Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298224001> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4298224001 abstract "This paper presents an end-to-end deep learning model for Automatic Speech Recognition (ASR) that transcribes Nepali speech to text. The model was trained and tested on the OpenSLR (audio, text) dataset. The majority of the audio dataset have silent gaps at both ends which are clipped during dataset preprocessing for a more uniform mapping of audio frames and their corresponding texts. Mel Frequency Cepstral Coe cients (MFCCs) are used as audio features to feed into the model. The model having Bidirectional LSTM paired with ResNet and one-dimensional CNN produces the best results for this dataset out of all the models (neural networks with variations of LSTM, GRU, CNN, and ResNet) that have been trained so far. This novel model uses Connectionist Temporal Classification (CTC) function for loss calculation during training and CTC beam search decoding for predicting characters as the most likely sequence of Nepali text. On the test dataset, the character error rate (CER) of 17.06 percent has been achieved." @default.
- W4298224001 created "2022-10-01" @default.
- W4298224001 creator A5001845313 @default.
- W4298224001 creator A5003077959 @default.
- W4298224001 creator A5076583709 @default.
- W4298224001 creator A5083404934 @default.
- W4298224001 creator A5087918614 @default.
- W4298224001 creator A5088367577 @default.
- W4298224001 date "2022-07-20" @default.
- W4298224001 modified "2023-10-01" @default.
- W4298224001 title "Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNet" @default.
- W4298224001 cites W1666984270 @default.
- W4298224001 cites W1677182931 @default.
- W4298224001 cites W2005708641 @default.
- W4298224001 cites W2064675550 @default.
- W4298224001 cites W2112796928 @default.
- W4298224001 cites W2119615570 @default.
- W4298224001 cites W2122797512 @default.
- W4298224001 cites W2127141656 @default.
- W4298224001 cites W2128454066 @default.
- W4298224001 cites W2131774270 @default.
- W4298224001 cites W2151402979 @default.
- W4298224001 cites W2157331557 @default.
- W4298224001 cites W2293634267 @default.
- W4298224001 cites W2327501763 @default.
- W4298224001 cites W2530876040 @default.
- W4298224001 cites W2766219058 @default.
- W4298224001 cites W2769205094 @default.
- W4298224001 cites W2770854636 @default.
- W4298224001 cites W2794209590 @default.
- W4298224001 cites W2895676041 @default.
- W4298224001 cites W2900582228 @default.
- W4298224001 cites W2938359332 @default.
- W4298224001 cites W2960110084 @default.
- W4298224001 cites W2970413753 @default.
- W4298224001 cites W3097030750 @default.
- W4298224001 cites W3132829453 @default.
- W4298224001 cites W3207558756 @default.
- W4298224001 doi "https://doi.org/10.1109/icict54344.2022.9850832" @default.
- W4298224001 hasPublicationYear "2022" @default.
- W4298224001 type Work @default.
- W4298224001 citedByCount "1" @default.
- W4298224001 countsByYear W42982240012023 @default.
- W4298224001 crossrefType "proceedings-article" @default.
- W4298224001 hasAuthorship W4298224001A5001845313 @default.
- W4298224001 hasAuthorship W4298224001A5003077959 @default.
- W4298224001 hasAuthorship W4298224001A5076583709 @default.
- W4298224001 hasAuthorship W4298224001A5083404934 @default.
- W4298224001 hasAuthorship W4298224001A5087918614 @default.
- W4298224001 hasAuthorship W4298224001A5088367577 @default.
- W4298224001 hasConcept C124952713 @default.
- W4298224001 hasConcept C137293760 @default.
- W4298224001 hasConcept C142362112 @default.
- W4298224001 hasConcept C153180895 @default.
- W4298224001 hasConcept C154945302 @default.
- W4298224001 hasConcept C23224414 @default.
- W4298224001 hasConcept C2780068402 @default.
- W4298224001 hasConcept C28490314 @default.
- W4298224001 hasConcept C34736171 @default.
- W4298224001 hasConcept C41008148 @default.
- W4298224001 hasConcept C50644808 @default.
- W4298224001 hasConcept C57273362 @default.
- W4298224001 hasConcept C76155785 @default.
- W4298224001 hasConceptScore W4298224001C124952713 @default.
- W4298224001 hasConceptScore W4298224001C137293760 @default.
- W4298224001 hasConceptScore W4298224001C142362112 @default.
- W4298224001 hasConceptScore W4298224001C153180895 @default.
- W4298224001 hasConceptScore W4298224001C154945302 @default.
- W4298224001 hasConceptScore W4298224001C23224414 @default.
- W4298224001 hasConceptScore W4298224001C2780068402 @default.
- W4298224001 hasConceptScore W4298224001C28490314 @default.
- W4298224001 hasConceptScore W4298224001C34736171 @default.
- W4298224001 hasConceptScore W4298224001C41008148 @default.
- W4298224001 hasConceptScore W4298224001C50644808 @default.
- W4298224001 hasConceptScore W4298224001C57273362 @default.
- W4298224001 hasConceptScore W4298224001C76155785 @default.
- W4298224001 hasLocation W42982240011 @default.
- W4298224001 hasOpenAccess W4298224001 @default.
- W4298224001 hasPrimaryLocation W42982240011 @default.
- W4298224001 hasRelatedWork W2058877998 @default.
- W4298224001 hasRelatedWork W2121992356 @default.
- W4298224001 hasRelatedWork W2225817525 @default.
- W4298224001 hasRelatedWork W2374918184 @default.
- W4298224001 hasRelatedWork W2380927352 @default.
- W4298224001 hasRelatedWork W2391959412 @default.
- W4298224001 hasRelatedWork W2768526037 @default.
- W4298224001 hasRelatedWork W2996122240 @default.
- W4298224001 hasRelatedWork W3128571556 @default.
- W4298224001 hasRelatedWork W60887625 @default.
- W4298224001 isParatext "false" @default.
- W4298224001 isRetracted "false" @default.
- W4298224001 workType "article" @default.