Emotional recognition from the speech signal for a virtual education agent

Andrew Jason Tickle; S Raghu; Mark Elshaw

doi:10.1088/1742-6596/450/1/012053

Emotional recognition from the speech signal for a virtual education agent

Andrew Jason Tickle
, S Raghu
, Mark Elshaw

Research output: Contribution to journal › Conference article › peer-review

19 Citations (Scopus)

144 Downloads (Pure)

Abstract

This paper explores the extraction of features from the speech wave to perform intelligent emotion recognition. A feature extract tool (openSmile) was used to obtain a baseline set of 998 acoustic features from a set of emotional speech recordings from amicrophone. The initial features were reduced to the most important ones so recognition ofemotions using a supervised neural network could be performed. Given that the future use of virtual education agents lies with making the agents more interactive, developing agents with the capability to recognise and adapt to the emotional state of humans is an important step.

Original language	English
Article number	012053
Number of pages	7
Journal	Journal of Physics: Conference Series
Volume	450
DOIs	https://doi.org/10.1088/1742-6596/450/1/012053
Publication status	Published - 2013
Event	Sensors & Their Applications XVII 2013 - Dubrovnik, Croatia Duration: 16 Sept 2013 → 18 Sept 2013 Conference number: 17

Bibliographical note

Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.

Access to Document

10.1088/1742-6596/450/1/012053Licence: CC BY

PublishedFinal published version, 1 MBLicence: CC BY

Cite this

@article{f01888602b094b668f104a8b9e90479d,

title = "Emotional recognition from the speech signal for a virtual education agent",

abstract = "This paper explores the extraction of features from the speech wave to perform intelligent emotion recognition. A feature extract tool (openSmile) was used to obtain a baseline set of 998 acoustic features from a set of emotional speech recordings from amicrophone. The initial features were reduced to the most important ones so recognition ofemotions using a supervised neural network could be performed. Given that the future use of virtual education agents lies with making the agents more interactive, developing agents with the capability to recognise and adapt to the emotional state of humans is an important step.",

author = "Tickle, \{Andrew Jason\} and S Raghu and Mark Elshaw",

note = "Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.; Sensors \& Their Applications XVII 2013 ; Conference date: 16-09-2013 Through 18-09-2013",

year = "2013",

doi = "10.1088/1742-6596/450/1/012053",

language = "English",

volume = "450",

journal = "Journal of Physics: Conference Series",

issn = "1742-6588",

publisher = "IOP Publishing Ltd.",

}

TY - JOUR

T1 - Emotional recognition from the speech signal for a virtual education agent

AU - Tickle, Andrew Jason

AU - Raghu, S

AU - Elshaw, Mark

N1 - Conference code: 17

PY - 2013

Y1 - 2013

N2 - This paper explores the extraction of features from the speech wave to perform intelligent emotion recognition. A feature extract tool (openSmile) was used to obtain a baseline set of 998 acoustic features from a set of emotional speech recordings from amicrophone. The initial features were reduced to the most important ones so recognition ofemotions using a supervised neural network could be performed. Given that the future use of virtual education agents lies with making the agents more interactive, developing agents with the capability to recognise and adapt to the emotional state of humans is an important step.

AB - This paper explores the extraction of features from the speech wave to perform intelligent emotion recognition. A feature extract tool (openSmile) was used to obtain a baseline set of 998 acoustic features from a set of emotional speech recordings from amicrophone. The initial features were reduced to the most important ones so recognition ofemotions using a supervised neural network could be performed. Given that the future use of virtual education agents lies with making the agents more interactive, developing agents with the capability to recognise and adapt to the emotional state of humans is an important step.

U2 - 10.1088/1742-6596/450/1/012053

DO - 10.1088/1742-6596/450/1/012053

M3 - Conference article

SN - 1742-6588

VL - 450

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

M1 - 012053

T2 - Sensors & Their Applications XVII 2013

Y2 - 16 September 2013 through 18 September 2013

ER -

Emotional recognition from the speech signal for a virtual education agent

Abstract

Bibliographical note

Access to Document

Fingerprint

Cite this