Paper Info
Title
A simplified Subspace Gaussian Mixture to compact acoustic models for speech recognition
Abstract
Speech recognition applications are known to require a significant amount of resources (memory, computing power). However, embedded speech recognition systems, such as in mobile phones, only authorizes few KB of memory and few MIPS. In the context of HMM-based speech recognizers, each HMM-state distribution is modeled independently from to the other and has a large amount of parameters. In spite of using state-tying techniques, the size of the acoustic models stays large and certain redundancy remains between states. In this paper, we investigate the capacity of the Subspace Gaussian Mixture approach to reduce the acoustic models size while keeping good performances. We introduce a simplification concerning state specific Gaussians weights estimation, which is a very complex and time consuming procedure in the original approach. With this approach, we show that the acoustic model size can be reduced by 92% with almost the same performance as the standard acoustic modeling.
Year
DOI
Venue
2011
10.1109/ICASSP.2011.5947453
Acoustics, Speech and Signal Processing
Keywords
Field
DocType
Gaussian processes,hidden Markov models,speech recognition,Gaussian weight estimation,HMM-based speech recognizer,HMM-state distribution model,MIPS,acoustic modeling,embedded speech recognition system,memory KB,mobile phone,subspace Gaussian mixture approach,Compact Acoustic Models,Embedded speech recognition,Gaussian Mixture Models,Hidden Markov Models,Subspace Gaussian Mixture
Speech processing,Pattern recognition,Subspace topology,Computer science,Speech recognition,Gaussian,Redundancy (engineering),Gaussian process,Artificial intelligence,Hidden Markov model,Mixture model,Acoustic model
Conference
ISSN
ISBN
Citations 
1520-6149 E-ISBN : 978-1-4577-0537-3
978-1-4577-0537-3
5
PageRank 
References 
Authors
0.49
7
3
Name
Order
Citations
PageRank
Mohamed Bouallegue1386.13
Driss Matrouf240441.80
Georges Linares38719.73