Matches in SemOpenAlex for { <https://semopenalex.org/work/W2973127116> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2973127116 abstract "Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate systems, namely, an automatic speech recognition (ASR) system and a speaker diarization (SD) system. The two systems are trained independently with different objective functions. Often the SD systems operate directly on the acoustics and are not constrained to respect word boundaries and this deficiency is overcome in an ad hoc manner. Motivated by recent advances in sequence to sequence learning, we propose a novel approach to tackle the two tasks by a joint ASR and SD system using a recurrent neural network transducer. Our approach utilizes both linguistic and acoustic cues to infer speaker roles, as opposed to typical SD systems, which only use acoustic cues. We evaluated the performance of our approach on a large corpus of medical conversations between physicians and patients. Compared to a competitive conventional baseline, our approach improves word-level diarization error rate from 15.8% to 2.2%." @default.
- W2973127116 created "2019-09-19" @default.
- W2973127116 creator A5010878109 @default.
- W2973127116 creator A5025419994 @default.
- W2973127116 creator A5072051996 @default.
- W2973127116 date "2019-09-15" @default.
- W2973127116 modified "2023-09-25" @default.
- W2973127116 title "Joint Speech Recognition and Speaker Diarization via Sequence Transduction" @default.
- W2973127116 doi "https://doi.org/10.21437/interspeech.2019-1943" @default.
- W2973127116 hasPublicationYear "2019" @default.
- W2973127116 type Work @default.
- W2973127116 sameAs 2973127116 @default.
- W2973127116 citedByCount "61" @default.
- W2973127116 countsByYear W29731271162019 @default.
- W2973127116 countsByYear W29731271162020 @default.
- W2973127116 countsByYear W29731271162021 @default.
- W2973127116 countsByYear W29731271162022 @default.
- W2973127116 countsByYear W29731271162023 @default.
- W2973127116 crossrefType "proceedings-article" @default.
- W2973127116 hasAuthorship W2973127116A5010878109 @default.
- W2973127116 hasAuthorship W2973127116A5025419994 @default.
- W2973127116 hasAuthorship W2973127116A5072051996 @default.
- W2973127116 hasBestOaLocation W29731271162 @default.
- W2973127116 hasConcept C127413603 @default.
- W2973127116 hasConcept C133892786 @default.
- W2973127116 hasConcept C149838564 @default.
- W2973127116 hasConcept C15152581 @default.
- W2973127116 hasConcept C154945302 @default.
- W2973127116 hasConcept C170154142 @default.
- W2973127116 hasConcept C18555067 @default.
- W2973127116 hasConcept C2778112365 @default.
- W2973127116 hasConcept C28490314 @default.
- W2973127116 hasConcept C41008148 @default.
- W2973127116 hasConcept C54355233 @default.
- W2973127116 hasConcept C55493867 @default.
- W2973127116 hasConcept C86803240 @default.
- W2973127116 hasConceptScore W2973127116C127413603 @default.
- W2973127116 hasConceptScore W2973127116C133892786 @default.
- W2973127116 hasConceptScore W2973127116C149838564 @default.
- W2973127116 hasConceptScore W2973127116C15152581 @default.
- W2973127116 hasConceptScore W2973127116C154945302 @default.
- W2973127116 hasConceptScore W2973127116C170154142 @default.
- W2973127116 hasConceptScore W2973127116C18555067 @default.
- W2973127116 hasConceptScore W2973127116C2778112365 @default.
- W2973127116 hasConceptScore W2973127116C28490314 @default.
- W2973127116 hasConceptScore W2973127116C41008148 @default.
- W2973127116 hasConceptScore W2973127116C54355233 @default.
- W2973127116 hasConceptScore W2973127116C55493867 @default.
- W2973127116 hasConceptScore W2973127116C86803240 @default.
- W2973127116 hasLocation W29731271161 @default.
- W2973127116 hasLocation W29731271162 @default.
- W2973127116 hasOpenAccess W2973127116 @default.
- W2973127116 hasPrimaryLocation W29731271161 @default.
- W2973127116 hasRelatedWork W1497807607 @default.
- W2973127116 hasRelatedWork W1509309911 @default.
- W2973127116 hasRelatedWork W1521049138 @default.
- W2973127116 hasRelatedWork W1813780412 @default.
- W2973127116 hasRelatedWork W2128773298 @default.
- W2973127116 hasRelatedWork W2144208207 @default.
- W2973127116 hasRelatedWork W2162158162 @default.
- W2973127116 hasRelatedWork W2499802997 @default.
- W2973127116 hasRelatedWork W2566925314 @default.
- W2973127116 hasRelatedWork W2175373321 @default.
- W2973127116 isParatext "false" @default.
- W2973127116 isRetracted "false" @default.
- W2973127116 magId "2973127116" @default.
- W2973127116 workType "article" @default.