Academic Commons

Articles

Using acoustic condition clustering to improve acoustic change detection on broadcast news

Lopez, Javier Ferreiros; Ellis, Daniel P. W.

We have developed a system that breaks input speech into segments using an acoustic similarity measure. The aim is to detect the time points where the acoustic characteristics change, usually due to speaker changes but also resulting from changes in the acoustic environment. We have also developed a system to cluster the segments generated by the first system into clusters composed of homogeneous acoustic conditions. In this paper, we present a technique to improve the robustness of the acoustic change detection by feeding back the results of the segment clustering, exploiting the extra information available in the distance between the two clusters to which the segments belong. The interaction between the acoustic change detection and clustering systems gives us a substantial improvement over results previously reported on the 1997 Hub-4 Broadcast News test set that we employed: Feedback of clustering information improved the Equal Error Rate (EER) of our acoustic change detection (ACD) system from 26.5% to 18%.

Files

Also Published In

Title
6th International Conference on Spoken Language Processing:
ICSLP 2000, the proceedings of the conference, Oct. 16-Oct. 20, 2000, Beijing International Convention Center, Beijing, China

More About This Work

Academic Units
Electrical Engineering
Publisher
China Military Friendship Publish
Published Here
July 3, 2012
Academic Commons provides global access to research and scholarship produced at Columbia University, Barnard College, Teachers College, Union Theological Seminary and Jewish Theological Seminary. Academic Commons is managed by the Columbia University Libraries.