@article{ ISI:000256679700002,
Author = {Sargin, Mehmet Emre and Yemez, Yuecel and Erzin, Engin and Tekalp, A.
   Murat},
Title = {{Analysis of head gesture and prosody patterns for prosody-driven
   head-gesture animation}},
Journal = {{IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE}},
Year = {{2008}},
Volume = {{30}},
Number = {{8}},
Pages = {{1330-1345}},
Month = {{AUG}},
Abstract = {{We propose a new two-stage framework for joint analysis of head gesture
   and speech prosody patterns of a speaker toward automatic realistic
   synthesis of head gestures from speech prosody. In the first stage
   analysis, we perform Hidden Markov Model (HMM)-based unsupervised
   temporal segmentation of head gesture and speech prosody features
   separately to determine elementary head gesture and speech prosody
   patterns, respectively, for a particular speaker. In the second stage,
   joint analysis of correlations between these elementary head gesture and
   prosody patterns is performed using Multistream HMMs to determine an
   audio-visual mapping model. The resulting audio-visual mapping model is
   then employed to synthesize natural head gestures from arbitrary input
   test speech given a head model for the speaker. In the synthesis stage,
   the audio-visual mapping model is used to predict a sequence of gesture
   patterns from the prosody pattern sequence computed for the input test
   speech. The Euler angles associated with each gesture pattern are then
   applied to animate the speaker head model. Objective and subjective
   evaluations indicate that the proposed synthesis by analysis scheme
   provides natural looking head gestures for the speaker with any input
   test speech, as well as in ``prosody transplant{''} and ``gesture
   transplant{''} scenarios.}},
DOI = {{10.1109/TPAMI.2007.70797}},
ISSN = {{0162-8828}},
ResearcherID-Numbers = {{Erzin, Engin/H-1716-2011}},
ORCID-Numbers = {{Erzin, Engin/0000-0002-2715-2368}},
Unique-ID = {{ISI:000256679700002}},
}

{"_id":"ks28BSBdeJ6zifJMi","bibbaseid":"sargin-yemez-erzin-tekalp-analysisofheadgestureandprosodypatternsforprosodydrivenheadgestureanimation-2008","downloads":0,"creationDate":"2015-12-09T21:23:15.495Z","title":"Analysis of head gesture and prosody patterns for prosody-driven head-gesture animation","author_short":["Sargin, M. E.","Yemez, Y.","Erzin, E.","Tekalp, A. M."],"year":2008,"bibtype":"article","biburl":"http://home.ku.edu.tr/~eerzin/pubs/mvgl.bib","bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Sargin"],"firstnames":["Mehmet","Emre"],"suffixes":[]},{"propositions":[],"lastnames":["Yemez"],"firstnames":["Yuecel"],"suffixes":[]},{"propositions":[],"lastnames":["Erzin"],"firstnames":["Engin"],"suffixes":[]},{"propositions":[],"lastnames":["Tekalp"],"firstnames":["A.","Murat"],"suffixes":[]}],"title":"Analysis of head gesture and prosody patterns for prosody-driven head-gesture animation","journal":"IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE","year":"2008","volume":"30","number":"8","pages":"1330-1345","month":"AUG","abstract":"We propose a new two-stage framework for joint analysis of head gesture and speech prosody patterns of a speaker toward automatic realistic synthesis of head gestures from speech prosody. In the first stage analysis, we perform Hidden Markov Model (HMM)-based unsupervised temporal segmentation of head gesture and speech prosody features separately to determine elementary head gesture and speech prosody patterns, respectively, for a particular speaker. In the second stage, joint analysis of correlations between these elementary head gesture and prosody patterns is performed using Multistream HMMs to determine an audio-visual mapping model. The resulting audio-visual mapping model is then employed to synthesize natural head gestures from arbitrary input test speech given a head model for the speaker. In the synthesis stage, the audio-visual mapping model is used to predict a sequence of gesture patterns from the prosody pattern sequence computed for the input test speech. The Euler angles associated with each gesture pattern are then applied to animate the speaker head model. Objective and subjective evaluations indicate that the proposed synthesis by analysis scheme provides natural looking head gestures for the speaker with any input test speech, as well as in ``prosody transplant'' and ``gesture transplant'' scenarios.","doi":"10.1109/TPAMI.2007.70797","issn":"0162-8828","researcherid-numbers":"Erzin, Engin/H-1716-2011","orcid-numbers":"Erzin, Engin/0000-0002-2715-2368","unique-id":"ISI:000256679700002","bibtex":"@article{ ISI:000256679700002,\nAuthor = {Sargin, Mehmet Emre and Yemez, Yuecel and Erzin, Engin and Tekalp, A.\n Murat},\nTitle = {{Analysis of head gesture and prosody patterns for prosody-driven\n head-gesture animation}},\nJournal = {{IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE}},\nYear = {{2008}},\nVolume = {{30}},\nNumber = {{8}},\nPages = {{1330-1345}},\nMonth = {{AUG}},\nAbstract = {{We propose a new two-stage framework for joint analysis of head gesture\n and speech prosody patterns of a speaker toward automatic realistic\n synthesis of head gestures from speech prosody. In the first stage\n analysis, we perform Hidden Markov Model (HMM)-based unsupervised\n temporal segmentation of head gesture and speech prosody features\n separately to determine elementary head gesture and speech prosody\n patterns, respectively, for a particular speaker. In the second stage,\n joint analysis of correlations between these elementary head gesture and\n prosody patterns is performed using Multistream HMMs to determine an\n audio-visual mapping model. The resulting audio-visual mapping model is\n then employed to synthesize natural head gestures from arbitrary input\n test speech given a head model for the speaker. In the synthesis stage,\n the audio-visual mapping model is used to predict a sequence of gesture\n patterns from the prosody pattern sequence computed for the input test\n speech. The Euler angles associated with each gesture pattern are then\n applied to animate the speaker head model. Objective and subjective\n evaluations indicate that the proposed synthesis by analysis scheme\n provides natural looking head gestures for the speaker with any input\n test speech, as well as in ``prosody transplant{''} and ``gesture\n transplant{''} scenarios.}},\nDOI = {{10.1109/TPAMI.2007.70797}},\nISSN = {{0162-8828}},\nResearcherID-Numbers = {{Erzin, Engin/H-1716-2011}},\nORCID-Numbers = {{Erzin, Engin/0000-0002-2715-2368}},\nUnique-ID = {{ISI:000256679700002}},\n}\n\n","author_short":["Sargin, M. E.","Yemez, Y.","Erzin, E.","Tekalp, A. M."],"key":"ISI:000256679700002","id":"ISI:000256679700002","bibbaseid":"sargin-yemez-erzin-tekalp-analysisofheadgestureandprosodypatternsforprosodydrivenheadgestureanimation-2008","role":"author","urls":{},"metadata":{"authorlinks":{"erzin, e":"http://home.ku.edu.tr/~eerzin/pubs/index6.html"}},"downloads":0,"html":""},"search_terms":["analysis","head","gesture","prosody","patterns","prosody","driven","head","gesture","animation","sargin","yemez","erzin","tekalp"],"keywords":[],"authorIDs":["56689bc2b3110c264a000354","566927fe71adeb5a05000063","s4rze5RZET4EY5wXY"],"dataSources":["P7SB4qiBxZPhjXYRW","eoMYcQtZLjtLCGT3K"]}