Mood state prediction from speech of varying acoustic quality for individuals with bipolar disorder

John Gideon, Emily Mower Provost, Melvin McInnis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Speech contains patterns that can be altered by the mood of an individual. There is an increasing focus on automated and distributed methods to collect and monitor speech from large groups of patients suffering from mental health disorders. However, as the scope of these collections increases, the variability in the data also increases. This variability is due in part to the range in the quality of the devices, which in turn affects the quality of the recorded data, negatively impacting the accuracy of automatic assessment. It is necessary to mitigate variability effects in order to expand the impact of these technologies. This paper explores speech collected from phone recordings for analysis of mood in individuals with bipolar disorder. Two different phones with varying amounts of clipping, loudness, and noise are employed. We describe methodologies for use during preprocessing, feature extraction, and data modeling to correct these differences and make the devices more comparable. The results demonstrate that these pipeline modifications result in statistically significantly higher performance, which highlights the potential of distributed mental health systems.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2359-2363
Number of pages5
Volume2016-May
ISBN (Electronic)9781479999880
DOIs
StatePublished - May 18 2016
Externally publishedYes
Event41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China
Duration: Mar 20 2016Mar 25 2016

Other

Other41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
CountryChina
CityShanghai
Period3/20/163/25/16

Fingerprint

Acoustics
Health
Data structures
Feature extraction
Pipelines

Keywords

  • Bipolar Disorder
  • Mobile Health
  • Mood Modeling
  • Speech Analysis

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Gideon, J., Provost, E. M., & McInnis, M. (2016). Mood state prediction from speech of varying acoustic quality for individuals with bipolar disorder. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings (Vol. 2016-May, pp. 2359-2363). [7472099] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2016.7472099

Mood state prediction from speech of varying acoustic quality for individuals with bipolar disorder. / Gideon, John; Provost, Emily Mower; McInnis, Melvin.

2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. p. 2359-2363 7472099.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gideon, J, Provost, EM & McInnis, M 2016, Mood state prediction from speech of varying acoustic quality for individuals with bipolar disorder. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. vol. 2016-May, 7472099, Institute of Electrical and Electronics Engineers Inc., pp. 2359-2363, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 3/20/16. https://doi.org/10.1109/ICASSP.2016.7472099
Gideon J, Provost EM, McInnis M. Mood state prediction from speech of varying acoustic quality for individuals with bipolar disorder. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May. Institute of Electrical and Electronics Engineers Inc. 2016. p. 2359-2363. 7472099 https://doi.org/10.1109/ICASSP.2016.7472099
Gideon, John ; Provost, Emily Mower ; McInnis, Melvin. / Mood state prediction from speech of varying acoustic quality for individuals with bipolar disorder. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. pp. 2359-2363
@inproceedings{800d0811208e4fe1ba9a9cc622ec92eb,
title = "Mood state prediction from speech of varying acoustic quality for individuals with bipolar disorder",
abstract = "Speech contains patterns that can be altered by the mood of an individual. There is an increasing focus on automated and distributed methods to collect and monitor speech from large groups of patients suffering from mental health disorders. However, as the scope of these collections increases, the variability in the data also increases. This variability is due in part to the range in the quality of the devices, which in turn affects the quality of the recorded data, negatively impacting the accuracy of automatic assessment. It is necessary to mitigate variability effects in order to expand the impact of these technologies. This paper explores speech collected from phone recordings for analysis of mood in individuals with bipolar disorder. Two different phones with varying amounts of clipping, loudness, and noise are employed. We describe methodologies for use during preprocessing, feature extraction, and data modeling to correct these differences and make the devices more comparable. The results demonstrate that these pipeline modifications result in statistically significantly higher performance, which highlights the potential of distributed mental health systems.",
keywords = "Bipolar Disorder, Mobile Health, Mood Modeling, Speech Analysis",
author = "John Gideon and Provost, {Emily Mower} and Melvin McInnis",
year = "2016",
month = "5",
day = "18",
doi = "10.1109/ICASSP.2016.7472099",
language = "English (US)",
volume = "2016-May",
pages = "2359--2363",
booktitle = "2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Mood state prediction from speech of varying acoustic quality for individuals with bipolar disorder

AU - Gideon, John

AU - Provost, Emily Mower

AU - McInnis, Melvin

PY - 2016/5/18

Y1 - 2016/5/18

N2 - Speech contains patterns that can be altered by the mood of an individual. There is an increasing focus on automated and distributed methods to collect and monitor speech from large groups of patients suffering from mental health disorders. However, as the scope of these collections increases, the variability in the data also increases. This variability is due in part to the range in the quality of the devices, which in turn affects the quality of the recorded data, negatively impacting the accuracy of automatic assessment. It is necessary to mitigate variability effects in order to expand the impact of these technologies. This paper explores speech collected from phone recordings for analysis of mood in individuals with bipolar disorder. Two different phones with varying amounts of clipping, loudness, and noise are employed. We describe methodologies for use during preprocessing, feature extraction, and data modeling to correct these differences and make the devices more comparable. The results demonstrate that these pipeline modifications result in statistically significantly higher performance, which highlights the potential of distributed mental health systems.

AB - Speech contains patterns that can be altered by the mood of an individual. There is an increasing focus on automated and distributed methods to collect and monitor speech from large groups of patients suffering from mental health disorders. However, as the scope of these collections increases, the variability in the data also increases. This variability is due in part to the range in the quality of the devices, which in turn affects the quality of the recorded data, negatively impacting the accuracy of automatic assessment. It is necessary to mitigate variability effects in order to expand the impact of these technologies. This paper explores speech collected from phone recordings for analysis of mood in individuals with bipolar disorder. Two different phones with varying amounts of clipping, loudness, and noise are employed. We describe methodologies for use during preprocessing, feature extraction, and data modeling to correct these differences and make the devices more comparable. The results demonstrate that these pipeline modifications result in statistically significantly higher performance, which highlights the potential of distributed mental health systems.

KW - Bipolar Disorder

KW - Mobile Health

KW - Mood Modeling

KW - Speech Analysis

UR - http://www.scopus.com/inward/record.url?scp=84973346043&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973346043&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2016.7472099

DO - 10.1109/ICASSP.2016.7472099

M3 - Conference contribution

AN - SCOPUS:84973346043

VL - 2016-May

SP - 2359

EP - 2363

BT - 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -