Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313194105> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4313194105 abstract "This paper investigates multiplicative interactions such as auto-correlations between features in neural networks. Conventionally, in the field of pattern recognition, including spoken language processing, non-linear relationships among features, e.g., high-order local auto-correlations and multiplicative features seen in sigma-pi cells, have been explored. These features are specifically designed to capture the correlations in the spectro-temporal regions to gain robustness for classification. However, the features based on the multiplicative interactions, or elementary second-order statistics like autocorrelations, have not been well explored in speech processing. Accordingly, there would be open to discussion about the performance improvement of classification problems employing multiplicative features. Thus, we will investigate the multiplicative interactions extracted from spectro-temporal regions through the neural networks. We will conduct the experiments on three kinds of classification tasks, i.e., acoustic event/scene classification and speech recognition, while implementing a simple multiplicative module to produce the interactions between features. Our proposed neural networks with multiplicative blocks achieved promising improvements in all tasks, and the experimental results show that the proposed method improved accuracy by 0.45 % in the acoustic event classification, by 2.15 % in the acoustic scene classification, and the phone error rate (PER) by 6.5 % in the phoneme recognition." @default.
- W4313194105 created "2023-01-06" @default.
- W4313194105 creator A5079042022 @default.
- W4313194105 date "2022-08-01" @default.
- W4313194105 modified "2023-10-16" @default.
- W4313194105 title "Neural Networks Using Multiplicative Features Based on Second-Order Statistics for Acoustic and Speech Applications" @default.
- W4313194105 cites W2005522781 @default.
- W4313194105 cites W2036785409 @default.
- W4313194105 cites W2194775991 @default.
- W4313194105 cites W2947497515 @default.
- W4313194105 cites W2954930822 @default.
- W4313194105 cites W2962780374 @default.
- W4313194105 cites W2963543871 @default.
- W4313194105 cites W2963548618 @default.
- W4313194105 cites W2964231884 @default.
- W4313194105 cites W3097777922 @default.
- W4313194105 cites W3197981388 @default.
- W4313194105 cites W3198446739 @default.
- W4313194105 doi "https://doi.org/10.1109/arace56528.2022.00029" @default.
- W4313194105 hasPublicationYear "2022" @default.
- W4313194105 type Work @default.
- W4313194105 citedByCount "0" @default.
- W4313194105 crossrefType "proceedings-article" @default.
- W4313194105 hasAuthorship W4313194105A5079042022 @default.
- W4313194105 hasConcept C104317684 @default.
- W4313194105 hasConcept C134306372 @default.
- W4313194105 hasConcept C138885662 @default.
- W4313194105 hasConcept C153180895 @default.
- W4313194105 hasConcept C154945302 @default.
- W4313194105 hasConcept C185592680 @default.
- W4313194105 hasConcept C2778707766 @default.
- W4313194105 hasConcept C28490314 @default.
- W4313194105 hasConcept C33923547 @default.
- W4313194105 hasConcept C41008148 @default.
- W4313194105 hasConcept C41895202 @default.
- W4313194105 hasConcept C42747912 @default.
- W4313194105 hasConcept C50644808 @default.
- W4313194105 hasConcept C55493867 @default.
- W4313194105 hasConcept C61328038 @default.
- W4313194105 hasConcept C63479239 @default.
- W4313194105 hasConceptScore W4313194105C104317684 @default.
- W4313194105 hasConceptScore W4313194105C134306372 @default.
- W4313194105 hasConceptScore W4313194105C138885662 @default.
- W4313194105 hasConceptScore W4313194105C153180895 @default.
- W4313194105 hasConceptScore W4313194105C154945302 @default.
- W4313194105 hasConceptScore W4313194105C185592680 @default.
- W4313194105 hasConceptScore W4313194105C2778707766 @default.
- W4313194105 hasConceptScore W4313194105C28490314 @default.
- W4313194105 hasConceptScore W4313194105C33923547 @default.
- W4313194105 hasConceptScore W4313194105C41008148 @default.
- W4313194105 hasConceptScore W4313194105C41895202 @default.
- W4313194105 hasConceptScore W4313194105C42747912 @default.
- W4313194105 hasConceptScore W4313194105C50644808 @default.
- W4313194105 hasConceptScore W4313194105C55493867 @default.
- W4313194105 hasConceptScore W4313194105C61328038 @default.
- W4313194105 hasConceptScore W4313194105C63479239 @default.
- W4313194105 hasLocation W43131941051 @default.
- W4313194105 hasOpenAccess W4313194105 @default.
- W4313194105 hasPrimaryLocation W43131941051 @default.
- W4313194105 hasRelatedWork W1520941986 @default.
- W4313194105 hasRelatedWork W1557666054 @default.
- W4313194105 hasRelatedWork W2000534859 @default.
- W4313194105 hasRelatedWork W2024146327 @default.
- W4313194105 hasRelatedWork W2097834170 @default.
- W4313194105 hasRelatedWork W2106462793 @default.
- W4313194105 hasRelatedWork W2114887563 @default.
- W4313194105 hasRelatedWork W2134867751 @default.
- W4313194105 hasRelatedWork W2399955410 @default.
- W4313194105 hasRelatedWork W2935803161 @default.
- W4313194105 isParatext "false" @default.
- W4313194105 isRetracted "false" @default.
- W4313194105 workType "article" @default.