FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2932319281> ?p ?o ?g. }

• W2932319281 abstract "In this paper, we report state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data. Our model, Jasper, uses only 1D convolutions, batch normalization, ReLU, dropout, and residual connections. To improve training, we further introduce a new layer-wise optimizer called NovoGrad. Through experiments, we demonstrate that the proposed deep architecture performs as well or better than more complex choices. Our deepest Jasper variant uses 54 convolutional layers. With this architecture, we achieve 2.95% WER using a beam-search decoder with an external neural language model and 3.86% WER with a greedy decoder on LibriSpeech test-clean. We also report competitive results on the Wall Street Journal and the Hub5'00 conversational evaluation datasets." @default.
• W2932319281 created "2019-04-11" @default.
• W2932319281 creator A5024453480 @default.
• W2932319281 creator A5026088310 @default.
• W2932319281 creator A5032957280 @default.
• W2932319281 creator A5048403564 @default.
• W2932319281 creator A5050071432 @default.
• W2932319281 creator A5079416691 @default.
• W2932319281 creator A5080235829 @default.
• W2932319281 creator A5090541149 @default.
• W2932319281 date "2019-04-05" @default.
• W2932319281 modified "2023-09-29" @default.
• W2932319281 title "Jasper: An End-to-End Convolutional Neural Acoustic Model" @default.
• W2932319281 cites W1494198834 @default.
• W2932319281 cites W2048060899 @default.
• W2932319281 cites W2127141656 @default.
• W2932319281 cites W2134800885 @default.
• W2932319281 cites W2148099973 @default.
• W2932319281 cites W2184045248 @default.
• W2932319281 cites W2193413348 @default.
• W2932319281 cites W2407080277 @default.
• W2932319281 cites W2511730936 @default.
• W2932319281 cites W2520160253 @default.
• W2932319281 cites W2530876040 @default.
• W2932319281 cites W2739427748 @default.
• W2932319281 cites W2755543420 @default.
• W2932319281 cites W2763421725 @default.
• W2932319281 cites W2781384251 @default.
• W2932319281 cites W2782451907 @default.
• W2932319281 cites W2799800213 @default.
• W2932319281 cites W2804704270 @default.
• W2932319281 cites W2888867175 @default.
• W2932319281 cites W2888907095 @default.
• W2932319281 cites W2889163603 @default.
• W2932319281 cites W2889282842 @default.
• W2932319281 cites W2898181186 @default.
• W2932319281 cites W2904818793 @default.
• W2932319281 cites W2906625520 @default.
• W2932319281 cites W2908510526 @default.
• W2932319281 cites W2936774411 @default.
• W2932319281 cites W2945697643 @default.
• W2932319281 cites W2949117887 @default.
• W2932319281 cites W2962949994 @default.
• W2932319281 cites W2963403664 @default.
• W2932319281 cites W2963636093 @default.
• W2932319281 cites W2963685250 @default.
• W2932319281 cites W2963827914 @default.
• W2932319281 cites W2963970792 @default.
• W2932319281 cites W2964121744 @default.
• W2932319281 cites W3023071679 @default.
• W2932319281 doi "https://doi.org/10.48550/arxiv.1904.03288" @default.
• W2932319281 hasPublicationYear "2019" @default.
• W2932319281 type Work @default.
• W2932319281 sameAs 2932319281 @default.
• W2932319281 citedByCount "28" @default.
• W2932319281 countsByYear W29323192812019 @default.
• W2932319281 countsByYear W29323192812020 @default.
• W2932319281 countsByYear W29323192812021 @default.
• W2932319281 countsByYear W29323192812022 @default.
• W2932319281 countsByYear W29323192812023 @default.
• W2932319281 crossrefType "posted-content" @default.
• W2932319281 hasAuthorship W2932319281A5024453480 @default.
• W2932319281 hasAuthorship W2932319281A5026088310 @default.
• W2932319281 hasAuthorship W2932319281A5032957280 @default.
• W2932319281 hasAuthorship W2932319281A5048403564 @default.
• W2932319281 hasAuthorship W2932319281A5050071432 @default.
• W2932319281 hasAuthorship W2932319281A5079416691 @default.
• W2932319281 hasAuthorship W2932319281A5080235829 @default.
• W2932319281 hasAuthorship W2932319281A5090541149 @default.
• W2932319281 hasBestOaLocation W29323192811 @default.
• W2932319281 hasConcept C11413529 @default.
• W2932319281 hasConcept C119857082 @default.
• W2932319281 hasConcept C123657996 @default.
• W2932319281 hasConcept C125583679 @default.
• W2932319281 hasConcept C136886441 @default.
• W2932319281 hasConcept C137293760 @default.
• W2932319281 hasConcept C142362112 @default.
• W2932319281 hasConcept C144024400 @default.
• W2932319281 hasConcept C153349607 @default.
• W2932319281 hasConcept C154945302 @default.
• W2932319281 hasConcept C155512373 @default.
• W2932319281 hasConcept C19165224 @default.
• W2932319281 hasConcept C19889080 @default.
• W2932319281 hasConcept C2776145597 @default.
• W2932319281 hasConcept C28490314 @default.
• W2932319281 hasConcept C41008148 @default.
• W2932319281 hasConcept C57273362 @default.
• W2932319281 hasConcept C74296488 @default.
• W2932319281 hasConcept C81363708 @default.
• W2932319281 hasConceptScore W2932319281C11413529 @default.
• W2932319281 hasConceptScore W2932319281C119857082 @default.
• W2932319281 hasConceptScore W2932319281C123657996 @default.
• W2932319281 hasConceptScore W2932319281C125583679 @default.
• W2932319281 hasConceptScore W2932319281C136886441 @default.
• W2932319281 hasConceptScore W2932319281C137293760 @default.
• W2932319281 hasConceptScore W2932319281C142362112 @default.
• W2932319281 hasConceptScore W2932319281C144024400 @default.
• W2932319281 hasConceptScore W2932319281C153349607 @default.
• W2932319281 hasConceptScore W2932319281C154945302 @default.
• W2932319281 hasConceptScore W2932319281C155512373 @default.

• next