Automatic speaker’s role classification with a bottom-up acoustic feature selection

Vered Silber-Varod; Anat Lerner; Oliver Jokisch

Automatic speaker’s role classification with a bottom-up acoustic feature selection

Vered Silber-Varod, Anat Lerner, Oliver Jokisch

Computer Science discipline

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The objective of the current study is to automatically identify
the role played by the speaker in a dialogue. By using machine
learning procedures over acoustic feature, we wish to
automatically trace the footprints of this information through
the speech signal. The acoustic feature set was selected from a large statistic-based feature sets including 1,583 dimension features. The analysis is carried out on interactive dialogues of a Map Task setting. The paper first describes the methodology of choosing the 100 most effective attributes among the 1,583 features that were extracted, and then presents the classification results test of the same speaker in two different roles, and a gender-based classification. Results show an average of a 71% classification rate of the role the same speaker played, 65% for all women together and 65% for all men together.

Original language	American English
Title of host publication	Proceedings of the 2017 International Workshop on Grounding Language Understanding
Pages	52-56
Number of pages	5
State	Published - 2017
Event	Grounding Language Understanding - KTH Royal Institute of Technology, Stockholm, Sweden Duration: 25 Aug 2017 → 25 Aug 2017

Conference

Conference	Grounding Language Understanding
Abbreviated title	GLU2017
Country/Territory	Sweden
City	Stockholm
Period	25/08/17 → 25/08/17

Access to Document

https://www.researchgate.net/profile/Vered-Silber-Varod/publication/319183418_Automatic_Speaker's_Role_Classification_With_a_Bottom-up_Acoustic_Feature_Selection/links/59993c570f7e9b3edb1700cc/Automatic-Speakers-Role-Classification-With-a-Bottom-up-Acoustic-Feature-Selection.pdf

Cite this

Silber-Varod, V., Lerner, A., & Jokisch, O. (2017). Automatic speaker’s role classification with a bottom-up acoustic feature selection. In Proceedings of the 2017 International Workshop on Grounding Language Understanding (pp. 52-56) https://www.researchgate.net/profile/Vered-Silber-Varod/publication/319183418_Automatic_Speaker's_Role_Classification_With_a_Bottom-up_Acoustic_Feature_Selection/links/59993c570f7e9b3edb1700cc/Automatic-Speakers-Role-Classification-With-a-Bottom-up-Acoustic-Feature-Selection.pdf

@inproceedings{fe20c2aba2884bc5bfcfa2f8ff2b1ac9,

title = "Automatic speaker{\textquoteright}s role classification with a bottom-up acoustic feature selection",

abstract = "The objective of the current study is to automatically identifythe role played by the speaker in a dialogue. By using machinelearning procedures over acoustic feature, we wish toautomatically trace the footprints of this information throughthe speech signal. The acoustic feature set was selected from a large statistic-based feature sets including 1,583 dimension features. The analysis is carried out on interactive dialogues of a Map Task setting. The paper first describes the methodology of choosing the 100 most effective attributes among the 1,583 features that were extracted, and then presents the classification results test of the same speaker in two different roles, and a gender-based classification. Results show an average of a 71% classification rate of the role the same speaker played, 65% for all women together and 65% for all men together.",

author = "Vered Silber-Varod and Anat Lerner and Oliver Jokisch",

year = "2017",

language = "American English",

pages = "52--56",

booktitle = "Proceedings of the 2017 International Workshop on Grounding Language Understanding",

note = "Grounding Language Understanding , GLU2017 ; Conference date: 25-08-2017 Through 25-08-2017",

}

Silber-Varod, V, Lerner, A & Jokisch, O 2017, Automatic speaker’s role classification with a bottom-up acoustic feature selection. in Proceedings of the 2017 International Workshop on Grounding Language Understanding. pp. 52-56, Grounding Language Understanding , Stockholm, Sweden, 25/08/17. <https://www.researchgate.net/profile/Vered-Silber-Varod/publication/319183418_Automatic_Speaker's_Role_Classification_With_a_Bottom-up_Acoustic_Feature_Selection/links/59993c570f7e9b3edb1700cc/Automatic-Speakers-Role-Classification-With-a-Bottom-up-Acoustic-Feature-Selection.pdf>

TY - GEN

T1 - Automatic speaker’s role classification with a bottom-up acoustic feature selection

AU - Silber-Varod, Vered

AU - Lerner, Anat

AU - Jokisch, Oliver

PY - 2017

Y1 - 2017

N2 - The objective of the current study is to automatically identifythe role played by the speaker in a dialogue. By using machinelearning procedures over acoustic feature, we wish toautomatically trace the footprints of this information throughthe speech signal. The acoustic feature set was selected from a large statistic-based feature sets including 1,583 dimension features. The analysis is carried out on interactive dialogues of a Map Task setting. The paper first describes the methodology of choosing the 100 most effective attributes among the 1,583 features that were extracted, and then presents the classification results test of the same speaker in two different roles, and a gender-based classification. Results show an average of a 71% classification rate of the role the same speaker played, 65% for all women together and 65% for all men together.

AB - The objective of the current study is to automatically identifythe role played by the speaker in a dialogue. By using machinelearning procedures over acoustic feature, we wish toautomatically trace the footprints of this information throughthe speech signal. The acoustic feature set was selected from a large statistic-based feature sets including 1,583 dimension features. The analysis is carried out on interactive dialogues of a Map Task setting. The paper first describes the methodology of choosing the 100 most effective attributes among the 1,583 features that were extracted, and then presents the classification results test of the same speaker in two different roles, and a gender-based classification. Results show an average of a 71% classification rate of the role the same speaker played, 65% for all women together and 65% for all men together.

M3 - Conference contribution

SP - 52

EP - 56

BT - Proceedings of the 2017 International Workshop on Grounding Language Understanding

T2 - Grounding Language Understanding

Y2 - 25 August 2017 through 25 August 2017

ER -

Automatic speaker’s role classification with a bottom-up acoustic feature selection

Abstract

Conference

Access to Document

Fingerprint

Cite this