Welcome to the InfoSci Platform
Reference Hub1
An Improved Approach to Audio Segmentation and Classification in Broadcasting Industries

An Improved Approach to Audio Segmentation and Classification in Broadcasting Industries

Jingzhou Sun, Yongbin Wang
Copyright: © 2019 |Volume: 30 |Issue: 2 |Pages: 23
ISSN: 1063-8016|EISSN: 1533-8010|EISBN13: 9781522563792|DOI: 10.4018/JDM.2019040103
Cite Article Cite Article

MLA

Sun, Jingzhou, and Yongbin Wang. "An Improved Approach to Audio Segmentation and Classification in Broadcasting Industries." JDM vol.30, no.2 2019: pp.44-66. http://doi.org/10.4018/JDM.2019040103

APA

Sun, J. & Wang, Y. (2019). An Improved Approach to Audio Segmentation and Classification in Broadcasting Industries. Journal of Database Management (JDM), 30(2), 44-66. http://doi.org/10.4018/JDM.2019040103

Chicago

Sun, Jingzhou, and Yongbin Wang. "An Improved Approach to Audio Segmentation and Classification in Broadcasting Industries," Journal of Database Management (JDM) 30, no.2: 44-66. http://doi.org/10.4018/JDM.2019040103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Audio segmentation and classification are the basis of audio processing in broadcasting industries. A Dual-CNN (Dual-Convolutional Neural Network) method is proposed in this article in which it is possible to pre-train a CNN with unlabeled audio data so as to deal with the scarcity of labeled data. Auto-encoders (including an encoder and a decoder) are utilized, thus the name “Dual.” In the first place, audio sampling points and the derived STFT (Short-Time Fourier Transform) spectrograms pass through their own CNNs. Fusion of the extracted features is then performed. Finally, the merged features are sent to a fully connected network and the classification results are produced via Softmax. Being one of the segmentation-by-classification approaches, our solution also presents a novel smoothing method (SEG-smoothing) in order to deliver the best result of segmentation. A series of experiments have been conducted and their result verifies that the proposed approach for segmentation and classification outperforms alternative solutions.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.