Robust Emotion Recognition using Spectral and Prosodic Features

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.

Verwandte Artikel

Download
PDF
Robust Emotion Recognition using Spectral and Prosodic Features K. Sreenivasa Rao, Shashidhar G. Koolagudi

53,49 €*

Weitere Produkte vom selben Autor

Language Identification Using Spectral and Prosodic Features Rao, K. Sreenivasa, Maity, Sudhamay, Reddy, V. Ramu

53,49 €*
Emotion Recognition using Speech Features Koolagudi, Shashidhar G., Rao, K. Sreenivasa

53,49 €*
Speech Processing in Mobile Environments Vuppala, Anil Kumar, Rao, K. Sreenivasa

53,49 €*