Please use this identifier to cite or link to this item:
Title: An investigation of tied-mixture GMM based triphone state clustering
Authors: Wang, G.
Sim, K.C. 
Keywords: context dependent modeling
phonetic decision tree
state clustering
Issue Date: 2012
Citation: Wang, G.,Sim, K.C. (2012). An investigation of tied-mixture GMM based triphone state clustering. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings : 4717-4720. ScholarBank@NUS Repository.
Abstract: Parameter tying is a crucial scheme for robust context dependent acoustic modeling since it takes a major role in balancing the desired model complexity and the amount of data available. In this paper, a modified decision tree state clustering scheme based on tied-mixture Gaussian Mixture Model (GMM) is proposed. Instead of using a single Gaussian untied triphone system, a tied-mixture GMM triphone system is adopted as a better acoustic model for state clustering. Meanwhile, the proposed scheme allows easy incorporation of discriminative training during clustering. Experimental results show that for a varying number of state clusters, the proposed approach consistently outperforms the standard single Gaussian based state tying. The best WER performance has a 10.5% relative improvement over the conventional decision tree clustering and the proposed scheme achieves its best performance using a much smaller number of state clusters. Moreover, detailed analyses reveal that the proposed GMM clustering has a better state distribution which leads to 1) better frame-state alignments 2) better phonetic question selections. These two factors may make the proposed approach superior for clustering. © 2012 IEEE.
Source Title: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISBN: 9781467300469
ISSN: 15206149
DOI: 10.1109/ICASSP.2012.6288972
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Dec 6, 2022

Page view(s)

checked on Dec 8, 2022

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.