Matches in SemOpenAlex for { <https://semopenalex.org/work/W3007376164> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3007376164 abstract "Despite the significant progress in end-to-end (E2E) automatic speech recognition (ASR), E2E ASR for low resourced code-switching (CS) speech has not been well studied. In this work, we describe an E2E ASR pipeline for the recognition of CS speech in which a low-resourced language is mixed with a high resourced language. Low-resourcedness in acoustic data hinders the performance of E2E ASR systems more severely than the conventional ASR systems. To mitigate this problem in the transcription of archives with code-switching Frisian-Dutch speech, we integrate a designated decoding scheme and perform rescoring with neural network-based language models to enable better utilization of the available textual resources. We first incorporate a multi-graph decoding approach which creates parallel search spaces for each monolingual and mixed recognition tasks to maximize the utilization of the textual resources from each language. Further, language model rescoring is performed using a recurrent neural network pre-trained with cross-lingual embedding and further adapted with the limited amount of in-domain CS text. The ASR experiments demonstrate the effectiveness of the described techniques in improving the recognition performance of an E2E CS ASR system in a low-resourced scenario." @default.
- W3007376164 created "2020-03-06" @default.
- W3007376164 creator A5004568334 @default.
- W3007376164 creator A5031656256 @default.
- W3007376164 creator A5032690182 @default.
- W3007376164 creator A5056020864 @default.
- W3007376164 creator A5060201191 @default.
- W3007376164 date "2019-12-01" @default.
- W3007376164 modified "2023-10-12" @default.
- W3007376164 title "End-to-End Code-Switching ASR for Low-Resourced Language Pairs" @default.
- W3007376164 cites W1582482241 @default.
- W3007376164 cites W2046932483 @default.
- W3007376164 cites W2056478562 @default.
- W3007376164 cites W2127141656 @default.
- W3007376164 cites W2157331557 @default.
- W3007376164 cites W2514741789 @default.
- W3007376164 cites W2766219058 @default.
- W3007376164 cites W2883989418 @default.
- W3007376164 cites W2884515606 @default.
- W3007376164 cites W2886820613 @default.
- W3007376164 cites W2891616026 @default.
- W3007376164 cites W2939069254 @default.
- W3007376164 cites W2939408446 @default.
- W3007376164 cites W2939757332 @default.
- W3007376164 cites W2962704885 @default.
- W3007376164 cites W2963827914 @default.
- W3007376164 cites W2963970535 @default.
- W3007376164 cites W2972312617 @default.
- W3007376164 doi "https://doi.org/10.1109/asru46091.2019.9004035" @default.
- W3007376164 hasPublicationYear "2019" @default.
- W3007376164 type Work @default.
- W3007376164 sameAs 3007376164 @default.
- W3007376164 citedByCount "14" @default.
- W3007376164 countsByYear W30073761642020 @default.
- W3007376164 countsByYear W30073761642021 @default.
- W3007376164 countsByYear W30073761642022 @default.
- W3007376164 crossrefType "proceedings-article" @default.
- W3007376164 hasAuthorship W3007376164A5004568334 @default.
- W3007376164 hasAuthorship W3007376164A5031656256 @default.
- W3007376164 hasAuthorship W3007376164A5032690182 @default.
- W3007376164 hasAuthorship W3007376164A5056020864 @default.
- W3007376164 hasAuthorship W3007376164A5060201191 @default.
- W3007376164 hasBestOaLocation W30073761642 @default.
- W3007376164 hasConcept C137293760 @default.
- W3007376164 hasConcept C138885662 @default.
- W3007376164 hasConcept C154945302 @default.
- W3007376164 hasConcept C18552078 @default.
- W3007376164 hasConcept C199360897 @default.
- W3007376164 hasConcept C204321447 @default.
- W3007376164 hasConcept C28490314 @default.
- W3007376164 hasConcept C41008148 @default.
- W3007376164 hasConcept C41608201 @default.
- W3007376164 hasConcept C41895202 @default.
- W3007376164 hasConcept C43521106 @default.
- W3007376164 hasConcept C50644808 @default.
- W3007376164 hasConcept C57273362 @default.
- W3007376164 hasConcept C74296488 @default.
- W3007376164 hasConcept C76155785 @default.
- W3007376164 hasConceptScore W3007376164C137293760 @default.
- W3007376164 hasConceptScore W3007376164C138885662 @default.
- W3007376164 hasConceptScore W3007376164C154945302 @default.
- W3007376164 hasConceptScore W3007376164C18552078 @default.
- W3007376164 hasConceptScore W3007376164C199360897 @default.
- W3007376164 hasConceptScore W3007376164C204321447 @default.
- W3007376164 hasConceptScore W3007376164C28490314 @default.
- W3007376164 hasConceptScore W3007376164C41008148 @default.
- W3007376164 hasConceptScore W3007376164C41608201 @default.
- W3007376164 hasConceptScore W3007376164C41895202 @default.
- W3007376164 hasConceptScore W3007376164C43521106 @default.
- W3007376164 hasConceptScore W3007376164C50644808 @default.
- W3007376164 hasConceptScore W3007376164C57273362 @default.
- W3007376164 hasConceptScore W3007376164C74296488 @default.
- W3007376164 hasConceptScore W3007376164C76155785 @default.
- W3007376164 hasLocation W30073761641 @default.
- W3007376164 hasLocation W30073761642 @default.
- W3007376164 hasOpenAccess W3007376164 @default.
- W3007376164 hasPrimaryLocation W30073761641 @default.
- W3007376164 hasRelatedWork W2020540721 @default.
- W3007376164 hasRelatedWork W2359001871 @default.
- W3007376164 hasRelatedWork W2592356860 @default.
- W3007376164 hasRelatedWork W2608712415 @default.
- W3007376164 hasRelatedWork W2739427748 @default.
- W3007376164 hasRelatedWork W2936848022 @default.
- W3007376164 hasRelatedWork W2997712488 @default.
- W3007376164 hasRelatedWork W3015923889 @default.
- W3007376164 hasRelatedWork W4206374977 @default.
- W3007376164 hasRelatedWork W62743518 @default.
- W3007376164 isParatext "false" @default.
- W3007376164 isRetracted "false" @default.
- W3007376164 magId "3007376164" @default.
- W3007376164 workType "article" @default.