Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICASSP.2012.6288972
DC FieldValue
dc.titleAn investigation of tied-mixture GMM based triphone state clustering
dc.contributor.authorWang, G.
dc.contributor.authorSim, K.C.
dc.date.accessioned2013-07-04T08:18:14Z
dc.date.available2013-07-04T08:18:14Z
dc.date.issued2012
dc.identifier.citationWang, 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. <a href="https://doi.org/10.1109/ICASSP.2012.6288972" target="_blank">https://doi.org/10.1109/ICASSP.2012.6288972</a>
dc.identifier.isbn9781467300469
dc.identifier.issn15206149
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/41040
dc.description.abstractParameter 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.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/ICASSP.2012.6288972
dc.sourceScopus
dc.subjectcontext dependent modeling
dc.subjectphonetic decision tree
dc.subjectstate clustering
dc.subjectTied-mixture
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.doi10.1109/ICASSP.2012.6288972
dc.description.sourcetitleICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
dc.description.page4717-4720
dc.description.codenIPROD
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

5
checked on Jan 30, 2023

Page view(s)

153
checked on Feb 2, 2023

Google ScholarTM

Check

Altmetric


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