Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387493896> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4387493896 endingPage "012021" @default.
- W4387493896 startingPage "012021" @default.
- W4387493896 abstract "Abstract While implementations of speech recognition grow rapidly in recent years and are slowly being integrated into our daily devices, the problem of noise robustness is still a challenging task, even with the recent advancement of deep learning technologies for speech recognition. The presence of noise may cause a mismatch between training, which is performed in clean conditions, and noisy testing conditions. This paper proposes a method to extract features for speech recognition by employing features derived under the power law scale, i.e., the Power-Normalized Cepstral Coefficient (PNCC). The power-law can provide better compression in low-energy regions so that it is not sensitive when the speech signal is distorted by noise. The features are implemented on speech recognition based on Convolutional Neural Networks (CNNs). The experiments were carried out by TensorFlow’s Speech Command Dataset mixed with various signal-to-noise ratio to evaluate the method. The experimental findings indicate that the accuracy ranges from 81% to 86%." @default.
- W4387493896 created "2023-10-11" @default.
- W4387493896 creator A5014790414 @default.
- W4387493896 creator A5018559332 @default.
- W4387493896 creator A5021241693 @default.
- W4387493896 creator A5037899058 @default.
- W4387493896 date "2023-09-01" @default.
- W4387493896 modified "2023-10-12" @default.
- W4387493896 title "The Power-Normalized Cepstral Coefficient (PNCC) for convolutional neural networks-based robust speech command recognition" @default.
- W4387493896 cites W2112796928 @default.
- W4387493896 cites W2163632146 @default.
- W4387493896 cites W2326699523 @default.
- W4387493896 cites W3001387854 @default.
- W4387493896 doi "https://doi.org/10.1088/1742-6596/2596/1/012021" @default.
- W4387493896 hasPublicationYear "2023" @default.
- W4387493896 type Work @default.
- W4387493896 citedByCount "0" @default.
- W4387493896 crossrefType "journal-article" @default.
- W4387493896 hasAuthorship W4387493896A5014790414 @default.
- W4387493896 hasAuthorship W4387493896A5018559332 @default.
- W4387493896 hasAuthorship W4387493896A5021241693 @default.
- W4387493896 hasAuthorship W4387493896A5037899058 @default.
- W4387493896 hasBestOaLocation W43874938961 @default.
- W4387493896 hasConcept C104317684 @default.
- W4387493896 hasConcept C108583219 @default.
- W4387493896 hasConcept C115961682 @default.
- W4387493896 hasConcept C151989614 @default.
- W4387493896 hasConcept C153180895 @default.
- W4387493896 hasConcept C154945302 @default.
- W4387493896 hasConcept C185592680 @default.
- W4387493896 hasConcept C28490314 @default.
- W4387493896 hasConcept C41008148 @default.
- W4387493896 hasConcept C52622490 @default.
- W4387493896 hasConcept C55493867 @default.
- W4387493896 hasConcept C63479239 @default.
- W4387493896 hasConcept C81363708 @default.
- W4387493896 hasConcept C88485024 @default.
- W4387493896 hasConcept C99498987 @default.
- W4387493896 hasConceptScore W4387493896C104317684 @default.
- W4387493896 hasConceptScore W4387493896C108583219 @default.
- W4387493896 hasConceptScore W4387493896C115961682 @default.
- W4387493896 hasConceptScore W4387493896C151989614 @default.
- W4387493896 hasConceptScore W4387493896C153180895 @default.
- W4387493896 hasConceptScore W4387493896C154945302 @default.
- W4387493896 hasConceptScore W4387493896C185592680 @default.
- W4387493896 hasConceptScore W4387493896C28490314 @default.
- W4387493896 hasConceptScore W4387493896C41008148 @default.
- W4387493896 hasConceptScore W4387493896C52622490 @default.
- W4387493896 hasConceptScore W4387493896C55493867 @default.
- W4387493896 hasConceptScore W4387493896C63479239 @default.
- W4387493896 hasConceptScore W4387493896C81363708 @default.
- W4387493896 hasConceptScore W4387493896C88485024 @default.
- W4387493896 hasConceptScore W4387493896C99498987 @default.
- W4387493896 hasIssue "1" @default.
- W4387493896 hasLocation W43874938961 @default.
- W4387493896 hasOpenAccess W4387493896 @default.
- W4387493896 hasPrimaryLocation W43874938961 @default.
- W4387493896 hasRelatedWork W106160982 @default.
- W4387493896 hasRelatedWork W1980297060 @default.
- W4387493896 hasRelatedWork W2018086531 @default.
- W4387493896 hasRelatedWork W2373675101 @default.
- W4387493896 hasRelatedWork W2387604097 @default.
- W4387493896 hasRelatedWork W3133861977 @default.
- W4387493896 hasRelatedWork W3167935049 @default.
- W4387493896 hasRelatedWork W3193565141 @default.
- W4387493896 hasRelatedWork W4226493464 @default.
- W4387493896 hasRelatedWork W4312417841 @default.
- W4387493896 hasVolume "2596" @default.
- W4387493896 isParatext "false" @default.
- W4387493896 isRetracted "false" @default.
- W4387493896 workType "article" @default.