Abstract

Objective assessment of pathological speech is an important part of existing systems for automatic diagnosis and treatment of various speech disorders. In this paper, we propose a new regression method for this application. Rather than treating speech samples from each speaker as individual data instances, we treat each speaker's data as a probability distribution. We propose a simple non-parametric learning method to make predictions for out-of-sample speakers based on a probability distance measure to the speakers in the training set. This is in contrast to traditional learning methods that rely on Euclidean distances between individual instances. We evaluate the method on two pathological speech data sets with promising results.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5050-5054
Number of pages5
ISBN (Electronic)9781509041176
DOIs
StatePublished - Jun 16 2017
Event2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States
Duration: Mar 5 2017Mar 9 2017

Other

Other2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
CountryUnited States
CityNew Orleans
Period3/5/173/9/17

Fingerprint

Probability distributions

Keywords

  • Distribution regression
  • divergence
  • objective assessment
  • speech pathology

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Tu, M., Berisha, V., & Liss, J. (2017). Objective assessment of pathological speech using distribution regression. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings (pp. 5050-5054). [7953118] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2017.7953118

Objective assessment of pathological speech using distribution regression. / Tu, Ming; Berisha, Visar; Liss, Julie.

2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 5050-5054 7953118.

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

Tu, M, Berisha, V & Liss, J 2017, Objective assessment of pathological speech using distribution regression. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7953118, Institute of Electrical and Electronics Engineers Inc., pp. 5050-5054, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 3/5/17. https://doi.org/10.1109/ICASSP.2017.7953118
Tu M, Berisha V, Liss J. Objective assessment of pathological speech using distribution regression. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 5050-5054. 7953118 https://doi.org/10.1109/ICASSP.2017.7953118
Tu, Ming ; Berisha, Visar ; Liss, Julie. / Objective assessment of pathological speech using distribution regression. 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 5050-5054
@inproceedings{e6fabebdb7af4a49bfca7c83c25a8840,
title = "Objective assessment of pathological speech using distribution regression",
abstract = "Objective assessment of pathological speech is an important part of existing systems for automatic diagnosis and treatment of various speech disorders. In this paper, we propose a new regression method for this application. Rather than treating speech samples from each speaker as individual data instances, we treat each speaker's data as a probability distribution. We propose a simple non-parametric learning method to make predictions for out-of-sample speakers based on a probability distance measure to the speakers in the training set. This is in contrast to traditional learning methods that rely on Euclidean distances between individual instances. We evaluate the method on two pathological speech data sets with promising results.",
keywords = "Distribution regression, divergence, objective assessment, speech pathology",
author = "Ming Tu and Visar Berisha and Julie Liss",
year = "2017",
month = "6",
day = "16",
doi = "10.1109/ICASSP.2017.7953118",
language = "English (US)",
pages = "5050--5054",
booktitle = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Objective assessment of pathological speech using distribution regression

AU - Tu, Ming

AU - Berisha, Visar

AU - Liss, Julie

PY - 2017/6/16

Y1 - 2017/6/16

N2 - Objective assessment of pathological speech is an important part of existing systems for automatic diagnosis and treatment of various speech disorders. In this paper, we propose a new regression method for this application. Rather than treating speech samples from each speaker as individual data instances, we treat each speaker's data as a probability distribution. We propose a simple non-parametric learning method to make predictions for out-of-sample speakers based on a probability distance measure to the speakers in the training set. This is in contrast to traditional learning methods that rely on Euclidean distances between individual instances. We evaluate the method on two pathological speech data sets with promising results.

AB - Objective assessment of pathological speech is an important part of existing systems for automatic diagnosis and treatment of various speech disorders. In this paper, we propose a new regression method for this application. Rather than treating speech samples from each speaker as individual data instances, we treat each speaker's data as a probability distribution. We propose a simple non-parametric learning method to make predictions for out-of-sample speakers based on a probability distance measure to the speakers in the training set. This is in contrast to traditional learning methods that rely on Euclidean distances between individual instances. We evaluate the method on two pathological speech data sets with promising results.

KW - Distribution regression

KW - divergence

KW - objective assessment

KW - speech pathology

UR - http://www.scopus.com/inward/record.url?scp=85016309853&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016309853&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7953118

DO - 10.1109/ICASSP.2017.7953118

M3 - Conference contribution

AN - SCOPUS:85016309853

SP - 5050

EP - 5054

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -