@inproceedings{cd14faa9c44a41d7ae03c38b920e17f5,
title = "Learning with synthesized speech for automatic emotion recognition",
abstract = "Data sparseness is an ever dominating problem in automatic emotion recognition. Using artificially generated speech for training or adapting models could potentially ease this: though less natural than human speech, one could synthesize the exact spoken content in different emotional nuances - of many speakers and even in different languages. To investigate chances, the phonemisation components Txt2Pho and openMary are used with Emofilt and Mbrola for emotional speech synthesis. Analysis is realized with our Munich open Emotion and Affect Recognition toolkit. As test set we gently limit to the acted Berlin and eNTERFACE databases for the moment. In the result synthesized speech can indeed be used for the recognition of human emotional speech.",
keywords = "Affective computing, Emotion recognition, Speech analysis, Speech synthesis",
author = "Bj{\"o}rn Schuller and Felix Burkhardt",
year = "2010",
doi = "10.1109/ICASSP.2010.5495017",
language = "English",
isbn = "9781424442966",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "5150--5153",
booktitle = "2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings",
note = "2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 ; Conference date: 14-03-2010 Through 19-03-2010",
}