Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/8917
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Darch, J | - |
dc.contributor.author | Milner, B | - |
dc.contributor.author | Vaseghi, S | - |
dc.date.accessioned | 2014-08-19T09:56:10Z | - |
dc.date.available | 2014-08-19T09:56:10Z | - |
dc.date.issued | 2008 | - |
dc.identifier.citation | Journal of the Acoustical Society of America, 124(6), 3989 - 4000, 2008 | en_US |
dc.identifier.issn | 0001-4966 | - |
dc.identifier.uri | http://scitation.aip.org/content/asa/journal/jasa/124/6/10.1121/1.2997436 | en |
dc.identifier.uri | http://bura.brunel.ac.uk/handle/2438/8917 | - |
dc.description | Copyright © 2008 Acoustical Society of America. | en_US |
dc.description.abstract | The aim of this work is to develop methods that enable acoustic speech features to be predicted from mel-frequency cepstral coefficient (MFCC) vectors as may be encountered in distributed speech recognition architectures. The work begins with a detailed analysis of the multiple correlation between acoustic speech features and MFCC vectors. This confirms the existence of correlation, which is found to be higher when measured within specific phonemes rather than globally across all speechsounds. The correlation analysis leads to the development of a statistical method of predicting acoustic speech features from MFCC vectors that utilizes a network of hidden Markov models (HMMs) to localize prediction to specific phonemes. Within each HMM, the joint density of acoustic features and MFCC vectors is modeled and used to make a maximum a posteriori prediction. Experimental results are presented across a range of conditions, such as with speaker-dependent, gender-dependent, and gender-independent constraints, and these show that acoustic speech features can be predicted from MFCC vectors with good accuracy. A comparison is also made against an alternative scheme that substitutes the higher-order MFCCs with acoustic features for transmission. This delivers accurate acoustic features but at the expense of a significant reduction in speech recognition accuracy. | en_US |
dc.language | English | - |
dc.language.iso | en | en_US |
dc.publisher | Acoustical Society of America | en_US |
dc.subject | Acoustic speech features | en_US |
dc.subject | Distributed speech recognition architectures | en_US |
dc.subject | Mel-frequency cepstral coefficient | en_US |
dc.subject | Hidden Markov models | en_US |
dc.title | Analysis and prediction of acoustic speech features from mel-frequency cepstral coefficients in distributed speech recognition architectures | en_US |
dc.type | Article | en_US |
dc.identifier.doi | http://dx.doi.org/10.1121/1.2997436 | - |
pubs.organisational-data | /Brunel | - |
pubs.organisational-data | /Brunel/Group Publication Pages | - |
pubs.organisational-data | /Brunel/Leavers | - |
pubs.organisational-data | /Brunel/University Research Centres and Groups | - |
pubs.organisational-data | /Brunel/University Research Centres and Groups/Brunel Business School - URCs and Groups | - |
pubs.organisational-data | /Brunel/University Research Centres and Groups/Brunel Business School - URCs and Groups/Centre for Research into Entrepreneurship, International Business and Innovation in Emerging Markets | - |
pubs.organisational-data | /Brunel/University Research Centres and Groups/School of Arts - URCs and Groups | - |
pubs.organisational-data | /Brunel/University Research Centres and Groups/School of Arts - URCs and Groups/Brunel Centre for Contemporary Writing | - |
pubs.organisational-data | /Brunel/University Research Centres and Groups/School of Health Sciences and Social Care - URCs and Groups | - |
pubs.organisational-data | /Brunel/University Research Centres and Groups/School of Health Sciences and Social Care - URCs and Groups/Brunel Institute for Ageing Studies | - |
pubs.organisational-data | /Brunel/University Research Centres and Groups/School of Health Sciences and Social Care - URCs and Groups/Brunel Institute of Cancer Genetics and Pharmacogenomics | - |
pubs.organisational-data | /Brunel/University Research Centres and Groups/School of Health Sciences and Social Care - URCs and Groups/Centre for Systems and Synthetic Biology | - |
pubs.organisational-data | /Brunel/University Research Centres and Groups/School of Information Systems, Computing and Mathematics - URCs and Groups | - |
pubs.organisational-data | /Brunel/University Research Centres and Groups/School of Information Systems, Computing and Mathematics - URCs and Groups/Multidisclipary Assessment of Technology Centre for Healthcare (MATCH) | - |
Appears in Collections: | Electronic and Electrical Engineering Dept of Electronic and Electrical Engineering Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Fulltext.pdf | 190.38 kB | Adobe PDF | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.