How speech/text alignment benefits web-based learning
暂无分享,去创建一个
This demonstration presents an integrated web-based synchronized scenario for many-to-one cross-media correlations between speech (an EFL, English as Foreign Language, lecture with free-style lecturing behaviors) and the corresponding textual content. The analysis/presentation of the temporal correlations enable the vivid web-based language learning through the interactive functions: browsing speech via content, word-by-word pointer guidance, synchronized scrolling/highlighting, and listening training mode. We regularly analyze and repackage the multimedia content of VoA (Voice of America) [1], ICRT (International Community Radio Taipei) [2], and Online Lectures in our University [3]. Through the subjective experiments, this repackaged synchronized speech/text content does facilitate the learning for EFL learners.
[1] Pedro J. Moreno,et al. A recursive algorithm for the forced alignment of very long audio segments , 1998, ICSLP.
[2] Ralf Steinmetz,et al. Human Perception of Jitter and Media Synchronization , 1996, IEEE J. Sel. Areas Commun..
[3] Wei-Ta Chu,et al. Cross-media correlation: a case study of navigated hypermedia documents , 2002, MULTIMEDIA '02.