dc.contributor.author |
Kleynhans, N
|
|
dc.contributor.author |
Barnard, E
|
|
dc.date.accessioned |
2012-01-27T08:42:57Z |
|
dc.date.available |
2012-01-27T08:42:57Z |
|
dc.date.issued |
2008-11 |
|
dc.identifier.citation |
Kleynhans, N and Barnard, E. 2008. Channel normalization technique for speech recognition in mismatched conditions. Nineteenth Annual Symposium of the Pattern Recognition Association of South Africa (PRASA 2008), Cape Town, South Africa, 27-28 November 2008 |
en_US |
dc.identifier.isbn |
9780799223507 |
|
dc.identifier.uri |
http://hdl.handle.net/10204/5541
|
|
dc.description |
Nineteenth Annual Symposium of the Pattern Recognition Association of South Africa (PRASA 2008), Cape Town, South Africa, 27-28 November 2008 |
en_US |
dc.description.abstract |
The performance of trainable speech-processing systems deteriorates significantly when there is a mismatch between the training and testing data. The data mismatch becomes a dominant factor when collecting speech data for resource scarce languages, where one wishes to use any available training data for a variety of purposes. Research into a new channel normalization (CN) technique for channel mismatched speech recognition is presented. A process of inverse linear filtering is used in order to match training and testing short-term spectra as closely as possible. Our technique is able to reduce the phoneme recognition error rate between the baseline and mismatched systems, to an extent comparable to the results obtained by the widely-used ceostral mean subtraction. Combining these techniques gives some additional improvement |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
PRASA 2008 |
en_US |
dc.subject |
Channel normalization technique |
en_US |
dc.subject |
Speech recognition |
en_US |
dc.subject |
Pattern recognition |
en_US |
dc.subject |
PRASA 2008 |
en_US |
dc.title |
Channel normalization technique for speech recognition in mismatched conditions |
en_US |
dc.type |
Conference Presentation |
en_US |
dc.identifier.apacitation |
Kleynhans, N., & Barnard, E. (2008). Channel normalization technique for speech recognition in mismatched conditions. PRASA 2008. http://hdl.handle.net/10204/5541 |
en_ZA |
dc.identifier.chicagocitation |
Kleynhans, N, and E Barnard. "Channel normalization technique for speech recognition in mismatched conditions." (2008): http://hdl.handle.net/10204/5541 |
en_ZA |
dc.identifier.vancouvercitation |
Kleynhans N, Barnard E, Channel normalization technique for speech recognition in mismatched conditions; PRASA 2008; 2008. http://hdl.handle.net/10204/5541 . |
en_ZA |
dc.identifier.ris |
TY - Conference Presentation
AU - Kleynhans, N
AU - Barnard, E
AB - The performance of trainable speech-processing systems deteriorates significantly when there is a mismatch between the training and testing data. The data mismatch becomes a dominant factor when collecting speech data for resource scarce languages, where one wishes to use any available training data for a variety of purposes. Research into a new channel normalization (CN) technique for channel mismatched speech recognition is presented. A process of inverse linear filtering is used in order to match training and testing short-term spectra as closely as possible. Our technique is able to reduce the phoneme recognition error rate between the baseline and mismatched systems, to an extent comparable to the results obtained by the widely-used ceostral mean subtraction. Combining these techniques gives some additional improvement
DA - 2008-11
DB - ResearchSpace
DP - CSIR
KW - Channel normalization technique
KW - Speech recognition
KW - Pattern recognition
KW - PRASA 2008
LK - https://researchspace.csir.co.za
PY - 2008
SM - 9780799223507
T1 - Channel normalization technique for speech recognition in mismatched conditions
TI - Channel normalization technique for speech recognition in mismatched conditions
UR - http://hdl.handle.net/10204/5541
ER -
|
en_ZA |