3 December 2015 Design of an audio advertisement dataset
Author Affiliations +
Proceedings Volume 9794, Sixth International Conference on Electronics and Information Engineering; 979436 (2015) https://doi.org/10.1117/12.2203234
Event: Sixth International Conference on Electronics and Information Engineering, 2015, Dalian, China
Abstract
Since more and more advertisements swarm into radios, it is necessary to establish an audio advertising dataset which could be used to analyze and classify the advertisement. A method of how to establish a complete audio advertising dataset is presented in this paper. The dataset is divided into four different kinds of advertisements. Each advertisement’s sample is given in *.wav file format, and annotated with a txt file which contains its file name, sampling frequency, channel number, broadcasting time and its class. The classifying rationality of the advertisements in this dataset is proved by clustering the different advertisements based on Principal Component Analysis (PCA). The experimental results show that this audio advertisement dataset offers a reliable set of samples for correlative audio advertisement experimental studies.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yutao Fu, Jihong Liu, Qi Zhang, Yuting Geng, "Design of an audio advertisement dataset", Proc. SPIE 9794, Sixth International Conference on Electronics and Information Engineering, 979436 (3 December 2015); doi: 10.1117/12.2203234; https://doi.org/10.1117/12.2203234
PROCEEDINGS
5 PAGES


SHARE
Back to Top