Matches in SemOpenAlex for { <https://semopenalex.org/work/W2009782887> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2009782887 abstract "In this paper, a novel method based on feedforward neural network is proposed to optimize the confidence measure for improving a mandarine keyword spotting system. Keyword spotting is to detect the occurrences of a pre-defined list of keywords in the input speech, and confidence measure is an critical part in the verification stage of keyword spotting. Posterior confidence has been widely used and was verified to be effective. In some previous works, the optimization of posterior confidence has been proposed, which linearly transforms the phone-level confidence into the word-level confidence. On this basis, we propose a neural network based method that make a non-linear transformation. In addition, a sparse activation and back-propagation strategy is proposed to make this method feasible and work fast. In the experiments, the proposed method is compared to other two previous methods. To evaluate performance, two most commonly used measures are considered: AUC and EER. The experimental result shows that the proposed method is effective and achieved the best performance among three methods." @default.
- W2009782887 created "2016-06-24" @default.
- W2009782887 creator A5005083870 @default.
- W2009782887 creator A5034202632 @default.
- W2009782887 creator A5053661520 @default.
- W2009782887 date "2014-07-01" @default.
- W2009782887 modified "2023-09-26" @default.
- W2009782887 title "Improved keyword spotting system by optimizing posterior confidence measure vector using feed-forward neural network" @default.
- W2009782887 cites W1768248362 @default.
- W2009782887 cites W1820599268 @default.
- W2009782887 cites W2028547769 @default.
- W2009782887 cites W2043422002 @default.
- W2009782887 cites W2086267546 @default.
- W2009782887 cites W2109933326 @default.
- W2009782887 cites W2142806759 @default.
- W2009782887 cites W2145215282 @default.
- W2009782887 cites W2396838512 @default.
- W2009782887 cites W2405666970 @default.
- W2009782887 doi "https://doi.org/10.1109/ijcnn.2014.6889823" @default.
- W2009782887 hasPublicationYear "2014" @default.
- W2009782887 type Work @default.
- W2009782887 sameAs 2009782887 @default.
- W2009782887 citedByCount "3" @default.
- W2009782887 countsByYear W20097828872016 @default.
- W2009782887 countsByYear W20097828872018 @default.
- W2009782887 countsByYear W20097828872020 @default.
- W2009782887 crossrefType "proceedings-article" @default.
- W2009782887 hasAuthorship W2009782887A5005083870 @default.
- W2009782887 hasAuthorship W2009782887A5034202632 @default.
- W2009782887 hasAuthorship W2009782887A5053661520 @default.
- W2009782887 hasConcept C105795698 @default.
- W2009782887 hasConcept C124101348 @default.
- W2009782887 hasConcept C153180895 @default.
- W2009782887 hasConcept C154945302 @default.
- W2009782887 hasConcept C2779506182 @default.
- W2009782887 hasConcept C2780009758 @default.
- W2009782887 hasConcept C2781213101 @default.
- W2009782887 hasConcept C33923547 @default.
- W2009782887 hasConcept C41008148 @default.
- W2009782887 hasConcept C44249647 @default.
- W2009782887 hasConcept C47702885 @default.
- W2009782887 hasConcept C50644808 @default.
- W2009782887 hasConceptScore W2009782887C105795698 @default.
- W2009782887 hasConceptScore W2009782887C124101348 @default.
- W2009782887 hasConceptScore W2009782887C153180895 @default.
- W2009782887 hasConceptScore W2009782887C154945302 @default.
- W2009782887 hasConceptScore W2009782887C2779506182 @default.
- W2009782887 hasConceptScore W2009782887C2780009758 @default.
- W2009782887 hasConceptScore W2009782887C2781213101 @default.
- W2009782887 hasConceptScore W2009782887C33923547 @default.
- W2009782887 hasConceptScore W2009782887C41008148 @default.
- W2009782887 hasConceptScore W2009782887C44249647 @default.
- W2009782887 hasConceptScore W2009782887C47702885 @default.
- W2009782887 hasConceptScore W2009782887C50644808 @default.
- W2009782887 hasLocation W20097828871 @default.
- W2009782887 hasOpenAccess W2009782887 @default.
- W2009782887 hasPrimaryLocation W20097828871 @default.
- W2009782887 hasRelatedWork W162591155 @default.
- W2009782887 hasRelatedWork W1767027142 @default.
- W2009782887 hasRelatedWork W1802155944 @default.
- W2009782887 hasRelatedWork W1856119614 @default.
- W2009782887 hasRelatedWork W1959963859 @default.
- W2009782887 hasRelatedWork W2000406544 @default.
- W2009782887 hasRelatedWork W2029733119 @default.
- W2009782887 hasRelatedWork W2033120629 @default.
- W2009782887 hasRelatedWork W2044381054 @default.
- W2009782887 hasRelatedWork W2096341811 @default.
- W2009782887 hasRelatedWork W2135096206 @default.
- W2009782887 hasRelatedWork W2138168847 @default.
- W2009782887 hasRelatedWork W2141021174 @default.
- W2009782887 hasRelatedWork W2146410987 @default.
- W2009782887 hasRelatedWork W2148054661 @default.
- W2009782887 hasRelatedWork W2160985694 @default.
- W2009782887 hasRelatedWork W2354384964 @default.
- W2009782887 hasRelatedWork W2509658457 @default.
- W2009782887 hasRelatedWork W2902572630 @default.
- W2009782887 hasRelatedWork W3097246512 @default.
- W2009782887 isParatext "false" @default.
- W2009782887 isRetracted "false" @default.
- W2009782887 magId "2009782887" @default.
- W2009782887 workType "article" @default.