Matches in SemOpenAlex for { <https://semopenalex.org/work/W2146264217> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2146264217 abstract "Recurrent neural networks (RNN) provide a solution for low cost speech recognition systems (SRS) in mass products or in products with energetic constraints if their inherent parallelism could be exploited in a hardware realization. Actually, the computational complexity of SRS based on fully recurrent neural networks (FRNN), e.g. the large number of connections, prevents a hardware realization. We introduce locally recurrent neural networks (LRNN) in order to keep the properties of RNN on the one hand and to reduce the connectivity density of the network on the other hand. By simulation experiments it is shown that the recognition capability of LRNN is equivalent to that of FRNN and superior to other proposed network architectures. Furthermore, it is shown that with an appropriate representation of the network parameters and a retraining of the network 5 Bit quantization of the weights and activities is possible without significant loss in recognition performance." @default.
- W2146264217 created "2016-06-24" @default.
- W2146264217 creator A5027839463 @default.
- W2146264217 creator A5068691722 @default.
- W2146264217 creator A5080595664 @default.
- W2146264217 date "2002-12-24" @default.
- W2146264217 modified "2023-09-25" @default.
- W2146264217 title "Strategies for reducing the complexity of a RNN based speech recognizer" @default.
- W2146264217 cites W1662819202 @default.
- W2146264217 cites W1996741810 @default.
- W2146264217 cites W2057653135 @default.
- W2146264217 cites W2107878631 @default.
- W2146264217 cites W2110871230 @default.
- W2146264217 cites W2117671523 @default.
- W2146264217 cites W2118273349 @default.
- W2146264217 doi "https://doi.org/10.1109/icassp.1996.550596" @default.
- W2146264217 hasPublicationYear "2002" @default.
- W2146264217 type Work @default.
- W2146264217 sameAs 2146264217 @default.
- W2146264217 citedByCount "5" @default.
- W2146264217 crossrefType "proceedings-article" @default.
- W2146264217 hasAuthorship W2146264217A5027839463 @default.
- W2146264217 hasAuthorship W2146264217A5068691722 @default.
- W2146264217 hasAuthorship W2146264217A5080595664 @default.
- W2146264217 hasConcept C105795698 @default.
- W2146264217 hasConcept C11413529 @default.
- W2146264217 hasConcept C147168706 @default.
- W2146264217 hasConcept C154945302 @default.
- W2146264217 hasConcept C17744445 @default.
- W2146264217 hasConcept C179799912 @default.
- W2146264217 hasConcept C199539241 @default.
- W2146264217 hasConcept C2776359362 @default.
- W2146264217 hasConcept C2781089630 @default.
- W2146264217 hasConcept C28490314 @default.
- W2146264217 hasConcept C28855332 @default.
- W2146264217 hasConcept C33923547 @default.
- W2146264217 hasConcept C41008148 @default.
- W2146264217 hasConcept C50644808 @default.
- W2146264217 hasConcept C94625758 @default.
- W2146264217 hasConceptScore W2146264217C105795698 @default.
- W2146264217 hasConceptScore W2146264217C11413529 @default.
- W2146264217 hasConceptScore W2146264217C147168706 @default.
- W2146264217 hasConceptScore W2146264217C154945302 @default.
- W2146264217 hasConceptScore W2146264217C17744445 @default.
- W2146264217 hasConceptScore W2146264217C179799912 @default.
- W2146264217 hasConceptScore W2146264217C199539241 @default.
- W2146264217 hasConceptScore W2146264217C2776359362 @default.
- W2146264217 hasConceptScore W2146264217C2781089630 @default.
- W2146264217 hasConceptScore W2146264217C28490314 @default.
- W2146264217 hasConceptScore W2146264217C28855332 @default.
- W2146264217 hasConceptScore W2146264217C33923547 @default.
- W2146264217 hasConceptScore W2146264217C41008148 @default.
- W2146264217 hasConceptScore W2146264217C50644808 @default.
- W2146264217 hasConceptScore W2146264217C94625758 @default.
- W2146264217 hasLocation W21462642171 @default.
- W2146264217 hasOpenAccess W2146264217 @default.
- W2146264217 hasPrimaryLocation W21462642171 @default.
- W2146264217 hasRelatedWork W1605005685 @default.
- W2146264217 hasRelatedWork W1835926121 @default.
- W2146264217 hasRelatedWork W2089093251 @default.
- W2146264217 hasRelatedWork W2138706153 @default.
- W2146264217 hasRelatedWork W2149009003 @default.
- W2146264217 hasRelatedWork W2157225572 @default.
- W2146264217 hasRelatedWork W2164741935 @default.
- W2146264217 hasRelatedWork W2165350140 @default.
- W2146264217 hasRelatedWork W2170258954 @default.
- W2146264217 hasRelatedWork W2171621711 @default.
- W2146264217 hasRelatedWork W2171928131 @default.
- W2146264217 hasRelatedWork W2260779673 @default.
- W2146264217 hasRelatedWork W2356350644 @default.
- W2146264217 hasRelatedWork W2537686215 @default.
- W2146264217 hasRelatedWork W2560127380 @default.
- W2146264217 hasRelatedWork W2593221942 @default.
- W2146264217 hasRelatedWork W2939767745 @default.
- W2146264217 hasRelatedWork W3016768016 @default.
- W2146264217 hasRelatedWork W3094631814 @default.
- W2146264217 hasRelatedWork W3129780921 @default.
- W2146264217 isParatext "false" @default.
- W2146264217 isRetracted "false" @default.
- W2146264217 magId "2146264217" @default.
- W2146264217 workType "article" @default.