CHEAVD: a Chinese natural emotional audio–visual database
| Autor: | Ya Li, Jianhua Tao, Linlin Chao, Yazhu Liu, Wei Bao |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
General Computer Science
Database Computer science business.industry Speech recognition 05 social sciences Contrast (statistics) Computational intelligence 02 engineering and technology computer.software_genre 050105 experimental psychology Recurrent neural network ComputerApplications_MISCELLANEOUS Audio visual 0202 electrical engineering electronic engineering information engineering Natural (music) 020201 artificial intelligence & image processing 0501 psychology and cognitive sciences Emotion recognition Artificial intelligence business computer Natural language processing |
| Zdroj: | Journal of Ambient Intelligence and Humanized Computing. 8:913-924 |
| ISSN: | 1868-5145 1868-5137 |
| DOI: | 10.1007/s12652-016-0406-z |
| Popis: | This paper presents a recently collected natural, multimodal, rich-annotated emotion database, CASIA Chinese Natural Emotional Audio-Visual Database (CHEAVD), which aims to provide a basic resource for the research on multimodal multimedia interaction. This corpus contains 140 min emotional segments extracted from films, TV plays and talk shows. 238 speakers, aging from child to elderly, constitute broad coverage of speaker diversity, which makes this database a valuable addition to the existing emotional databases. In total, 26 non-prototypical emotional states, including the basic six, are labeled by four native speakers. In contrast to other existing emotional databases, we provide multi-emotion labels and fake/suppressed emotion labels. To our best knowledge, this database is the first large-scale Chinese natural emotion corpus dealing with multimodal and natural emotion, and free to research use. Automatic emotion recognition with Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN) is performed on this corpus. Experiments show that an average accuracy of 56 % could be achieved on six major emotion states. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink