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2019/4/17

Y1 - 2019/4/17

N2 - The performance of voice-based systems for remote monitoring of Parkinson’s disease is highly dependent on the degree of adherence of the recordings to the test protocols, which probe for specific symptoms. Identifying segments of the signal that adhere to the protocol assumptions is typically performed manually by experts. This process is costly, time consuming, and often infeasible for large-scale data sets. In this paper, we propose a method to automatically identify the segments of signals that violate the test protocol with a high accuracy. In our approach, the signal is first split into variable duration segments by fitting an infinite hidden Markov model (iHMM) to the frames of the signals in the mel-frequency cepstral domain. The complexity of the iHMM is capable of growing jointly with the data allowing us to infer a potentially large (asymptotically infinite) number of different phenomena segmented into different hidden states. Then, we identify the segments that adhere to the test protocol by applying a multinomial naive Bayes classifier to the state indicators of segments. The experimental results show that even by using a small amount of training data, we can achieve around 96% accuracy in identifying short-term protocol violations with a 0.2 s resolution.

AB - The performance of voice-based systems for remote monitoring of Parkinson’s disease is highly dependent on the degree of adherence of the recordings to the test protocols, which probe for specific symptoms. Identifying segments of the signal that adhere to the protocol assumptions is typically performed manually by experts. This process is costly, time consuming, and often infeasible for large-scale data sets. In this paper, we propose a method to automatically identify the segments of signals that violate the test protocol with a high accuracy. In our approach, the signal is first split into variable duration segments by fitting an infinite hidden Markov model (iHMM) to the frames of the signals in the mel-frequency cepstral domain. The complexity of the iHMM is capable of growing jointly with the data allowing us to infer a potentially large (asymptotically infinite) number of different phenomena segmented into different hidden states. Then, we identify the segments that adhere to the test protocol by applying a multinomial naive Bayes classifier to the state indicators of segments. The experimental results show that even by using a small amount of training data, we can achieve around 96% accuracy in identifying short-term protocol violations with a 0.2 s resolution.

KW - Bayesian Nonparametric

KW - Parkinson's disease

KW - infinite HMM

KW - quality control

KW - segmentation

UR - https://ieeexplore.ieee.org/document/8682523/

UR - http://www.scopus.com/inward/record.url?scp=85068969018&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2019.8682523

DO - 10.1109/ICASSP.2019.8682523

M3 - Conference article

VL - 2019-May

SP - 805

EP - 809

ER -