Emotion Dependent Facial Animation from Affective Speech

In human-to-computer interaction, facial animation in synchrony with affective speech can deliver more naturalistic conversational agents. In this paper, we present a two-stage deep learning approach for affective speech driven facial shape animation. In the first stage, we classify affective speech...

Full description

Saved in:
Bibliographic Details
Main Authors: Sadiq, Rizwan, Asadiabadi, Sasan, Erzin, Engin
Format: Conference Proceeding
Language:English
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 6
container_issue
container_start_page 1
container_title
container_volume
creator Sadiq, Rizwan
Asadiabadi, Sasan
Erzin, Engin
description In human-to-computer interaction, facial animation in synchrony with affective speech can deliver more naturalistic conversational agents. In this paper, we present a two-stage deep learning approach for affective speech driven facial shape animation. In the first stage, we classify affective speech into seven emotion categories. In the second stage, we train separate deep estimators within each emotion category to synthesize facial shape from the affective speech. Objective and subjective evaluations are performed over the SAVEE dataset. The proposed emotion dependent facial shape model performs better in terms of the Mean Squared Error (MSE) loss and in generating the landmark animations, as compared to training a universal model regardless of the emotion.
doi_str_mv 10.1109/MMSP48831.2020.9287086
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9287086</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9287086</ieee_id><sourcerecordid>9287086</sourcerecordid><originalsourceid>FETCH-LOGICAL-i251t-86abc0c6628f564983c508180c345c5e992905f3afa180ee7ba93f2ff692c50f3</originalsourceid><addsrcrecordid>eNotT11LwzAUjYLgmP0FgvQPtN7cNMnNY5mbChsK0-eRxRuMrB-0RfDfW3RPB845nA8h7iSUUoK73-32rxWRkiUCQumQLJC5EJmzJC2SdApBX4oFVlYVyiBdi2wcvwBAGqwIYSFo3XRT6tr8gXtuP7id8o0PyZ_yuk2N_5Pi0DV5HSOHKX1zvu-Zw-eNuIr-NHJ2xqV436zfVk_F9uXxeVVvi4RaTgUZfwwQzFwetakcqaCBJEFQlQ6anUMHOiof_Uwy26N3KmKMxuHsjGopbv9zEzMf-mEeNfwczl_VL5f7R40</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Emotion Dependent Facial Animation from Affective Speech</title><source>IEEE Xplore All Conference Series</source><creator>Sadiq, Rizwan ; Asadiabadi, Sasan ; Erzin, Engin</creator><creatorcontrib>Sadiq, Rizwan ; Asadiabadi, Sasan ; Erzin, Engin</creatorcontrib><description>In human-to-computer interaction, facial animation in synchrony with affective speech can deliver more naturalistic conversational agents. In this paper, we present a two-stage deep learning approach for affective speech driven facial shape animation. In the first stage, we classify affective speech into seven emotion categories. In the second stage, we train separate deep estimators within each emotion category to synthesize facial shape from the affective speech. Objective and subjective evaluations are performed over the SAVEE dataset. The proposed emotion dependent facial shape model performs better in terms of the Mean Squared Error (MSE) loss and in generating the landmark animations, as compared to training a universal model regardless of the emotion.</description><identifier>EISSN: 2473-3628</identifier><identifier>EISBN: 9781728193205</identifier><identifier>EISBN: 1728193206</identifier><identifier>DOI: 10.1109/MMSP48831.2020.9287086</identifier><language>eng</language><publisher>IEEE</publisher><ispartof>2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP), 2020, p.1-6</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9287086$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9287086$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Sadiq, Rizwan</creatorcontrib><creatorcontrib>Asadiabadi, Sasan</creatorcontrib><creatorcontrib>Erzin, Engin</creatorcontrib><title>Emotion Dependent Facial Animation from Affective Speech</title><title>2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)</title><addtitle>MMSP</addtitle><description>In human-to-computer interaction, facial animation in synchrony with affective speech can deliver more naturalistic conversational agents. In this paper, we present a two-stage deep learning approach for affective speech driven facial shape animation. In the first stage, we classify affective speech into seven emotion categories. In the second stage, we train separate deep estimators within each emotion category to synthesize facial shape from the affective speech. Objective and subjective evaluations are performed over the SAVEE dataset. The proposed emotion dependent facial shape model performs better in terms of the Mean Squared Error (MSE) loss and in generating the landmark animations, as compared to training a universal model regardless of the emotion.</description><issn>2473-3628</issn><isbn>9781728193205</isbn><isbn>1728193206</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2020</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotT11LwzAUjYLgmP0FgvQPtN7cNMnNY5mbChsK0-eRxRuMrB-0RfDfW3RPB845nA8h7iSUUoK73-32rxWRkiUCQumQLJC5EJmzJC2SdApBX4oFVlYVyiBdi2wcvwBAGqwIYSFo3XRT6tr8gXtuP7id8o0PyZ_yuk2N_5Pi0DV5HSOHKX1zvu-Zw-eNuIr-NHJ2xqV436zfVk_F9uXxeVVvi4RaTgUZfwwQzFwetakcqaCBJEFQlQ6anUMHOiof_Uwy26N3KmKMxuHsjGopbv9zEzMf-mEeNfwczl_VL5f7R40</recordid><startdate>20200921</startdate><enddate>20200921</enddate><creator>Sadiq, Rizwan</creator><creator>Asadiabadi, Sasan</creator><creator>Erzin, Engin</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20200921</creationdate><title>Emotion Dependent Facial Animation from Affective Speech</title><author>Sadiq, Rizwan ; Asadiabadi, Sasan ; Erzin, Engin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i251t-86abc0c6628f564983c508180c345c5e992905f3afa180ee7ba93f2ff692c50f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2020</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Sadiq, Rizwan</creatorcontrib><creatorcontrib>Asadiabadi, Sasan</creatorcontrib><creatorcontrib>Erzin, Engin</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sadiq, Rizwan</au><au>Asadiabadi, Sasan</au><au>Erzin, Engin</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Emotion Dependent Facial Animation from Affective Speech</atitle><btitle>2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)</btitle><stitle>MMSP</stitle><date>2020-09-21</date><risdate>2020</risdate><spage>1</spage><epage>6</epage><pages>1-6</pages><eissn>2473-3628</eissn><eisbn>9781728193205</eisbn><eisbn>1728193206</eisbn><abstract>In human-to-computer interaction, facial animation in synchrony with affective speech can deliver more naturalistic conversational agents. In this paper, we present a two-stage deep learning approach for affective speech driven facial shape animation. In the first stage, we classify affective speech into seven emotion categories. In the second stage, we train separate deep estimators within each emotion category to synthesize facial shape from the affective speech. Objective and subjective evaluations are performed over the SAVEE dataset. The proposed emotion dependent facial shape model performs better in terms of the Mean Squared Error (MSE) loss and in generating the landmark animations, as compared to training a universal model regardless of the emotion.</abstract><pub>IEEE</pub><doi>10.1109/MMSP48831.2020.9287086</doi><tpages>6</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2473-3628
ispartof 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP), 2020, p.1-6
issn 2473-3628
language eng
recordid cdi_ieee_primary_9287086
source IEEE Xplore All Conference Series
title Emotion Dependent Facial Animation from Affective Speech
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T15%3A37%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Emotion%20Dependent%20Facial%20Animation%20from%20Affective%20Speech&rft.btitle=2020%20IEEE%2022nd%20International%20Workshop%20on%20Multimedia%20Signal%20Processing%20(MMSP)&rft.au=Sadiq,%20Rizwan&rft.date=2020-09-21&rft.spage=1&rft.epage=6&rft.pages=1-6&rft.eissn=2473-3628&rft_id=info:doi/10.1109/MMSP48831.2020.9287086&rft.eisbn=9781728193205&rft.eisbn_list=1728193206&rft_dat=%3Cieee_CHZPO%3E9287086%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i251t-86abc0c6628f564983c508180c345c5e992905f3afa180ee7ba93f2ff692c50f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9287086&rfr_iscdi=true