Title :
Classification of audio events in broadcast news
Author :
Liu, Zhu ; Huang, Qian
Author_Institution :
AT&T Labs.-Res., Red Bank, NJ, USA
Abstract :
This paper describes an approach to discriminate news report from others such as commercials and music in broadcast news programs based on audio information. The reported work is part of the effort at AT&T to hierarchically segment broadcast news programs into semantically meaningful units at different levels of abstraction. At the coarse level, using the described approach we preprocess the audio data to pass only the news segments as input to a speaker identification system. To develop a lightweight preprocessing scheme for efficiency, we adopted a set of audio features that are simple to compute yet, based on our observation, statistically capture the intrinsic properties of the audio events to be classified. To improve the performance of the classifier, fuzzy membership functions associated with the features are introduced. Preliminary experimental results are reported which demonstrate the usefulness of the approach
Keywords :
audio signal processing; broadcasting; feature extraction; fuzzy systems; signal classification; speaker recognition; AT&T; abstraction levels; audio data preprocessing; audio events classification; classifier performance; coarse level; commercials; experimental results; fuzzy membership functions; hierarchical segmentation; music; news report; news segments; semantically meaningful units; speaker identification system; Data preprocessing; Feature extraction; Indexing; Information retrieval; Multimedia communication; Niobium compounds; Radio broadcasting; Speech; Switches; TV broadcasting;
Conference_Titel :
Multimedia Signal Processing, 1998 IEEE Second Workshop on
Conference_Location :
Redondo Beach, CA
Print_ISBN :
0-7803-4919-9
DOI :
10.1109/MMSP.1998.738963
