Matches in SemOpenAlex for { <https://semopenalex.org/work/W2798949062> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2798949062 abstract "Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have required additional training data such as isolated source signals or senone alignments for effective learning. In this paper, we propose a new sequence-to-sequence framework to directly decode multiple label sequences from a single speech sequence by unifying source separation and speech recognition functions in an end-to-end manner. We further propose a new objective function to improve the contrast between the hidden vectors to avoid generating similar hypotheses. Experimental results show that the model is directly able to learn a mapping from a speech mixture to multiple label sequences, achieving 83.1 % relative improvement compared to a model trained without the proposed objective. Interestingly, the results are comparable to those produced by previous end-to-end works featuring explicit separation and recognition modules." @default.
- W2798949062 created "2018-05-07" @default.
- W2798949062 creator A5001291873 @default.
- W2798949062 creator A5076453358 @default.
- W2798949062 creator A5077186384 @default.
- W2798949062 creator A5082524152 @default.
- W2798949062 creator A5087554069 @default.
- W2798949062 date "2018-05-15" @default.
- W2798949062 modified "2023-09-23" @default.
- W2798949062 title "A Purely End-to-end System for Multi-speaker Speech Recognition" @default.
- W2798949062 hasPublicationYear "2018" @default.
- W2798949062 type Work @default.
- W2798949062 sameAs 2798949062 @default.
- W2798949062 citedByCount "1" @default.
- W2798949062 countsByYear W27989490622020 @default.
- W2798949062 crossrefType "posted-content" @default.
- W2798949062 hasAuthorship W2798949062A5001291873 @default.
- W2798949062 hasAuthorship W2798949062A5076453358 @default.
- W2798949062 hasAuthorship W2798949062A5077186384 @default.
- W2798949062 hasAuthorship W2798949062A5082524152 @default.
- W2798949062 hasAuthorship W2798949062A5087554069 @default.
- W2798949062 hasConcept C127413603 @default.
- W2798949062 hasConcept C133892786 @default.
- W2798949062 hasConcept C14036430 @default.
- W2798949062 hasConcept C153180895 @default.
- W2798949062 hasConcept C154945302 @default.
- W2798949062 hasConcept C201995342 @default.
- W2798949062 hasConcept C2778112365 @default.
- W2798949062 hasConcept C2780451532 @default.
- W2798949062 hasConcept C28490314 @default.
- W2798949062 hasConcept C35639132 @default.
- W2798949062 hasConcept C41008148 @default.
- W2798949062 hasConcept C54355233 @default.
- W2798949062 hasConcept C74296488 @default.
- W2798949062 hasConcept C78458016 @default.
- W2798949062 hasConcept C86803240 @default.
- W2798949062 hasConceptScore W2798949062C127413603 @default.
- W2798949062 hasConceptScore W2798949062C133892786 @default.
- W2798949062 hasConceptScore W2798949062C14036430 @default.
- W2798949062 hasConceptScore W2798949062C153180895 @default.
- W2798949062 hasConceptScore W2798949062C154945302 @default.
- W2798949062 hasConceptScore W2798949062C201995342 @default.
- W2798949062 hasConceptScore W2798949062C2778112365 @default.
- W2798949062 hasConceptScore W2798949062C2780451532 @default.
- W2798949062 hasConceptScore W2798949062C28490314 @default.
- W2798949062 hasConceptScore W2798949062C35639132 @default.
- W2798949062 hasConceptScore W2798949062C41008148 @default.
- W2798949062 hasConceptScore W2798949062C54355233 @default.
- W2798949062 hasConceptScore W2798949062C74296488 @default.
- W2798949062 hasConceptScore W2798949062C78458016 @default.
- W2798949062 hasConceptScore W2798949062C86803240 @default.
- W2798949062 hasOpenAccess W2798949062 @default.
- W2798949062 hasRelatedWork W142758689 @default.
- W2798949062 hasRelatedWork W1494243555 @default.
- W2798949062 hasRelatedWork W2554781714 @default.
- W2798949062 hasRelatedWork W2737108017 @default.
- W2798949062 hasRelatedWork W2799930831 @default.
- W2798949062 hasRelatedWork W2900312178 @default.
- W2798949062 hasRelatedWork W2933148111 @default.
- W2798949062 hasRelatedWork W2949526695 @default.
- W2798949062 hasRelatedWork W2949788262 @default.
- W2798949062 hasRelatedWork W2963477857 @default.
- W2798949062 hasRelatedWork W2991480510 @default.
- W2798949062 hasRelatedWork W3008181812 @default.
- W2798949062 hasRelatedWork W3014973941 @default.
- W2798949062 hasRelatedWork W3026709049 @default.
- W2798949062 hasRelatedWork W3037383957 @default.
- W2798949062 hasRelatedWork W3046954891 @default.
- W2798949062 hasRelatedWork W3096665264 @default.
- W2798949062 hasRelatedWork W3132220150 @default.
- W2798949062 hasRelatedWork W3133801870 @default.
- W2798949062 hasRelatedWork W3145709712 @default.
- W2798949062 isParatext "false" @default.
- W2798949062 isRetracted "false" @default.
- W2798949062 magId "2798949062" @default.
- W2798949062 workType "article" @default.