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.
|Keywords:||context dependent modeling
phonetic decision tree
|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. https://doi.org/10.1109/ICASSP.2012.6288972||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||URI:||http://scholarbank.nus.edu.sg/handle/10635/41040||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.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.