Recent advances in the automatic recognition of audiovisual speech Export

@article{Potamianos2003, abstract = {Visual speech information from the speaker's mouth region has been successfully shown to improve noise robustness of automatic speech recognizers, thus promising to extend their usability in the human computer interface. In this paper, we review the main components of audiovisual automatic speech recognition (ASR) and present novel contributions in two main areas: first, the visual front-end design, based on a cascade of linear image transforms of an appropriate video region of interest, and subsequently, audiovisual speech integration. On the latter topic, we discuss new work on feature and decision fusion combination, the modeling of audiovisual speech asynchrony, and incorporating modality reliability estimates to the bimodal recognition process. We also briefly touch upon the issue of audiovisual adaptation. We apply our algorithms to three multisubject bimodal databases, ranging from small- to large-vocabulary recognition tasks, recorded in both visually controlled and challenging environments. Our experiments demonstrate that the visual modality improves ASR over all conditions and data considered, though less so for visually challenging environments and large vocabulary tasks.}, author = {Potamianos, G. and Neti, C. and Gravier, G. and Garg, A. and Senior, A. W.}, citeulike-article-id = {1103827}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/JPROC.2003.817150}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1230212}, doi = {10.1109/JPROC.2003.817150}, journal = {Proceedings of the IEEE}, keywords = {audio-visual, recognition, speech}, number = {9}, pages = {1306--1326}, posted-at = {2008-03-22 07:50:11}, priority = {2}, title = {Recent advances in the automatic recognition of audiovisual speech}, url = {http://dx.doi.org/10.1109/JPROC.2003.817150}, volume = {91}, year = {2003} }

TY - JOUR ID - Potamianos2003 L3 - citeulike-article-id:1103827 N2 - Visual speech information from the speaker's mouth region has been successfully shown to improve noise robustness of automatic speech recognizers, thus promising to extend their usability in the human computer interface. In this paper, we review the main components of audiovisual automatic speech recognition (ASR) and present novel contributions in two main areas: first, the visual front-end design, based on a cascade of linear image transforms of an appropriate video region of interest, and subsequently, audiovisual speech integration. On the latter topic, we discuss new work on feature and decision fusion combination, the modeling of audiovisual speech asynchrony, and incorporating modality reliability estimates to the bimodal recognition process. We also briefly touch upon the issue of audiovisual adaptation. We apply our algorithms to three multisubject bimodal databases, ranging from small- to large-vocabulary recognition tasks, recorded in both visually controlled and challenging environments. Our experiments demonstrate that the visual modality improves ASR over all conditions and data considered, though less so for visually challenging environments and large vocabulary tasks. IS - 9 JF - Proceedings of the IEEE EP - 1326 TI - Recent advances in the automatic recognition of audiovisual speech VL - 91 SP - 1306 KW - audio-visual KW - recognition KW - speech AU - Potamianos, G AU - Neti, C AU - Gravier, G AU - Garg, A AU - Senior, AW PY - 2003/// UR - http://dx.doi.org/10.1109/JPROC.2003.817150 ER -