Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319663602> ?p ?o ?g. }
- W4319663602 endingPage "13917" @default.
- W4319663602 startingPage "13906" @default.
- W4319663602 abstract "Automatic speech recognition of a target speaker in the presence of interfering speakers remains a challenging issue. One approach to tackle this problem is target-speaker speech recognition, which conditions the recognition process on an embedding that characterizes the voice of the target speaker. This enables recognizing only the speech of the target speaker while ignoring interferences. In this work, we propose an end-to-end target-speaker speech recognition system based on a neural transducer architecture to allow streaming and on-device recognition. Moreover, a target-speaker speech recognition system should be able to detect when the target speaker is inactive and output nothing in such a case. We introduce training and decoding schemes to allow target-speaker activity detection within our proposed recognition system. We confirm experimentally that our proposed end-to-end system performs competitively to conventional cascade approaches of a target speech extraction module and a recognition module while reducing computation costs and allowing streaming decoding." @default.
- W4319663602 created "2023-02-10" @default.
- W4319663602 creator A5023868166 @default.
- W4319663602 creator A5049107389 @default.
- W4319663602 creator A5049917170 @default.
- W4319663602 creator A5070624983 @default.
- W4319663602 creator A5087290011 @default.
- W4319663602 date "2023-01-01" @default.
- W4319663602 modified "2023-09-30" @default.
- W4319663602 title "Streaming End-to-End Target-Speaker Automatic Speech Recognition and Activity Detection" @default.
- W4319663602 cites W2064675550 @default.
- W4319663602 cites W2160815625 @default.
- W4319663602 cites W2559809918 @default.
- W4319663602 cites W2884797218 @default.
- W4319663602 cites W2936774411 @default.
- W4319663602 cites W2951130829 @default.
- W4319663602 cites W2952218014 @default.
- W4319663602 cites W2962780374 @default.
- W4319663602 cites W2964084166 @default.
- W4319663602 cites W2972362771 @default.
- W4319663602 cites W2972474532 @default.
- W4319663602 cites W2973054998 @default.
- W4319663602 cites W3015190365 @default.
- W4319663602 cites W3015636705 @default.
- W4319663602 cites W3015927303 @default.
- W4319663602 cites W3094806148 @default.
- W4319663602 cites W3096090308 @default.
- W4319663602 cites W3096518646 @default.
- W4319663602 cites W3097777922 @default.
- W4319663602 cites W3105928222 @default.
- W4319663602 cites W3109079702 @default.
- W4319663602 cites W3161158930 @default.
- W4319663602 cites W3161354387 @default.
- W4319663602 cites W3161873870 @default.
- W4319663602 cites W3162444624 @default.
- W4319663602 cites W3162847598 @default.
- W4319663602 cites W3186652349 @default.
- W4319663602 cites W3198254488 @default.
- W4319663602 cites W3198442913 @default.
- W4319663602 cites W3198575250 @default.
- W4319663602 cites W3198667862 @default.
- W4319663602 cites W4210663600 @default.
- W4319663602 cites W4221153233 @default.
- W4319663602 cites W4224920108 @default.
- W4319663602 cites W4226098957 @default.
- W4319663602 cites W4226491018 @default.
- W4319663602 cites W4283074506 @default.
- W4319663602 cites W4296070363 @default.
- W4319663602 cites W4297841877 @default.
- W4319663602 doi "https://doi.org/10.1109/access.2023.3243690" @default.
- W4319663602 hasPublicationYear "2023" @default.
- W4319663602 type Work @default.
- W4319663602 citedByCount "0" @default.
- W4319663602 crossrefType "journal-article" @default.
- W4319663602 hasAuthorship W4319663602A5023868166 @default.
- W4319663602 hasAuthorship W4319663602A5049107389 @default.
- W4319663602 hasAuthorship W4319663602A5049917170 @default.
- W4319663602 hasAuthorship W4319663602A5070624983 @default.
- W4319663602 hasAuthorship W4319663602A5087290011 @default.
- W4319663602 hasBestOaLocation W43196636021 @default.
- W4319663602 hasConcept C133892786 @default.
- W4319663602 hasConcept C149838564 @default.
- W4319663602 hasConcept C153180895 @default.
- W4319663602 hasConcept C154945302 @default.
- W4319663602 hasConcept C204201278 @default.
- W4319663602 hasConcept C28490314 @default.
- W4319663602 hasConcept C41008148 @default.
- W4319663602 hasConcept C57273362 @default.
- W4319663602 hasConcept C61328038 @default.
- W4319663602 hasConcept C74296488 @default.
- W4319663602 hasConcept C76155785 @default.
- W4319663602 hasConceptScore W4319663602C133892786 @default.
- W4319663602 hasConceptScore W4319663602C149838564 @default.
- W4319663602 hasConceptScore W4319663602C153180895 @default.
- W4319663602 hasConceptScore W4319663602C154945302 @default.
- W4319663602 hasConceptScore W4319663602C204201278 @default.
- W4319663602 hasConceptScore W4319663602C28490314 @default.
- W4319663602 hasConceptScore W4319663602C41008148 @default.
- W4319663602 hasConceptScore W4319663602C57273362 @default.
- W4319663602 hasConceptScore W4319663602C61328038 @default.
- W4319663602 hasConceptScore W4319663602C74296488 @default.
- W4319663602 hasConceptScore W4319663602C76155785 @default.
- W4319663602 hasLocation W43196636021 @default.
- W4319663602 hasOpenAccess W4319663602 @default.
- W4319663602 hasPrimaryLocation W43196636021 @default.
- W4319663602 hasRelatedWork W2020970176 @default.
- W4319663602 hasRelatedWork W2059891707 @default.
- W4319663602 hasRelatedWork W2111874347 @default.
- W4319663602 hasRelatedWork W2122924390 @default.
- W4319663602 hasRelatedWork W2185667427 @default.
- W4319663602 hasRelatedWork W2573756443 @default.
- W4319663602 hasRelatedWork W3087422378 @default.
- W4319663602 hasRelatedWork W4382050168 @default.
- W4319663602 hasRelatedWork W2556771176 @default.
- W4319663602 hasRelatedWork W2733679854 @default.
- W4319663602 hasVolume "11" @default.
- W4319663602 isParatext "false" @default.
- W4319663602 isRetracted "false" @default.