Detecting and analysing spontaneous oral cancer speech in the wild

Bence Mark Halpern; Rob van Son; Michiel W.M. van den Brekel; Odette Scharenborg

doi:10.21437/Interspeech.2020-1598

Detecting and analysing spontaneous oral cancer speech in the wild

Bence Mark Halpern, Rob van Son, Michiel W.M. van den Brekel, Odette Scharenborg

Multimedia Computing

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

11 Citations (Scopus)

Abstract

Oral cancer speech is a disease which impacts more than half a million people worldwide every year. Analysis of oral cancer speech has so far focused on read speech. In this paper, we 1) present and 2) analyse a three-hour long spontaneous oral cancer speech dataset collected from YouTube. 3) We set baselines for an oral cancer speech detection task on this dataset. The analysis of these explainable machine learning baselines shows that sibilants and stop consonants are the most important indicators for spontaneous oral cancer speech detection.

Original language	English
Title of host publication	Proceedings of Interspeech 2020
Publisher	ISCA
Pages	4826 - 4830
Number of pages	5
DOIs	https://doi.org/10.21437/Interspeech.2020-1598
Publication status	Published - 2020
Event	INTERSPEECH 2020 - Shanghai, Shanghai, China Duration: 25 Oct 2020 → 29 Oct 2020

Publication series

Name	Interspeech 2020
Publisher	ISCA
ISSN (Print)	1990-9772

Conference

Conference	INTERSPEECH 2020
Country/Territory	China
City	Shanghai
Period	25/10/20 → 29/10/20

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Corpus
Explainable AI
Oral cancer speech
Pathological speech

Access to Document

10.21437/Interspeech.2020-1598

Cite this

@inproceedings{0e44cd3fbd95460eab22318ef4e6a8db,

title = "Detecting and analysing spontaneous oral cancer speech in the wild",

abstract = "Oral cancer speech is a disease which impacts more than half a million people worldwide every year. Analysis of oral cancer speech has so far focused on read speech. In this paper, we 1) present and 2) analyse a three-hour long spontaneous oral cancer speech dataset collected from YouTube. 3) We set baselines for an oral cancer speech detection task on this dataset. The analysis of these explainable machine learning baselines shows that sibilants and stop consonants are the most important indicators for spontaneous oral cancer speech detection.",

keywords = "Corpus, Explainable AI, Oral cancer speech, Pathological speech",

author = "Halpern, \{Bence Mark\} and \{van Son\}, Rob and \{van den Brekel\}, \{Michiel W.M.\} and Odette Scharenborg",

year = "2020",

doi = "10.21437/Interspeech.2020-1598",

language = "English",

series = "Interspeech 2020",

publisher = "ISCA",

pages = "4826 -- 4830",

booktitle = "Proceedings of Interspeech 2020",

note = "INTERSPEECH 2020 ; Conference date: 25-10-2020 Through 29-10-2020",

}

TY - GEN

T1 - Detecting and analysing spontaneous oral cancer speech in the wild

AU - Halpern, Bence Mark

AU - van Son, Rob

AU - van den Brekel, Michiel W.M.

AU - Scharenborg, Odette

PY - 2020

Y1 - 2020

N2 - Oral cancer speech is a disease which impacts more than half a million people worldwide every year. Analysis of oral cancer speech has so far focused on read speech. In this paper, we 1) present and 2) analyse a three-hour long spontaneous oral cancer speech dataset collected from YouTube. 3) We set baselines for an oral cancer speech detection task on this dataset. The analysis of these explainable machine learning baselines shows that sibilants and stop consonants are the most important indicators for spontaneous oral cancer speech detection.

AB - Oral cancer speech is a disease which impacts more than half a million people worldwide every year. Analysis of oral cancer speech has so far focused on read speech. In this paper, we 1) present and 2) analyse a three-hour long spontaneous oral cancer speech dataset collected from YouTube. 3) We set baselines for an oral cancer speech detection task on this dataset. The analysis of these explainable machine learning baselines shows that sibilants and stop consonants are the most important indicators for spontaneous oral cancer speech detection.

KW - Corpus

KW - Explainable AI

KW - Oral cancer speech

KW - Pathological speech

UR - https://www.scopus.com/pages/publications/85098230992

U2 - 10.21437/Interspeech.2020-1598

DO - 10.21437/Interspeech.2020-1598

M3 - Conference contribution

T3 - Interspeech 2020

SP - 4826

EP - 4830

BT - Proceedings of Interspeech 2020

PB - ISCA

T2 - INTERSPEECH 2020

Y2 - 25 October 2020 through 29 October 2020

ER -

Detecting and analysing spontaneous oral cancer speech in the wild

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this