Uncovering Voice Misuse Using Symbolic Mismatch

Marzyeh Ghassemi, Zeeshan Syed, Daryush Mehta, Jarrad Van Stan, Robert Hillman, John Guttag
; Proceedings of the 1st Machine Learning for Healthcare Conference, PMLR 56:239-252, 2016.

Abstract

Voice disorders affect an estimated 14 million working-aged Americans, and many more worldwide. We present the first large scale study of vocal misuse based on long-term ambulatory data collected by an accelerometer placed on the neck. We investigate an unsupervised data mining approach to uncovering latent information about voice misuse. We segment signals from over 253 days of data from 22 subjects into over a hundred million single glottal pulses (closures of the vocal folds), cluster segments into symbols, and use symbolic mismatch to uncover differences between patients and matched controls, and between patients pre- and post-treatment. Our results show significant behavioral differences between patients and controls, as well as between some pre- and post-treatment patients. Our proposed approach provides an objective basis for helping diagnose behavioral voice disorders, and is a first step towards a more data-driven understanding of the impact of voice therapy.

Cite this Paper


BibTeX
@InProceedings{pmlr-v56-Ghassemi16, title = {Uncovering Voice Misuse Using Symbolic Mismatch}, author = {Marzyeh Ghassemi and Zeeshan Syed and Daryush Mehta and Jarrad Van Stan and Robert Hillman and John Guttag}, booktitle = {Proceedings of the 1st Machine Learning for Healthcare Conference}, pages = {239--252}, year = {2016}, editor = {Finale Doshi-Velez and Jim Fackler and David Kale and Byron Wallace and Jenna Wiens}, volume = {56}, series = {Proceedings of Machine Learning Research}, address = {Northeastern University, Boston, MA, USA}, month = {18--19 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v56/Ghassemi16.pdf}, url = {http://proceedings.mlr.press/v56/Ghassemi16.html}, abstract = {Voice disorders affect an estimated 14 million working-aged Americans, and many more worldwide. We present the first large scale study of vocal misuse based on long-term ambulatory data collected by an accelerometer placed on the neck. We investigate an unsupervised data mining approach to uncovering latent information about voice misuse. We segment signals from over 253 days of data from 22 subjects into over a hundred million single glottal pulses (closures of the vocal folds), cluster segments into symbols, and use symbolic mismatch to uncover differences between patients and matched controls, and between patients pre- and post-treatment. Our results show significant behavioral differences between patients and controls, as well as between some pre- and post-treatment patients. Our proposed approach provides an objective basis for helping diagnose behavioral voice disorders, and is a first step towards a more data-driven understanding of the impact of voice therapy.} }
Endnote
%0 Conference Paper %T Uncovering Voice Misuse Using Symbolic Mismatch %A Marzyeh Ghassemi %A Zeeshan Syed %A Daryush Mehta %A Jarrad Van Stan %A Robert Hillman %A John Guttag %B Proceedings of the 1st Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2016 %E Finale Doshi-Velez %E Jim Fackler %E David Kale %E Byron Wallace %E Jenna Wiens %F pmlr-v56-Ghassemi16 %I PMLR %J Proceedings of Machine Learning Research %P 239--252 %U http://proceedings.mlr.press %V 56 %W PMLR %X Voice disorders affect an estimated 14 million working-aged Americans, and many more worldwide. We present the first large scale study of vocal misuse based on long-term ambulatory data collected by an accelerometer placed on the neck. We investigate an unsupervised data mining approach to uncovering latent information about voice misuse. We segment signals from over 253 days of data from 22 subjects into over a hundred million single glottal pulses (closures of the vocal folds), cluster segments into symbols, and use symbolic mismatch to uncover differences between patients and matched controls, and between patients pre- and post-treatment. Our results show significant behavioral differences between patients and controls, as well as between some pre- and post-treatment patients. Our proposed approach provides an objective basis for helping diagnose behavioral voice disorders, and is a first step towards a more data-driven understanding of the impact of voice therapy.
RIS
TY - CPAPER TI - Uncovering Voice Misuse Using Symbolic Mismatch AU - Marzyeh Ghassemi AU - Zeeshan Syed AU - Daryush Mehta AU - Jarrad Van Stan AU - Robert Hillman AU - John Guttag BT - Proceedings of the 1st Machine Learning for Healthcare Conference PY - 2016/12/10 DA - 2016/12/10 ED - Finale Doshi-Velez ED - Jim Fackler ED - David Kale ED - Byron Wallace ED - Jenna Wiens ID - pmlr-v56-Ghassemi16 PB - PMLR SP - 239 DP - PMLR EP - 252 L1 - http://proceedings.mlr.press/v56/Ghassemi16.pdf UR - http://proceedings.mlr.press/v56/Ghassemi16.html AB - Voice disorders affect an estimated 14 million working-aged Americans, and many more worldwide. We present the first large scale study of vocal misuse based on long-term ambulatory data collected by an accelerometer placed on the neck. We investigate an unsupervised data mining approach to uncovering latent information about voice misuse. We segment signals from over 253 days of data from 22 subjects into over a hundred million single glottal pulses (closures of the vocal folds), cluster segments into symbols, and use symbolic mismatch to uncover differences between patients and matched controls, and between patients pre- and post-treatment. Our results show significant behavioral differences between patients and controls, as well as between some pre- and post-treatment patients. Our proposed approach provides an objective basis for helping diagnose behavioral voice disorders, and is a first step towards a more data-driven understanding of the impact of voice therapy. ER -
APA
Ghassemi, M., Syed, Z., Mehta, D., Stan, J.V., Hillman, R. & Guttag, J.. (2016). Uncovering Voice Misuse Using Symbolic Mismatch. Proceedings of the 1st Machine Learning for Healthcare Conference, in PMLR 56:239-252

Related Material