In this paper, a method of noise-robust speech emotion recognition under music noises is proposed by using a denoising autoencoder (DAE) and a support vector machine (SVM). The proposed method first trains a DAE by using emotional speech signals corrupted by music noises. Then, the output values from a middle layer of the DAE are used as speech features. Next, an SVM is trained to classify emotions using the DAE features. The performance of the proposed method is compared with that of a conventional SVM classifier. Consequently, it is shown that the proposed method relatively improves the overall emotion recognition rate by 9.76% under music noise conditions, compared to the conventional method.
https://www.aes.org/e-lib/browse.cfm?elib=18164
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.
Learn more about the AES E-Library
The Engineering Briefs at this Convention were selected on the basis of a submitted synopsis, ensuring that they are of interest to AES members, and are not overly commercial. These briefs have been reproduced from the authors' advance manuscripts, without editing, corrections, or consideration by the Review Board. The AES takes no responsibility for their contents. Paper copies are not available, but any member can freely access these briefs. Members are encouraged to provide comments that enhance their usefulness.
Start a discussion about this paper!
