Abstract:
This paper addresses a novel algorithm of incremental speaker adaptation (ISA) based on universal background model (UBM) for saving storage and real-time processing. This...Show MoreMetadata
Abstract:
This paper addresses a novel algorithm of incremental speaker adaptation (ISA) based on universal background model (UBM) for saving storage and real-time processing. This algorithm can be seen as an extension of traditional speaker adaptation. It consists of two steps, adaptation and combination. It not only considers the speaker's characteristics in limited training data, but also prohibits over-fitting of the updated model. The incremental adaptation algorithm needs little storage and meets the requirement of real-time processing. In order to evaluate the efficiency and effectivity of the proposed approach, a real-time speaker segmentation system for broadcasting news is built. Experiment results demonstrate that our approach yields real time operation and achieves satisfactory performance.
Published in: 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)
Date of Conference: 06-09 July 2003
Date Added to IEEE Xplore: 18 August 2003
Print ISBN:0-7803-7965-9