http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20050082566-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_80c71471bfe22b98a749a2abbd923b5a |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/E01H5-106 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G10L15-20 |
filingDate | 2004-02-19-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_bf0176b77c981990a30727e35d9a8b4b |
publicationDate | 2005-08-24-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | KR-20050082566-A |
titleOfInvention | Method for extracting speech feature of speech feature device |
abstract | The present invention relates to a technique for extracting a speech feature vector in a state of minimizing the influence of the additive noise generated by the surrounding environment, which is a major cause of lowering the speech recognition rate.n n n To this end, the present invention analyzes the frequency of the speech signal using wavelet transform, calculates each sample value using adjacent sample values, and extracts the speech feature vector in consideration of the difference of the calculated sample values to add noise. In this existing environment, it is characterized by extracting a speech feature vector with a minimal effect of addition noise. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2008063005-A1 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-100655953-B1 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-100789084-B1 http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-100798056-B1 |
priorityDate | 2004-02-19-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419526450 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID1051 |
Total number of triples: 17.