Matches in SemOpenAlex for { <https://semopenalex.org/work/W2117318574> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2117318574 abstract "Hybrid systems, using neural networks (NNs) and hidden Markov models (HMMs) are designed to take advantage of both methods; the pattern classification power of NNs and the temporal modelling structure of HMMs. This paper describes the use of expert sub-network modules of the type time delay neural network (TDNN) for phone recognition of continuous speech. The originality of the hybrid system developed is in combining the probabilities of the modular TDNN architecture with those of CDHMMs during the recognition phase. On three speakers of the DARPA RM speaker-dependent task, we show that these small TDNNs trained on phone ambiguities can improve word recognition performance of state-of-the-art CDHMMs. The TDNN implementation achieved a word error rate reduction of 15%. We discuss strategies for extending this approach from the DARPA RM speaker-dependent database to the larger DARPA RM speaker-independent database. >" @default.
- W2117318574 created "2016-06-24" @default.
- W2117318574 creator A5002036844 @default.
- W2117318574 creator A5047162050 @default.
- W2117318574 date "2002-12-17" @default.
- W2117318574 modified "2023-09-25" @default.
- W2117318574 title "Hybrid system combining expert-TDNNs and HMMs for continuous speech recognition" @default.
- W2117318574 cites W1643320849 @default.
- W2117318574 cites W1977434607 @default.
- W2117318574 cites W2083811208 @default.
- W2117318574 cites W2145366657 @default.
- W2117318574 cites W2151135538 @default.
- W2117318574 cites W2166659534 @default.
- W2117318574 cites W248072654 @default.
- W2117318574 cites W47421369 @default.
- W2117318574 doi "https://doi.org/10.1109/icassp.1994.389693" @default.
- W2117318574 hasPublicationYear "2002" @default.
- W2117318574 type Work @default.
- W2117318574 sameAs 2117318574 @default.
- W2117318574 citedByCount "1" @default.
- W2117318574 crossrefType "proceedings-article" @default.
- W2117318574 hasAuthorship W2117318574A5002036844 @default.
- W2117318574 hasAuthorship W2117318574A5047162050 @default.
- W2117318574 hasConcept C133892786 @default.
- W2117318574 hasConcept C138885662 @default.
- W2117318574 hasConcept C153180895 @default.
- W2117318574 hasConcept C154945302 @default.
- W2117318574 hasConcept C175202392 @default.
- W2117318574 hasConcept C23224414 @default.
- W2117318574 hasConcept C2778707766 @default.
- W2117318574 hasConcept C28490314 @default.
- W2117318574 hasConcept C40969351 @default.
- W2117318574 hasConcept C41008148 @default.
- W2117318574 hasConcept C41895202 @default.
- W2117318574 hasConcept C50644808 @default.
- W2117318574 hasConcept C90805587 @default.
- W2117318574 hasConceptScore W2117318574C133892786 @default.
- W2117318574 hasConceptScore W2117318574C138885662 @default.
- W2117318574 hasConceptScore W2117318574C153180895 @default.
- W2117318574 hasConceptScore W2117318574C154945302 @default.
- W2117318574 hasConceptScore W2117318574C175202392 @default.
- W2117318574 hasConceptScore W2117318574C23224414 @default.
- W2117318574 hasConceptScore W2117318574C2778707766 @default.
- W2117318574 hasConceptScore W2117318574C28490314 @default.
- W2117318574 hasConceptScore W2117318574C40969351 @default.
- W2117318574 hasConceptScore W2117318574C41008148 @default.
- W2117318574 hasConceptScore W2117318574C41895202 @default.
- W2117318574 hasConceptScore W2117318574C50644808 @default.
- W2117318574 hasConceptScore W2117318574C90805587 @default.
- W2117318574 hasLocation W21173185741 @default.
- W2117318574 hasOpenAccess W2117318574 @default.
- W2117318574 hasPrimaryLocation W21173185741 @default.
- W2117318574 hasRelatedWork W1576165295 @default.
- W2117318574 hasRelatedWork W1979809432 @default.
- W2117318574 hasRelatedWork W2014345428 @default.
- W2117318574 hasRelatedWork W2030898703 @default.
- W2117318574 hasRelatedWork W2104046483 @default.
- W2117318574 hasRelatedWork W2140121194 @default.
- W2117318574 hasRelatedWork W2150001221 @default.
- W2117318574 hasRelatedWork W2158169391 @default.
- W2117318574 hasRelatedWork W2162871885 @default.
- W2117318574 hasRelatedWork W2166659534 @default.
- W2117318574 hasRelatedWork W2341776112 @default.
- W2117318574 hasRelatedWork W2962826786 @default.
- W2117318574 hasRelatedWork W3011013680 @default.
- W2117318574 hasRelatedWork W3016614324 @default.
- W2117318574 hasRelatedWork W3043541165 @default.
- W2117318574 hasRelatedWork W379956812 @default.
- W2117318574 hasRelatedWork W944579169 @default.
- W2117318574 hasRelatedWork W2008879989 @default.
- W2117318574 hasRelatedWork W2957208190 @default.
- W2117318574 hasRelatedWork W3092815761 @default.
- W2117318574 isParatext "false" @default.
- W2117318574 isRetracted "false" @default.
- W2117318574 magId "2117318574" @default.
- W2117318574 workType "article" @default.