Please use this identifier to cite or link to this item: https://doi.org/10.1109/ASRU.2011.6163914
DC FieldValue
dc.titleA trajectory-based parallel model combination with a unified static and dynamic parameter compensation for noisy speech recognition
dc.contributor.authorSim, K.C.
dc.contributor.authorLuong, M.-T.
dc.date.accessioned2013-07-04T08:38:21Z
dc.date.available2013-07-04T08:38:21Z
dc.date.issued2011
dc.identifier.citationSim, K.C.,Luong, M.-T. (2011). A trajectory-based parallel model combination with a unified static and dynamic parameter compensation for noisy speech recognition. 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings : 107-112. ScholarBank@NUS Repository. <a href="https://doi.org/10.1109/ASRU.2011.6163914" target="_blank">https://doi.org/10.1109/ASRU.2011.6163914</a>
dc.identifier.isbn9781467303675
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/41893
dc.description.abstractParallel Model Combination (PMC) is widely used as a technique to compensate Gaussian parameters of a clean speech model for noisy speech recognition. The basic principle of PMC uses a log normal approximation to transform statistics of the data distribution between the cepstral domain and the linear spectral domain. Typically, further approximations are needed to compensate the dynamic parameters separately. In this paper, Trajectory PMC (TPMC) is proposed to compensate both the static and dynamic parameters. TPMC uses the explicit relationships between the static and dynamic features to transform the static and dynamic parameters into a sequence (trajectory) of static parameters, so that the log normal approximation can be applied. Experimental results on WSJCAM0 database corrupted with additive babble noise reveals that the proposed TPMC method gives promising improvements over PMC and VTS. © 2011 IEEE.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/ASRU.2011.6163914
dc.sourceScopus
dc.subjectNoise Robustness
dc.subjectParallel Model Combination
dc.subjectTrajectroy HMM
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.doi10.1109/ASRU.2011.6163914
dc.description.sourcetitle2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings
dc.description.page107-112
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

6
checked on Jan 25, 2023

Page view(s)

154
checked on Jan 26, 2023

Google ScholarTM

Check

Altmetric


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