Segmentation and recognition of meeting events using a two-layered HMM and a combined MLP-HMM approach

Automatic segmentation and classification of recorded meet-ings provides a basis that enables effective browsing and querying in a meeting archive. Yet, robustness of today’s approaches is often not reliable enough. We therefore strive to improve on this task by introduction of a hybrid approach combining the discriminative abilities of artificial neural nets and warping capabilities of hidden markov models. Divid-ing the task into two layers and defining a proper set of in-dividual actions helps to cope with the problem of lack of data and overcomes conventional single-layered approaches. Extensive test runs on the public M4 Scripted Meeting Cor-pus prove the great performance gain applying our suggested novel approach compared to other similar methods. 1