Speech Emotion Recognition Using Transfer Learning

Peng SONG  Yun JIN  Li ZHAO  Minghai XIN  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E97-D   No.9   pp.2530-2532
Publication Date: 2014/09/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2014EDL8038
Type of Manuscript: LETTER
Category: Speech and Hearing
Keyword: 
speech emotion recognition,  transfer learning,  cross-corpus,  dimension reduction,  

Full Text: PDF(272.8KB)>>
Buy this Article




Summary: 
A major challenge for speech emotion recognition is that when the training and deployment conditions do not use the same speech corpus, the recognition rates will obviously drop. Transfer learning, which has successfully addressed the cross-domain classification or recognition problem, is presented for cross-corpus speech emotion recognition. First, by using the maximum mean discrepancy embedding (MMDE) optimization and dimension reduction algorithms, two close low-dimensional feature spaces are obtained for source and target speech corpora, respectively. Then, a classifier function is trained using the learned low-dimensional features in the labeled source corpus, and directly applied to the unlabeled target corpus for emotion label recognition. Experimental results demonstrate that the transfer learning method can significantly outperform the traditional automatic recognition technique for cross-corpus speech emotion recognition.