Transfer Semi-Supervised Non-Negative Matrix Factorization for Speech Emotion Recognition

Peng SONG  Shifeng OU  Xinran ZHANG  Yun JIN  Wenming ZHENG  Jinglei LIU  Yanwei YU  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E99-D   No.10   pp.2647-2650
Publication Date: 2016/10/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2016EDL8067
Type of Manuscript: LETTER
Category: Speech and Hearing
Keyword: 
speech emotion recognition,  transfer learning,  non-negative matrix factorization,  semi-supervised learning,  

Full Text: PDF(86KB)>>
Buy this Article




Summary: 
In practice, emotional speech utterances are often collected from different devices or conditions, which will lead to discrepancy between the training and testing data, resulting in sharp decrease of recognition rates. To solve this problem, in this letter, a novel transfer semi-supervised non-negative matrix factorization (TSNMF) method is presented. A semi-supervised negative matrix factorization algorithm, utilizing both labeled source and unlabeled target data, is adopted to learn common feature representations. Meanwhile, the maximum mean discrepancy (MMD) as a similarity measurement is employed to reduce the distance between the feature distributions of two databases. Finally, the TSNMF algorithm, which optimizes the SNMF and MMD functions together, is proposed to obtain robust feature representations across databases. Extensive experiments demonstrate that in comparison to the state-of-the-art approaches, our proposed method can significantly improve the cross-corpus recognition rates.