Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319862458> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4319862458 abstract "For Mandarin end-to-end (E2E) automatic speech recognition (ASR) tasks, compared to character-based modeling units, pronunciation-based modeling units could improve the sharing of modeling units in model training but meet homophone problems. In this study, we propose to use a novel pronunciation-aware unique character encoding for building E2E RNN-T-based Mandarin ASR systems. The proposed encoding is a combination of pronunciation-base syllable and character index (CI). By introducing the CI, the RNN-T model can overcome the homophone problem while utilizing the pronunciation information for extracting modeling units. With the proposed encoding, the model outputs can be converted into the final recognition result through a one-to-one mapping. We conducted experiments on Aishell and MagicData datasets, and the experimental results showed the effectiveness of the proposed method." @default.
- W4319862458 created "2023-02-11" @default.
- W4319862458 creator A5013069605 @default.
- W4319862458 creator A5034792613 @default.
- W4319862458 creator A5069927701 @default.
- W4319862458 date "2023-01-09" @default.
- W4319862458 modified "2023-09-27" @default.
- W4319862458 title "Pronunciation-Aware Unique Character Encoding for RNN Transducer-Based Mandarin Speech Recognition" @default.
- W4319862458 cites W2327501763 @default.
- W4319862458 cites W2936774411 @default.
- W4319862458 cites W2962784628 @default.
- W4319862458 cites W2963070863 @default.
- W4319862458 cites W2963226322 @default.
- W4319862458 cites W2963242190 @default.
- W4319862458 cites W2963250244 @default.
- W4319862458 cites W2963939538 @default.
- W4319862458 cites W2972686346 @default.
- W4319862458 cites W3015194534 @default.
- W4319862458 cites W3094667432 @default.
- W4319862458 cites W3097777922 @default.
- W4319862458 cites W3144345593 @default.
- W4319862458 cites W3151526698 @default.
- W4319862458 cites W3162639446 @default.
- W4319862458 cites W3163702140 @default.
- W4319862458 cites W3211278025 @default.
- W4319862458 cites W4210811812 @default.
- W4319862458 doi "https://doi.org/10.1109/slt54892.2023.10022528" @default.
- W4319862458 hasPublicationYear "2023" @default.
- W4319862458 type Work @default.
- W4319862458 citedByCount "0" @default.
- W4319862458 crossrefType "proceedings-article" @default.
- W4319862458 hasAuthorship W4319862458A5013069605 @default.
- W4319862458 hasAuthorship W4319862458A5034792613 @default.
- W4319862458 hasAuthorship W4319862458A5069927701 @default.
- W4319862458 hasConcept C109089402 @default.
- W4319862458 hasConcept C125411270 @default.
- W4319862458 hasConcept C137293760 @default.
- W4319862458 hasConcept C138885662 @default.
- W4319862458 hasConcept C138954614 @default.
- W4319862458 hasConcept C147168706 @default.
- W4319862458 hasConcept C154945302 @default.
- W4319862458 hasConcept C160253069 @default.
- W4319862458 hasConcept C204321447 @default.
- W4319862458 hasConcept C2524010 @default.
- W4319862458 hasConcept C2780844864 @default.
- W4319862458 hasConcept C2780861071 @default.
- W4319862458 hasConcept C28490314 @default.
- W4319862458 hasConcept C33923547 @default.
- W4319862458 hasConcept C41008148 @default.
- W4319862458 hasConcept C41895202 @default.
- W4319862458 hasConcept C50644808 @default.
- W4319862458 hasConceptScore W4319862458C109089402 @default.
- W4319862458 hasConceptScore W4319862458C125411270 @default.
- W4319862458 hasConceptScore W4319862458C137293760 @default.
- W4319862458 hasConceptScore W4319862458C138885662 @default.
- W4319862458 hasConceptScore W4319862458C138954614 @default.
- W4319862458 hasConceptScore W4319862458C147168706 @default.
- W4319862458 hasConceptScore W4319862458C154945302 @default.
- W4319862458 hasConceptScore W4319862458C160253069 @default.
- W4319862458 hasConceptScore W4319862458C204321447 @default.
- W4319862458 hasConceptScore W4319862458C2524010 @default.
- W4319862458 hasConceptScore W4319862458C2780844864 @default.
- W4319862458 hasConceptScore W4319862458C2780861071 @default.
- W4319862458 hasConceptScore W4319862458C28490314 @default.
- W4319862458 hasConceptScore W4319862458C33923547 @default.
- W4319862458 hasConceptScore W4319862458C41008148 @default.
- W4319862458 hasConceptScore W4319862458C41895202 @default.
- W4319862458 hasConceptScore W4319862458C50644808 @default.
- W4319862458 hasLocation W43198624581 @default.
- W4319862458 hasOpenAccess W4319862458 @default.
- W4319862458 hasPrimaryLocation W43198624581 @default.
- W4319862458 hasRelatedWork W1491795195 @default.
- W4319862458 hasRelatedWork W2110864561 @default.
- W4319862458 hasRelatedWork W2125271142 @default.
- W4319862458 hasRelatedWork W2364136279 @default.
- W4319862458 hasRelatedWork W2380384931 @default.
- W4319862458 hasRelatedWork W2580589825 @default.
- W4319862458 hasRelatedWork W3151526698 @default.
- W4319862458 hasRelatedWork W4289445535 @default.
- W4319862458 hasRelatedWork W4319862458 @default.
- W4319862458 hasRelatedWork W3105760203 @default.
- W4319862458 isParatext "false" @default.
- W4319862458 isRetracted "false" @default.
- W4319862458 workType "article" @default.