期刊文献+

唇读研究进展综述 被引量:1

Review of lip-reading research development
下载PDF
导出
摘要 将计算机唇读技术和语音识别技术进行融合,提高语音识别效果的方法,引起了一些研究者的关注,并已取得了长足的进步,但仍有许多难题需要突破。为了引起更多研究者对此研究领域的兴趣和关注,参与到唇读技术的研究,共同推进该领域的发展,就目前唇读技术的发展现状做了详细的介绍。总结一些主要的传统方法及相关方面的新技术,主要关注点为视觉特征提取方法、识别技术和音视频的信息融合算法。 To improve speech recognition results,the approach fusing lip-reading computer technology and speech recognition technology was introduced.This method attracted the attention of some researchers,and considerable progress was made,but there were still many problems to be brokethrough.To attract more researchers' interests and concerns in this area of research and hoped that they could participate in the study of lip-reading technology to jointly promote the development of the field,a detailed introduction on the current status of lip-reading technology was given,some of the main relevant aspects of the traditional methods and new technologies were described.It focused on the visual feature extraction,recognition technology and speech visual fusion algorithr.
出处 《计算机工程与设计》 CSCD 北大核心 2014年第6期2135-2141,共7页 Computer Engineering and Design
基金 国家科技支撑计划子课题基金项目(2011BAK07B03-9)
关键词 唇读 视觉特征 特征提取 隐马尔可夫模型 信息融合 lip-reading visual feature extraction feature extraction HMM information fusion
  • 相关文献

参考文献40

  • 1McGurk H, MacDonald J. Hearing lips and seeing voices [J]. Nature, 1976, 264 (5588): 746-748.
  • 2Graf H P, Cosatto E, Gibbon D, et al. Multi modal system for locating heads and faces [C]/ / Proc IEEE FG Killington, 2008: 88-93.
  • 3Rowley H A, Baiuja S, Kanade T. Neural network-based face detection [C] / / IEEE Trans Patt Anal Mach Int, 2008: 23-38.
  • 4Zhang Zeliang, Li Xiongfei. An effective parameter estimation algorithm of the visual language features [J]. International Journal of Digital Content Technology and its Applications, 2012, 6 (4): 69-76.
  • 5Yao H, Wang R, Gao W. Method of deformable optimum threshold for lip-reading [C]/ / IEEE Fourth International Conference on Signal Processing, 2007: 912-915.
  • 6Zhang Zeliang, Li Xiongfei, A study on improved hidden Markov models and applications to speech recognition [C] / / International Conference on Computer Science and Service System, 2011: 1996-1999.
  • 7Potamianos G, Neti C, Iyengar G, et al. A cascade visual front end for speaker independent automatic speechreading [J]. UST, 2011, 4 (1): 193-208.
  • 8Aleksic p, Williams J, Wu Z, et al. Audiovisual continuous speech recognition using MPEG-4 compliant visual features [C] / /ICIP, 2012: 960-963.
  • 9Chen T. Audiovisual speech processing [J]. SPM, 2011, 18 (1): 9-21.
  • 10Kaynak M, Zhi Q, Cheok A, et al. Audio-visual modeling for bimodal speech recognition [C]//ICSMC, 2009: 181-186.

同被引文献4

引证文献1

二级引证文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部