Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100453183> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3100453183 abstract "Convolutional neural networks are sensitive to unknown noisy condition in the test phase and so their performance degrades for the noisy data classification task including noisy speech recognition. In this research, a new convolutional neural network (CNN) model with data uncertainty handling; referred as NCNN (Neutrosophic Convolutional Neural Network); is proposed for classification task. Here, speech signals are used as input data and their noise is modeled as uncertainty. In this task, using speech spectrogram, a definition of uncertainty is proposed in neutrosophic (NS) domain. Uncertainty is computed for each Time-frequency point of speech spectrogram as like a pixel. Therefore, uncertainty matrix with the same size of spectrogram is created in NS domain. In the next step, a two parallel paths CNN classification model is proposed. Speech spectrogram is used as input of the first path and uncertainty matrix for the second path. The outputs of two paths are combined to compute the final output of the classifier. To show the effectiveness of the proposed method, it has been compared with conventional CNN on the isolated words of Aurora2 dataset. The proposed method achieves the average accuracy of 85.96 in noisy train data. It is more robust against Car, Airport and Subway noises with accuracies 90, 88 and 81 in test sets A, B and C, respectively. Results show that the proposed method outperforms conventional CNN with the improvement of 6, 5 and 2 percentage in test set A, test set B and test sets C, respectively. It means that the proposed method is more robust against noisy data and handle these data effectively." @default.
- W3100453183 created "2020-11-23" @default.
- W3100453183 creator A5007485536 @default.
- W3100453183 creator A5020216791 @default.
- W3100453183 creator A5068736509 @default.
- W3100453183 date "2019-03-01" @default.
- W3100453183 modified "2023-10-14" @default.
- W3100453183 title "A Convolutional Neural Network model based on Neutrosophy for Noisy Speech Recognition" @default.
- W3100453183 cites W1963974799 @default.
- W3100453183 cites W1973068905 @default.
- W3100453183 cites W2033310064 @default.
- W3100453183 cites W2045613518 @default.
- W3100453183 cites W2060175823 @default.
- W3100453183 cites W2067809457 @default.
- W3100453183 cites W2314737038 @default.
- W3100453183 cites W2587717635 @default.
- W3100453183 cites W2737142618 @default.
- W3100453183 cites W2745592547 @default.
- W3100453183 cites W2745858515 @default.
- W3100453183 cites W2749922855 @default.
- W3100453183 cites W2753085294 @default.
- W3100453183 cites W2766522389 @default.
- W3100453183 cites W2767367925 @default.
- W3100453183 cites W2963972644 @default.
- W3100453183 cites W4211007335 @default.
- W3100453183 doi "https://doi.org/10.1109/pria.2019.8786010" @default.
- W3100453183 hasPublicationYear "2019" @default.
- W3100453183 type Work @default.
- W3100453183 sameAs 3100453183 @default.
- W3100453183 citedByCount "5" @default.
- W3100453183 countsByYear W31004531832019 @default.
- W3100453183 countsByYear W31004531832020 @default.
- W3100453183 countsByYear W31004531832021 @default.
- W3100453183 countsByYear W31004531832022 @default.
- W3100453183 crossrefType "proceedings-article" @default.
- W3100453183 hasAuthorship W3100453183A5007485536 @default.
- W3100453183 hasAuthorship W3100453183A5020216791 @default.
- W3100453183 hasAuthorship W3100453183A5068736509 @default.
- W3100453183 hasBestOaLocation W31004531832 @default.
- W3100453183 hasConcept C115961682 @default.
- W3100453183 hasConcept C153180895 @default.
- W3100453183 hasConcept C154945302 @default.
- W3100453183 hasConcept C16910744 @default.
- W3100453183 hasConcept C169903167 @default.
- W3100453183 hasConcept C199360897 @default.
- W3100453183 hasConcept C28490314 @default.
- W3100453183 hasConcept C41008148 @default.
- W3100453183 hasConcept C45273575 @default.
- W3100453183 hasConcept C81363708 @default.
- W3100453183 hasConcept C95623464 @default.
- W3100453183 hasConcept C99498987 @default.
- W3100453183 hasConceptScore W3100453183C115961682 @default.
- W3100453183 hasConceptScore W3100453183C153180895 @default.
- W3100453183 hasConceptScore W3100453183C154945302 @default.
- W3100453183 hasConceptScore W3100453183C16910744 @default.
- W3100453183 hasConceptScore W3100453183C169903167 @default.
- W3100453183 hasConceptScore W3100453183C199360897 @default.
- W3100453183 hasConceptScore W3100453183C28490314 @default.
- W3100453183 hasConceptScore W3100453183C41008148 @default.
- W3100453183 hasConceptScore W3100453183C45273575 @default.
- W3100453183 hasConceptScore W3100453183C81363708 @default.
- W3100453183 hasConceptScore W3100453183C95623464 @default.
- W3100453183 hasConceptScore W3100453183C99498987 @default.
- W3100453183 hasLocation W31004531831 @default.
- W3100453183 hasLocation W31004531832 @default.
- W3100453183 hasLocation W31004531833 @default.
- W3100453183 hasOpenAccess W3100453183 @default.
- W3100453183 hasPrimaryLocation W31004531831 @default.
- W3100453183 hasRelatedWork W1574942924 @default.
- W3100453183 hasRelatedWork W2027071967 @default.
- W3100453183 hasRelatedWork W2028462208 @default.
- W3100453183 hasRelatedWork W2187490799 @default.
- W3100453183 hasRelatedWork W2982831492 @default.
- W3100453183 hasRelatedWork W3101081936 @default.
- W3100453183 hasRelatedWork W3138055416 @default.
- W3100453183 hasRelatedWork W4210826189 @default.
- W3100453183 hasRelatedWork W4285337533 @default.
- W3100453183 hasRelatedWork W4312887852 @default.
- W3100453183 isParatext "false" @default.
- W3100453183 isRetracted "false" @default.
- W3100453183 magId "3100453183" @default.
- W3100453183 workType "article" @default.