全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于生理舌头模型的语音可视化系统

DOI: 10.11834/jig.20150911

Keywords: 语音可视化,舌头模型,人脸动画,舌头动画,物理仿真

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的目前针对舌头的语音同步动画技术还未得到广泛的研究。在此背景下,提出了一种基于生理模型的舌头动画合成方法。方法首先构建了一个精细的、能够在肌肉激励下产生逼真舌头变形的舌头生理模型;其次利用该舌头模型合成了大量的舌头运动样本,并据此通过学习得到一个从肌肉激励到舌头轮廓的转换模型;然后对采集的动态2维舌头轮廓数据进行运动参数估计以得到与音素对应的体素(肌肉激励序列和刚体位移序列);最后将体素按一定的排列方式输入到舌头生理模型进行仿真以生成相应的舌头动画。结果该系统可以合成听觉效果逼真的语音和视觉效果逼真且与合成语音同步的舌头动画。结论本文方法可以根据汉语普通话或其他语言的2维舌头轮廓数据构建音素―体素数据库,并据此合成该语言对应的高真实感的3维舌头动画。

References

[1]  Parke F I. Computer generated animation of faces [C]//Proceedings of the ACM Annual Conference. New York: ACM Press, 1972: 451-457. [DOI: 10.1145/800193.569955]
[2]  Waters K. A muscle model for animation three-dimensional facial expression [C]// Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques. New York: ACM Press, 1987: 17-24. [DOI: 10.1145/37401.37405]
[3]  Sanguineti V, Laboissiere R, Payan Y. A control model of human tongue movements in speech [J]. Biological Cybernetics, 1997, 77(1): 11-22. [DOI: 10.1007/s004220050362]
[4]  Fujita S, Dang J, Suzuki N, et al. A computational tongue model and its clinical application [J]. Oral Science International, 2007, 4(2): 97-109. [DOI: 10.1016/S1348-8643(07)80004-8]
[5]  Cohen M M, Massaro D W. Modeling coarticulation in synthetic visual speech [M]. Models and Techniques in Computer Animation. Berlin: Springer, 1993: 139-156. [DOI: 10.1007/ 978-4-431-66911-1_13]
[6]  Sikora T. The MPEG-4 video standard verification model [J]. IEEE Transactions on Circuits and Systems for Video Technology, 1997, 7(1): 19-31. [DOI: 10.1109/76.554415]
[7]  Badin P, Bailly G, Reveret L, et al. Three-dimensional linear articulatory modeling of tongue, lips and face, based on MRI and video images [J]. Journal of Phonetics, 2002, 30(3): 533-553. [DOI: doi:10.1006/jpho.2002.0166]
[8]  Engwall O. A 3d tongue model based on MRI data[C]//Proceedings of the 6th IEEE International Conference on Spoken Language Processing. Beijing, China: IEEE Computer Society, 2000: 901-904.
[9]  Wilhelms-Tricarico R. Physiological modeling of speech production: Methods for modeling soft-tissue articulators [J]. Journal of the Acoustical Society of America, 1995, 97(5): 3085-3098. [DOI: 10.1121/1.411871]
[10]  King S A, Parent R E. A 3d parametric tongue model for animated speech [J]. Journal of Visualization and Computer Animation, 2001, 12(3): 107-115. [DOI: 10.1002/vis.249]
[11]  Ilie M D, Negrescu C, Stanomir D. An efficient parametric model for real-time 3D tongue skeletal animation [C]//Proceedings of the 9th International Conference on Communications. Bucharest, Romania: IEEE Computer Society, 2012: 129-132.[DOI: 10.1109/ ICComm.2012.6262577]
[12]  Engwall O. Combining MRI, EMA and EPG measurements in a three-dimensional tongue model [J]. Speech Communication, 2003, 41(2): 303-329. [DOI: 0.1016/S0167-6393(02)00132-2]
[13]  Jiang C, Luo C W, Yu J, et al. Modeling a realistic 3D physiological tongue for visual speech synthesis[C]//Proceedings of IEEE International Conference on Multimedia and Expo Workshops. Chengdu, China: IEEE Computer Society, 2014: 1-6. [DOI: 10.1109/ ICMEW.2014.6890595]
[14]  Miyawaki K. A study of the musculature of the human tongue[J]. Annual Bulletin of the Research Institute of Logopedics and Phoniatrics, 1974, 8: 23-50.
[15]  Agur A M R, Dalley A F. Grant\'s Atlas of Anatomy [M]. Philadelphia: Lippincott Williams & Wilkins, 2009.
[16]  Mac Neilage P F, Sholes G N. An electromyographic study of the tongue during vowel production [J]. Journal of Speech, Language, and Hearing Research, 1964, 7(3): 209-232. [DOI: 10.1044/jshr.0703.209]
[17]  Takemoto H. Morphological analyses of the human tongue musculature for three-dimensional modeling [J]. Journal of Speech, Language, and Hearing Research, 2001, 44(1): 95-107. [DOI: 10.1044/1092-4388(2001/009)]
[18]  Bao H Q. Articulator Movement Characters of Mandarin [M]. Beijing: Beijing Languages Institute Press, 1985.[鲍怀翘.普通话发音器官动作特性 [M].北京:北京语言学院出版社, 1985.]
[19]  Weatherill N P, Hassan O. Efficient three dimensional Delaunay triangulation with automatic point creation and imposed boundary constraints [J]. International Journal for Numerical Methods in Engineering, 1994, 37(12): 2005-2039. [DOI: 10.1002/nme.1620371203]
[20]  Mooney M. A theory of large elastic deformation [J]. Journal of Applied Physics, 1940, 11(9): 582-592. [DOI: 10.1063/1.1712836]
[21]  更多...
[22]  Deng Z, Chiang P Y, Fox P, et al. Animating blendshape faces by cross-mapping motion capture data [C]//Symposium on Interactive 3D Graphics and Games. New York: ACM press, 2006: 43-48. [DOI: 10.1145/1111411.1111419]
[23]  Cootes T F, Edwards G J, Taylor C J. Active appearance models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(6): 681-685. [DOI: 10.1109/34.927467]
[24]  Laprie Y, Berger M O. Extraction of tongue contours in x-ray images with minimal user interaction [C]//Proceedings of the 4th International Conference on Spoken Language. Philadelphia, Pennsylvania: IEEE Computer Society, 1996, 1: 268-271. [DOI: 10.1109/ICSLP.1996.607097]
[25]  Yu J, Li A J. 3D visual pronunciation of Mandarine Chinese for language learning [C]//Proceedings of IEEE International Conference on Image Processing. Paris, France: IEEE Computer Society, 2014: 2036-2040. [DOI: 10.1109/ICIP. 2014. 7025408]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133