Exploring many-to-one speech-to-text correlation for web-based language learning

• Authors: Herng-Yow Chen;Sheng-Wei Li
• Venue: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
• Year: 2007

This article investigates the correlations between multimedia objects (particularly speech and text) involved in language lectures in order to design an effective presentation mechanism for web-based learning. The cross-media correlations are classified into implicit relations (retrieved by computing) and explicit relations (recorded during the preprocessing stage). The implicit temporal correlation between speech and text is primarily to help to negotiate supplementary lecture navigations like tele-pointer movement, lips-sync movement, and content scrolling. We propose a speech-text alignment framework, using an iterative algorithm based on local alignment, to probe many-to-one temporal correlations, and not the one-to-one only. The proposed framework is a more practical method for analyzing general language lectures, and the algorithm's time complexity conforms to the best-possible computation cost, O(nm), without introducing additional computation. In addition, we have shown the feasibility of creating vivid presentations by exploiting implicit relations and artificially simulating some explicit media. To facilitate the navigation of integrated multimedia documents, we develop several visualization techniques for describing media correlations, including guidelines for speech-text correlations, visible-automatic scrolling, and levels of detail of timeline, to provide intuitive and easy-to-use random access mechanisms. We evaluated the performance of the analysis method and human perceptions of the synchronized presentation. The overall performance of the analysis method is that about 99.5% of the words analyzed are of a temporal error within 0.5 sec and the subjective evaluation result shows that the synchronized presentation is highly acceptable to human beings.