15
0
0
0
0
Robust emotion recognition using spectral and prosodic features [electronic resource]
- 作者： Rao, K. Sreenivasa.
- 其他作者：
- 其他題名：
- SpringerBriefs in electrical and computer engineering.
- 出版： New York, NY : Springer New York :Imprint: Springer
- 叢書名： SpringerBriefs in electrical and computer engineering, Speech technology,
- 主題： Speech processing systems. , Pattern recognition systems. , Prosodic analysis (Linguistics) , Engineering. , Signal, Image and Speech Processing. , User Interfaces and Human Computer Interaction. , Language Translation and Linguistics. , Computational Linguistics.
- ISBN： 9781461463603 (electronic bk.) 、 9781461463597 (paper)
-
FIND@SFXID:
CGU
- 資料類型: 電子書
-
讀者標籤：
- 系統號： 005397187 | 機讀編目格式
館藏資訊
In this brief, the authors discuss recently explored spectral (sub-segmental and pitch synchronous) and prosodic (global and local features at word and syllable levels in different parts of the utterance) features for discerning emotions in a robust manner. The authors also delve into the complementary evidences obtained from excitation source, vocal tract system and prosodic features for the purpose of enhancing emotion recognition performance. Features based on speaking rate characteristics are explored with the help of multi-stage and hybrid models for further improving emotion recognition performance. Proposed spectral and prosodic features are evaluated on real life emotional speech corpus.
資料來源：
Google Book
延伸查詢
Google Books
Amazon