Audio segmentation of broadcast news: A hierarchical system with feature selection for the Albayzin-2010 evaluation

In this paper, we present an audio segmentation system for broadcast news, and its results in the Albayzín-2010 evaluation. First of all, the Albayzín-2010 evaluation setup, developed by the authors, is presented; in particular, the database and the metric are described. The reported hierarchical HMM-GMM-based system is composed of one binary detector for each of the five considered classes (music, speech, speech over music, speech over noise and other). A fast one-pass-training feature selection technique is adapted to the audio segmentation task to improve the results and to reduce the dimensionality of the input feature vector.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Taras Butko, Climent Nadeu
• Keywords: Albayzín-2010 Evaluation, Audio Segmentation, Audio Segmentation Task, ICASSP 2011, Signal Processing