2026-09-25T22:57:11Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/80202022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022
Tomaso Poggio.
Ezzat, Tony F. (Tony Farid)
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2005-08-24T22:07:30Z
2005-08-24T22:07:30Z
2002
2002
http://hdl.handle.net/1721.1/8020
52293159
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2002.
Includes bibliographical references (p. 53-58).
I describe how to create with machine learning techniques a generative, videorealistic, speech animation module. A human subject is first recorded using a videocamera as he/she utters a pre-determined speech corpus. After processing the corpus automatically, a visual speech module is learned from the data that is capable of synthesizing the human subject's mouth uttering entirely novel utterances that were not recorded in the original video. The synthesized utterance is re-composited onto a background sequence which contains natural head and eye movement. The final output is videorealistic in the sense that it looks like a video camera recording of the subject. At run time, the input to the system can be either real audio sequences or synthetic audio produced by a text-to-speech system, as long as they have been phonetically aligned. The two key contributions of this work are * a variant of the multidimensional morphable model (MMM) [4] [26] [25] to synthesize new, previously unseen mouth configurations from a small set of mouth image prototypes, * a trajectory synthesis technique based on regularization, which is automatically trained from the recorded video corpus, and which is capable of synthesizing trajectories in MMM space corresponding to any desired utterance. Results are presented on a series of numerical and psychophysical experiments designed to evaluate the synthetic animations.
by Tony Farid Ezzat.
Ph.D.
58 p.
3669478 bytes
3669239 bytes
application/pdf
application/pdf
eng
Massachusetts Institute of Technology
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Trainable videorealistic speech animation
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="7eee1238-636a-47ae-a3ad-573c56dc792f">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Trainable videorealistic speech animation</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2002</PublicationDate>
<Authors>
<Author>
<DisplayName>Ezzat, Tony F. (Tony Farid)</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>I describe how to create with machine learning techniques a generative, videorealistic, speech animation module. A human subject is first recorded using a videocamera as he/she utters a pre-determined speech corpus. After processing the corpus automatically, a visual speech module is learned from the data that is capable of synthesizing the human subject's mouth uttering entirely novel utterances that were not recorded in the original video. The synthesized utterance is re-composited onto a background sequence which contains natural head and eye movement. The final output is videorealistic in the sense that it looks like a video camera recording of the subject. At run time, the input to the system can be either real audio sequences or synthetic audio produced by a text-to-speech system, as long as they have been phonetically aligned. The two key contributions of this work are * a variant of the multidimensional morphable model (MMM) [4] [26] [25] to synthesize new, previously unseen mouth configurations from a small set of mouth image prototypes, * a trajectory synthesis technique based on regularization, which is automatically trained from the recorded video corpus, and which is capable of synthesizing trajectories in MMM space corresponding to any desired utterance. Results are presented on a series of numerical and psychophysical experiments designed to evaluate the synthetic animations.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>