| Presentation | 2019-06-10 Impression Prediction of Oral Presentation Using LSTM with Dot-product Attention Mechanism Shengzhou Yi, Xueting Wang, Toshihiko Yamasaki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | For automatically evaluating oral presentation, we propose an end-to-end system to predict audience’s impression on speech video. Our framework is a multimodal neural network including two Long Short-Term Memory (LSTM) with dot-product attention mechanism to learn linguistic feature and acoustic feature respectively for our classification task, as well as a hidden network to consider the correlation between different types of feature representations for model-level fusion. We utilize 2,445 videos with official captions and users’ ratings from TED Talks. The experiment result shows the good performance of our proposal can recognize audience’s 14 types of impression with the average accuracy of 85.3%. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Presentation AnalysisMultimodal NetworkEnd-to-End SystemTED Talks |
| Paper # | MVE2019-1 |
| Date of Issue | 2019-06-03 (MVE) |
| Conference Information | |
| Committee | MVE / ITE-HI |
|---|---|
| Conference Date | 2019/6/10(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Kenji Mase(Nagoya Univ.) / Tatsuya Yoshizawa(Kanazawa Inst. of Tech.) |
| Vice Chair | Masayuki Ihara(NTT) |
| Secretary | Masayuki Ihara(NTT) / (Kyushu Univ.) |
| Assistant | Satoshi Nishiguchi(Oosaka Inst. of Tech.) / Masanori Yokoyama(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Media Experience and Virtual Environment / Technical Group on Human Information |
|---|---|
| Language | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Impression Prediction of Oral Presentation Using LSTM with Dot-product Attention Mechanism |
| Sub Title (in English) | |
| Keyword(1) | Presentation AnalysisMultimodal NetworkEnd-to-End SystemTED Talks |
| 1st Author's Name | Shengzhou Yi |
| 1st Author's Affiliation | The University of Tokyo(UTokyo) |
| 2nd Author's Name | Xueting Wang |
| 2nd Author's Affiliation | The University of Tokyo(UTokyo) |
| 3rd Author's Name | Toshihiko Yamasaki |
| 3rd Author's Affiliation | The University of Tokyo(UTokyo) |
| Date | 2019-06-10 |
| Paper # | MVE2019-1 |
| Volume (vol) | vol.119 |
| Number (no) | MVE-75 |
| Page | pp.pp.1-6(MVE), |
| #Pages | 6 |
| Date of Issue | 2019-06-03 (MVE) |