Multiple change-point audio segmentation and classification using an MDL-based Gaussian model

Authors:
Chung-Hsien Wu;Chia-Hsin Hsieh
Affiliations:
Dept. of Comput. Sci. & Inf. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan;-
Venue:
IEEE Transactions on Audio, Speech, and Language Processing
Year:
2006

Citing 0
Cited 6

Review: Speaker segmentation and clustering

Signal Processing
Story segmentation and topic classification of broadcast news via a topic-based segmental model and a genetic algorithm

IEEE Transactions on Audio, Speech, and Language Processing
BIC-based speaker segmentation using divide-and-conquer strategies with application to speaker diarization

IEEE Transactions on Audio, Speech, and Language Processing
Barankin-type lower bound on multiple change-point estimation

IEEE Transactions on Signal Processing
A review on speaker diarization systems and approaches

Speech Communication
Dynamic and scalable audio classification by collective network of binary classifiers framework: An evolutionary approach

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This study presents an approach for segmenting and classifying an audio stream based on audio type. First, a silence deletion procedure is employed to remove silence segments in the audio stream. A minimum description length (MDL)-based Gaussian model is then proposed to statistically characterize the audio features. Audio segmentation segments the audio stream into a sequence of homogeneous subsegments using the MDL-based Gaussian model. A hierarchical threshold-based classifier is then used to classify each subsegment into different audio types. Finally, a heuristic method is adopted to smooth the subsegment sequence and provide the final segmentation and classification results. Experimental results indicate that for TDT-3 news broadcast, a missed detection rate (MDR) of 0.1 and a false alarm rate (FAR) of 0.14 were achieved for audio segmentation. Given the same MDR and FAR values, segment-based audio classification achieved a better classification accuracy of 88% compared to a clip-based approach.