Evrişimsel Aǧlar ile Sesten 3B Yüz Animasyonu Üretilmesi

Turker Unlu; Arda Inceoglu; Erkan Ozgur Yilmaz; Sanem Sariel

doi:10.1109/SIU55565.2022.9864734

Evrişimsel Aǧlar ile Sesten 3B Yüz Animasyonu Üretilmesi

Translated title of the contribution: 3D Face Animation Generation from Audio Using Convolutional Networks

Turker Unlu, Arda Inceoglu, Erkan Ozgur Yilmaz, Sanem Sariel

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

Abstract

3D facial animation generation from audio problem is drawing attention as it is demanded for generating artificial characters in games and movies. In the literature, several studies address this problem. However, the generated facial animations are far away from being realistic. In this work, we represent faces with Facial Action Coding System (FACS) and collect a 37-minute-long dataset. We develop convolutional and transformer based models. It is observed that the trained model is able to generate animations that can be used in video games and virtual reality applications, even with novel speaker audio data of speakers it has never seen in the training data.

Translated title of the contribution	3D Face Animation Generation from Audio Using Convolutional Networks
Original language	Turkish
Title of host publication	2022 30th Signal Processing and Communications Applications Conference, SIU 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665450928
DOIs	https://doi.org/10.1109/SIU55565.2022.9864734
Publication status	Published - 2022
Event	30th Signal Processing and Communications Applications Conference, SIU 2022 - Safranbolu, Turkey Duration: 15 May 2022 → 18 May 2022

Publication series

Name	2022 30th Signal Processing and Communications Applications Conference, SIU 2022

Conference

Conference	30th Signal Processing and Communications Applications Conference, SIU 2022
Country/Territory	Turkey
City	Safranbolu
Period	15/05/22 → 18/05/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Access to Document

10.1109/SIU55565.2022.9864734

Cite this

Unlu, T., Inceoglu, A., Yilmaz, E. O., & Sariel, S. (2022). Evrişimsel Aǧlar ile Sesten 3B Yüz Animasyonu Üretilmesi. In 2022 30th Signal Processing and Communications Applications Conference, SIU 2022 (2022 30th Signal Processing and Communications Applications Conference, SIU 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIU55565.2022.9864734

@inproceedings{06e2b975189f4c879fb5ebbfe4842944,

title = "Evri{\c s}imsel Aǧlar ile Sesten 3B Y{\"u}z Animasyonu {\"U}retilmesi",

abstract = "3D facial animation generation from audio problem is drawing attention as it is demanded for generating artificial characters in games and movies. In the literature, several studies address this problem. However, the generated facial animations are far away from being realistic. In this work, we represent faces with Facial Action Coding System (FACS) and collect a 37-minute-long dataset. We develop convolutional and transformer based models. It is observed that the trained model is able to generate animations that can be used in video games and virtual reality applications, even with novel speaker audio data of speakers it has never seen in the training data.",

keywords = "3D Face Animation from Audio, Deep Learning, Speech Processing",

author = "Turker Unlu and Arda Inceoglu and Yilmaz, {Erkan Ozgur} and Sanem Sariel",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 30th Signal Processing and Communications Applications Conference, SIU 2022 ; Conference date: 15-05-2022 Through 18-05-2022",

year = "2022",

doi = "10.1109/SIU55565.2022.9864734",

language = "T{\"u}rk{\c c}e",

series = "2022 30th Signal Processing and Communications Applications Conference, SIU 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 30th Signal Processing and Communications Applications Conference, SIU 2022",

address = "United States",

}

Unlu, T, Inceoglu, A, Yilmaz, EO & Sariel, S 2022, Evrişimsel Aǧlar ile Sesten 3B Yüz Animasyonu Üretilmesi. in 2022 30th Signal Processing and Communications Applications Conference, SIU 2022. 2022 30th Signal Processing and Communications Applications Conference, SIU 2022, Institute of Electrical and Electronics Engineers Inc., 30th Signal Processing and Communications Applications Conference, SIU 2022, Safranbolu, Turkey, 15/05/22. https://doi.org/10.1109/SIU55565.2022.9864734

Evrişimsel Aǧlar ile Sesten 3B Yüz Animasyonu Üretilmesi. / Unlu, Turker; Inceoglu, Arda; Yilmaz, Erkan Ozgur et al.
2022 30th Signal Processing and Communications Applications Conference, SIU 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 30th Signal Processing and Communications Applications Conference, SIU 2022).

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

TY - GEN

T1 - Evrişimsel Aǧlar ile Sesten 3B Yüz Animasyonu Üretilmesi

AU - Unlu, Turker

AU - Inceoglu, Arda

AU - Yilmaz, Erkan Ozgur

AU - Sariel, Sanem

PY - 2022

Y1 - 2022

N2 - 3D facial animation generation from audio problem is drawing attention as it is demanded for generating artificial characters in games and movies. In the literature, several studies address this problem. However, the generated facial animations are far away from being realistic. In this work, we represent faces with Facial Action Coding System (FACS) and collect a 37-minute-long dataset. We develop convolutional and transformer based models. It is observed that the trained model is able to generate animations that can be used in video games and virtual reality applications, even with novel speaker audio data of speakers it has never seen in the training data.

AB - 3D facial animation generation from audio problem is drawing attention as it is demanded for generating artificial characters in games and movies. In the literature, several studies address this problem. However, the generated facial animations are far away from being realistic. In this work, we represent faces with Facial Action Coding System (FACS) and collect a 37-minute-long dataset. We develop convolutional and transformer based models. It is observed that the trained model is able to generate animations that can be used in video games and virtual reality applications, even with novel speaker audio data of speakers it has never seen in the training data.

KW - 3D Face Animation from Audio

KW - Deep Learning

KW - Speech Processing

UR - http://www.scopus.com/inward/record.url?scp=85138707613&partnerID=8YFLogxK

U2 - 10.1109/SIU55565.2022.9864734

DO - 10.1109/SIU55565.2022.9864734

M3 - Konferans katkısı

AN - SCOPUS:85138707613

T3 - 2022 30th Signal Processing and Communications Applications Conference, SIU 2022

BT - 2022 30th Signal Processing and Communications Applications Conference, SIU 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 30th Signal Processing and Communications Applications Conference, SIU 2022

Y2 - 15 May 2022 through 18 May 2022

ER -

Evrişimsel Aǧlar ile Sesten 3B Yüz Animasyonu Üretilmesi

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this