Deep temporal architecture for audiovisual speech recognition
文献类型:会议论文
作者 | Tian, Chunlin1,2; Yuan, Yuan1; Lu, Xiaoqiang1; Lu, Xiaoqiang (luxiaoqiang@opt.ac.cn)1 |
出版日期 | 2017 |
会议日期 | 2017-10-11 |
会议地点 | Tianjin, China |
卷号 | 771 |
DOI | 10.1007/978-981-10-7299-4_54 |
页码 | 650-661 |
英文摘要 | The Audiovisual Speech Recognition (AVSR) is one of the applications of multimodal machine learning related to speech recognition, lipreading systems and video classification. In recent and related work, increasing efforts are made in Deep Neural Network (DNN) for AVSR, moreover some DNN models including Multimodal Deep Autoencoder, Multimodal Deep Belief Network and Multimodal Deep Boltzmann Machine perform well in experiments owing to the better generalization and nonlinear transformation. However, these DNN models have several disadvantages: (1) They mainly deal with modal fusion while ignoring temporal fusion. (2) Traditional methods fail to consider the connection among frames in the modal fusion. (3) These models aren’t end-to-end structure. We propose a deep temporal architecture, which has not only classical modal fusion, but temporal modal fusion and temporal fusion. Furthermore, the overfitting and learning with small size samples in the AVSR are also studied, so that we propose a set of useful training strategies. The experiments show the superiority of our model and necessity of the training strategies in three datasets: AVLetters, AVLetters2, AVDigits. In the end, we conclude the work. © Springer Nature Singapore Pte Ltd. 2017. |
产权排序 | 1 |
会议录 | Computer Vision - 2nd CCF Chinese Conference, CCCV 2017, Proceedings |
会议录出版者 | Springer Verlag |
语种 | 英语 |
ISSN号 | 18650929 |
ISBN号 | 9789811072987 |
WOS记录号 | WOS:000449835200054 |
源URL | [http://ir.opt.ac.cn/handle/181661/29612] |
专题 | 西安光学精密机械研究所_光学影像学习与分析中心 |
通讯作者 | Lu, Xiaoqiang (luxiaoqiang@opt.ac.cn) |
作者单位 | 1.Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an; Shaanxi; 710119, China 2.University of Chinese Academy of Sciences, 19A Yuquanlu, Beijing; 100049, China |
推荐引用方式 GB/T 7714 | Tian, Chunlin,Yuan, Yuan,Lu, Xiaoqiang,et al. Deep temporal architecture for audiovisual speech recognition[C]. 见:. Tianjin, China. 2017-10-11. |
入库方式: OAI收割
来源:西安光学精密机械研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。