Matches in SemOpenAlex for { <https://semopenalex.org/work/W1986051330> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W1986051330 abstract "We showed in our recent work that Bidirectional neural network (BNN) is a powerful tool for feature compensation in automatic speech recognition systems. In this paper, we have introduced BNN as feature compensator for better discriminating of pathological voices from normal subjects. Mel-Frequency Cepstral Coefficients (MFCCs) were extracted from each frame of sample voices and were compensated in two steps. First, BNN is trained with both normal and pathological feature vectors. Our hypothesis is that BNN can extract useful knowledge about the patterns of each class during training step. In second step, MFCC feature vectors feed into BNN and compensate according to latent knowledge of BNN. In the last step, Compensated MFCCs are classified as pathological or normal by HMMs. We achieved 4.67%, 2.81% and 2.24% improvement in measures of specificity, accuracy and sensitivity by compensated feature vectors compared to the original feature vectors. Results corroborated our hypothesis about the ability of BNN in compensation of feature vectors in a way that these features become more suitable for detection of pathological voices from normal ones." @default.
- W1986051330 created "2016-06-24" @default.
- W1986051330 creator A5035978702 @default.
- W1986051330 creator A5039701676 @default.
- W1986051330 creator A5083892347 @default.
- W1986051330 date "2013-12-01" @default.
- W1986051330 modified "2023-10-16" @default.
- W1986051330 title "Bidirectional neural network for pathological voice detection" @default.
- W1986051330 cites W1560013842 @default.
- W1986051330 cites W1578856370 @default.
- W1986051330 cites W1580625448 @default.
- W1986051330 cites W1972777189 @default.
- W1986051330 cites W1988974600 @default.
- W1986051330 cites W2039174771 @default.
- W1986051330 cites W2079240096 @default.
- W1986051330 cites W2093862051 @default.
- W1986051330 cites W2117095944 @default.
- W1986051330 cites W2138041026 @default.
- W1986051330 cites W2148380032 @default.
- W1986051330 cites W226870725 @default.
- W1986051330 doi "https://doi.org/10.1109/icbme.2013.6782226" @default.
- W1986051330 hasPublicationYear "2013" @default.
- W1986051330 type Work @default.
- W1986051330 sameAs 1986051330 @default.
- W1986051330 citedByCount "0" @default.
- W1986051330 crossrefType "proceedings-article" @default.
- W1986051330 hasAuthorship W1986051330A5035978702 @default.
- W1986051330 hasAuthorship W1986051330A5039701676 @default.
- W1986051330 hasAuthorship W1986051330A5083892347 @default.
- W1986051330 hasConcept C11171543 @default.
- W1986051330 hasConcept C138885662 @default.
- W1986051330 hasConcept C151989614 @default.
- W1986051330 hasConcept C153180895 @default.
- W1986051330 hasConcept C154945302 @default.
- W1986051330 hasConcept C15744967 @default.
- W1986051330 hasConcept C2776401178 @default.
- W1986051330 hasConcept C2780023022 @default.
- W1986051330 hasConcept C28490314 @default.
- W1986051330 hasConcept C41008148 @default.
- W1986051330 hasConcept C41895202 @default.
- W1986051330 hasConcept C50644808 @default.
- W1986051330 hasConcept C52622490 @default.
- W1986051330 hasConcept C83665646 @default.
- W1986051330 hasConceptScore W1986051330C11171543 @default.
- W1986051330 hasConceptScore W1986051330C138885662 @default.
- W1986051330 hasConceptScore W1986051330C151989614 @default.
- W1986051330 hasConceptScore W1986051330C153180895 @default.
- W1986051330 hasConceptScore W1986051330C154945302 @default.
- W1986051330 hasConceptScore W1986051330C15744967 @default.
- W1986051330 hasConceptScore W1986051330C2776401178 @default.
- W1986051330 hasConceptScore W1986051330C2780023022 @default.
- W1986051330 hasConceptScore W1986051330C28490314 @default.
- W1986051330 hasConceptScore W1986051330C41008148 @default.
- W1986051330 hasConceptScore W1986051330C41895202 @default.
- W1986051330 hasConceptScore W1986051330C50644808 @default.
- W1986051330 hasConceptScore W1986051330C52622490 @default.
- W1986051330 hasConceptScore W1986051330C83665646 @default.
- W1986051330 hasLocation W19860513301 @default.
- W1986051330 hasOpenAccess W1986051330 @default.
- W1986051330 hasPrimaryLocation W19860513301 @default.
- W1986051330 hasRelatedWork W2016461833 @default.
- W1986051330 hasRelatedWork W2046295345 @default.
- W1986051330 hasRelatedWork W2146076056 @default.
- W1986051330 hasRelatedWork W2350343535 @default.
- W1986051330 hasRelatedWork W2365346975 @default.
- W1986051330 hasRelatedWork W2385132419 @default.
- W1986051330 hasRelatedWork W2546942002 @default.
- W1986051330 hasRelatedWork W2772780115 @default.
- W1986051330 hasRelatedWork W2988724699 @default.
- W1986051330 hasRelatedWork W3197541072 @default.
- W1986051330 isParatext "false" @default.
- W1986051330 isRetracted "false" @default.
- W1986051330 magId "1986051330" @default.
- W1986051330 workType "article" @default.