Expressive Visual Text-To-Speech Using Active Appearance Models

被引：40

作者：

Anderson, Robert ^{[1
]}

Stenger, Bjoern ^{[2
]}

Wan, Vincent ^{[2
]}

Cipolla, Roberto ^{[1
]}

机构：

[1] Univ Cambridge, Dept Engn, Cambridge, England

[2] Toshiba Res Europe, Cambridge, England

来源：

2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2013年

关键词：

SYNTHETIC TALKING FACES;

D O I：

10.1109/CVPR.2013.434

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a complete system for expressive visual text-to-speech (VTTS), which is capable of producing expressive output, in the form of a 'talking head', given an input text and a set of continuous expression weights. The face is modeled using an active appearance model (AAM), and several extensions are proposed which make it more applicable to the task of VTTS. The model allows for normalization with respect to both pose and blink state which significantly reduces artifacts in the resulting synthesized sequences. We demonstrate quantitative improvements in terms of reconstruction error over a million frames, as well as in large-scale user studies, comparing the output of different systems.

引用

页码：3382 / 3389

页数：8

共 50 条

[41] Multilingual text-to-speech synthesis
Black, AW
Lenzo, KA
2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL III, PROCEEDINGS: IMAGE AND MULTIDIMENSIONAL SIGNAL PROCESSING SPECIAL SESSIONS, 2004, : 761 - 764
[42] Slovenian text-to-speech system
Sef, T
ISCAS 2000: IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS - PROCEEDINGS, VOL V: EMERGING TECHNOLOGIES FOR THE 21ST CENTURY, 2000, : 41 - 44
[43] Indonesian Text-To-Speech System Using Syllable Concatenation: Speech Optimization
Mengko, Richard
Ayuningtyas, Aulia
PROCEEDINGS OF 2013 3RD INTERNATIONAL CONFERENCE ON INSTRUMENTATION, COMMUNICATIONS, INFORMATION TECHNOLOGY, AND BIOMEDICAL ENGINEERING (ICICI-BME), 2013, : 412 - 415
[44] WhiteboardVCR - a presentation tool using text-to-speech agents
Chong, NST
Tosukhowong, P
Sakauchi, M
IEEE INTERNATIONAL CONFERENCE ON ADVANCED LEARNING TECHNOLOGIES, PROCEEDINGS, 2001, : 319 - 322
[45] A Hakka text-to-speech system
Yu, Hsiu-Min
Hwang, Hsin-Te
Lin, Dong-Yi
Chen, Sin-Horng
CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2006, 4274 : 241 - +
[46] TEXT-TO-SPEECH CONVERSION TECHNOLOGY
OMALLEY, MH
COMPUTER, 1990, 23 (08) : 17 - 23
[47] Improving text-to-speech synthesis
Tatham, M
Lewis, E
ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 1856 - 1859
[48] EPIC TTS Models: Empirical Pruning Investigations Characterizing Text-To-Speech Models
Lam, Perry
Zhang, Huayun
Chen, Nancy F.
Sisman, Berrak
INTERSPEECH 2022, 2022, : 823 - 827
[49] Latvian Text-to-Speech Synthesizer
Pinnis, Marcis
Auzina, Ilze
HUMAN LANGUAGE TECHNOLOGIES - THE BALTIC PERSPECTIVE, 2010, 219 : 69 - 72
[50] Towards Universal Text-to-Speech
Yang, Jingzhou
He, Lei
INTERSPEECH 2020, 2020, : 3171 - 3175

← 1 2 3 4 5 →