Improving generation performance of speech emotion recognition by denoising autoencoders

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 人机语音交互团队

	Improving generation performance of speech emotion recognition by denoising autoencoders
	Linlin Chao; Jianhua Tao; Minghao Yang; Ya Li
	2014
会议日期	2014-9
会议地点	Singapore
关键词	Speech Emotion Recognition
页码	341-344
英文摘要	1; A speech emotion recognition algorithm should generalize well when the target person’s speech samples and prior knowledge about their emotional content are not included in the training data. In order to achieve this objective, we utilize denoising autoencoders based approach to solve this task. In this study, a relatively small dataset, which contains close to 1500 persons’ emotion sentences, is introduced. By unsupervised pre-training with this dataset, denoising autoencoders learn features which contain more emotion-specific information than speaker-specific information in data successfully. Experiment results in CASIA dataset show that this denoising autoencoders based approach can improve the generation performance of speech emotion recognition significantly.
会议录	The 9th International Symposium on Chinese Spoken Language Processing
语种	英语
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/11847]
专题	自动化研究所_模式识别国家重点实验室_人机语音交互团队
通讯作者	Linlin Chao
作者单位	Institute of Automation, Chinese Academy of Sciences
推荐引用方式 GB/T 7714	Linlin Chao,Jianhua Tao,Minghao Yang,et al. Improving generation performance of speech emotion recognition by denoising autoencoders[C]. 见:. Singapore. 2014-9.