|
JAIST Repository >
b. 情報科学研究科・情報科学系 >
b10. 学術雑誌論文等 >
b10-1. 雑誌掲載論文 >
このアイテムの引用には次の識別子を使用してください:
http://hdl.handle.net/10119/16289
|
完全登録情報レコード
| ダブリン･コア･フィールド | 値 | 言語 |
|---|
| contributor.author | Atmaja, Bagus Tris | en_US |
| contributor.author | Akagi, Masato | en_US |
| date.accessioned | 2020-06-03T01:03:43Z | - |
| date.available | 2020-06-03T01:03:43Z | - |
| date.issued | 2020-05-27 | en_US |
| identifier.uri | http://hdl.handle.net/10119/16289 | - |
| description.abstract | The majority of research in speech emotion recognition (SER) is conducted to recognize emotion categories. Recognizing dimensional emotion attributes is also important, however, and it has several advantages over categorical emotion. For this research, we investigate dimensional SER using both speech features and word embeddings. The concatenation network joins acoustic networks and text networks from bimodal features. We demonstrate that those bimodal features, both are extracted from speech, improve the performance of dimensional SER over unimodal SER either using acoustic features or word embeddings. A significant improvement on the valence dimension is contributed by the addition of word embeddings to SER system, while arousal and dominance dimensions are also improved. We proposed a multitask learning (MTL) approach for the prediction of all emotional attributes. This MTL maximizes the concordance correlation between predicted emotion degrees and true emotion labels simultaneously. The findings suggest that the use of MTL with two parameters is better than other evaluated methods in representing the interrelation of emotional attributes. In unimodal results, speech features attain higher performance on arousal and dominance, while word embeddings are better for predicting valence. The overall evaluation uses the concordance correlation coefficient score of the three emotional attributes. We also discuss some differences between categorical and dimensional emotion results from psychological and engineering perspectives. | en_US |
| format.extent | 744243 bytes | - |
| format.mimetype | application/pdf | - |
| language.iso | en | en_US |
| publisher | Cambridge University Press | en_US |
| rights | SIP (2020), vol. 9, e17, page 1 of 12 (c) The Author(s), 2020. Published by Cambridge University Press in association with Asia Pacific Signal and Information Processing Association. This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited. doi:10.1017/ATSIP.2020.14 | en_US |
| subject | Speech emotion recognition | en_US |
| subject | Multitask learning | en_US |
| subject | Feature fusion | en_US |
| subject | Dimensional emotion | en_US |
| subject | Affective computing | en_US |
| title | Dimensional speech emotion recognition from speech features and word embeddings by using multitask learning | en_US |
| type.nii | Journal Article | en_US |
| identifier.niiissn | 2048-7703 | en_US |
| identifier.jtitle | APSIPA Transactions on Signal and Information Processing | en_US |
| identifier.volume | 9 | en_US |
| identifier.spage | e17 | en_US |
| relation.doi | 10.1017/ATSIP.2020.14 | en_US |
| rights.textversion | publisher | en_US |
| language.iso639-2 | eng | en_US |
| 出現コレクション: | b10-1. 雑誌掲載論文 (Journal Articles)
|
このアイテムのファイル:
| ファイル |
記述 |
サイズ | 形式 |
|---|
| SIP_Atmaja.pdf | | 726Kb | Adobe PDF | 見る/開く |
|
当システムに保管されているアイテムはすべて著作権により保護されています。
|
