Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309573071> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4309573071 endingPage "119293" @default.
- W4309573071 startingPage "119293" @default.
- W4309573071 abstract "Speech recognition aims to convert human speech into text and has applications in security, healthcare, commerce, automobiles, and technology, just to name a few. Inserting residual neural networks before recurrent neural network cells improves accuracy and cuts training time by a good margin. Furthermore, layer normalization instead of batch normalization is more effective in model training and performance enhancement. Also, the size of the datasets presents tremendous influences in achieving the best performance. Leveraging these tricks, this article proposes an automatic speech recognition model with a stacked five layers of customized Residual Convolution Neural Network and seven layers of Bi-Directional Gated Recurrent Units, including a logarithmic softmax for the model output. Each of them incorporates a learnable per-element affine parameter-based layer normalization technique. The training and testing of the new model were conducted on the LibriSpeech corpus and LJ Speech dataset. The experimental results demonstrate a character error rate (CER) of 4.7 and 3.61% on the two datasets, respectively, with only 33 million parameters without the requirement of any external language model." @default.
- W4309573071 created "2022-11-28" @default.
- W4309573071 creator A5015412270 @default.
- W4309573071 creator A5045379032 @default.
- W4309573071 creator A5056546246 @default.
- W4309573071 creator A5085872646 @default.
- W4309573071 date "2023-04-01" @default.
- W4309573071 modified "2023-10-06" @default.
- W4309573071 title "A customized residual neural network and bi-directional gated recurrent unit-based automatic speech recognition model" @default.
- W4309573071 cites W2127141656 @default.
- W4309573071 cites W2156279557 @default.
- W4309573071 cites W2168961642 @default.
- W4309573071 cites W2964350391 @default.
- W4309573071 cites W3035421056 @default.
- W4309573071 cites W3095173472 @default.
- W4309573071 cites W3097159520 @default.
- W4309573071 cites W3163292139 @default.
- W4309573071 cites W3201017142 @default.
- W4309573071 doi "https://doi.org/10.1016/j.eswa.2022.119293" @default.
- W4309573071 hasPublicationYear "2023" @default.
- W4309573071 type Work @default.
- W4309573071 citedByCount "0" @default.
- W4309573071 crossrefType "journal-article" @default.
- W4309573071 hasAuthorship W4309573071A5015412270 @default.
- W4309573071 hasAuthorship W4309573071A5045379032 @default.
- W4309573071 hasAuthorship W4309573071A5056546246 @default.
- W4309573071 hasAuthorship W4309573071A5085872646 @default.
- W4309573071 hasBestOaLocation W43095730711 @default.
- W4309573071 hasConcept C11413529 @default.
- W4309573071 hasConcept C136886441 @default.
- W4309573071 hasConcept C137293760 @default.
- W4309573071 hasConcept C144024400 @default.
- W4309573071 hasConcept C147168706 @default.
- W4309573071 hasConcept C153180895 @default.
- W4309573071 hasConcept C154945302 @default.
- W4309573071 hasConcept C155512373 @default.
- W4309573071 hasConcept C188441871 @default.
- W4309573071 hasConcept C19165224 @default.
- W4309573071 hasConcept C202444582 @default.
- W4309573071 hasConcept C28490314 @default.
- W4309573071 hasConcept C33923547 @default.
- W4309573071 hasConcept C40969351 @default.
- W4309573071 hasConcept C41008148 @default.
- W4309573071 hasConcept C50644808 @default.
- W4309573071 hasConcept C81363708 @default.
- W4309573071 hasConcept C92757383 @default.
- W4309573071 hasConceptScore W4309573071C11413529 @default.
- W4309573071 hasConceptScore W4309573071C136886441 @default.
- W4309573071 hasConceptScore W4309573071C137293760 @default.
- W4309573071 hasConceptScore W4309573071C144024400 @default.
- W4309573071 hasConceptScore W4309573071C147168706 @default.
- W4309573071 hasConceptScore W4309573071C153180895 @default.
- W4309573071 hasConceptScore W4309573071C154945302 @default.
- W4309573071 hasConceptScore W4309573071C155512373 @default.
- W4309573071 hasConceptScore W4309573071C188441871 @default.
- W4309573071 hasConceptScore W4309573071C19165224 @default.
- W4309573071 hasConceptScore W4309573071C202444582 @default.
- W4309573071 hasConceptScore W4309573071C28490314 @default.
- W4309573071 hasConceptScore W4309573071C33923547 @default.
- W4309573071 hasConceptScore W4309573071C40969351 @default.
- W4309573071 hasConceptScore W4309573071C41008148 @default.
- W4309573071 hasConceptScore W4309573071C50644808 @default.
- W4309573071 hasConceptScore W4309573071C81363708 @default.
- W4309573071 hasConceptScore W4309573071C92757383 @default.
- W4309573071 hasFunder F4320335322 @default.
- W4309573071 hasLocation W43095730711 @default.
- W4309573071 hasLocation W43095730712 @default.
- W4309573071 hasOpenAccess W4309573071 @default.
- W4309573071 hasPrimaryLocation W43095730711 @default.
- W4309573071 hasRelatedWork W2263232528 @default.
- W4309573071 hasRelatedWork W2608712415 @default.
- W4309573071 hasRelatedWork W2743258233 @default.
- W4309573071 hasRelatedWork W2782005958 @default.
- W4309573071 hasRelatedWork W2784158897 @default.
- W4309573071 hasRelatedWork W2963414781 @default.
- W4309573071 hasRelatedWork W2977314777 @default.
- W4309573071 hasRelatedWork W4205868073 @default.
- W4309573071 hasRelatedWork W4288754470 @default.
- W4309573071 hasRelatedWork W4307834408 @default.
- W4309573071 hasVolume "215" @default.
- W4309573071 isParatext "false" @default.
- W4309573071 isRetracted "false" @default.
- W4309573071 workType "article" @default.