Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963574857> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2963574857 abstract "Recently, end-to-end models have become a popular approach as an alternative to traditional hybrid models in automatic speech recognition (ASR). The multi-speaker speech separation and recognition task is a central task in cocktail party problem. In this paper, we present a state-of-the-art monaural multi-speaker end-to-end automatic speech recognition model. In contrast to previous studies on the monaural multi-speaker speech recognition, this end-to-end framework is trained to recognize multiple label sequences completely from scratch. The system only requires the speech mixture and corresponding label sequences, without needing any indeterminate supervisions obtained from non-mixture speech or corresponding labels/alignments. Moreover, we exploited using the individual attention module for each separated speaker and the scheduled sampling to further improve the performance. Finally, we evaluate the proposed model on the 2-speaker mixed speech generated from the WSJ corpus and the wsj0-2mix dataset, which is a speech separation and recognition benchmark. The experiments demonstrate that the proposed methods can improve the performance of the end-to-end model in separating the overlapping speech and recognizing the separated streams. From the results, the proposed model leads to ~ 10.0% relative performance gains in terms of CER and WER respectively." @default.
- W2963574857 created "2019-07-30" @default.
- W2963574857 creator A5001291873 @default.
- W2963574857 creator A5015824704 @default.
- W2963574857 creator A5043098653 @default.
- W2963574857 creator A5050058892 @default.
- W2963574857 date "2019-05-01" @default.
- W2963574857 modified "2023-09-23" @default.
- W2963574857 title "End-to-end Monaural Multi-speaker ASR System without Pretraining" @default.
- W2963574857 cites W2060822897 @default.
- W2963574857 cites W2112739286 @default.
- W2963574857 cites W2160815625 @default.
- W2963574857 cites W2221409856 @default.
- W2963574857 cites W2327501763 @default.
- W2963574857 cites W2460742184 @default.
- W2963574857 cites W2519224033 @default.
- W2963574857 cites W2526425061 @default.
- W2963574857 cites W2734774145 @default.
- W2963574857 cites W2739883972 @default.
- W2963574857 cites W2766219058 @default.
- W2963574857 cites W2794289187 @default.
- W2963574857 cites W2799800213 @default.
- W2963574857 cites W2884797218 @default.
- W2963574857 cites W2889144942 @default.
- W2963574857 cites W2890244912 @default.
- W2963574857 cites W2892025684 @default.
- W2963574857 cites W2962715207 @default.
- W2963574857 cites W2962780374 @default.
- W2963574857 cites W2963211739 @default.
- W2963574857 cites W2963477857 @default.
- W2963574857 cites W2963773971 @default.
- W2963574857 cites W2963843276 @default.
- W2963574857 cites W3099832538 @default.
- W2963574857 cites W2890505457 @default.
- W2963574857 doi "https://doi.org/10.1109/icassp.2019.8682822" @default.
- W2963574857 hasPublicationYear "2019" @default.
- W2963574857 type Work @default.
- W2963574857 sameAs 2963574857 @default.
- W2963574857 citedByCount "51" @default.
- W2963574857 countsByYear W29635748572019 @default.
- W2963574857 countsByYear W29635748572020 @default.
- W2963574857 countsByYear W29635748572021 @default.
- W2963574857 countsByYear W29635748572022 @default.
- W2963574857 countsByYear W29635748572023 @default.
- W2963574857 crossrefType "proceedings-article" @default.
- W2963574857 hasAuthorship W2963574857A5001291873 @default.
- W2963574857 hasAuthorship W2963574857A5015824704 @default.
- W2963574857 hasAuthorship W2963574857A5043098653 @default.
- W2963574857 hasAuthorship W2963574857A5050058892 @default.
- W2963574857 hasBestOaLocation W29635748572 @default.
- W2963574857 hasConcept C102894143 @default.
- W2963574857 hasConcept C28490314 @default.
- W2963574857 hasConcept C41008148 @default.
- W2963574857 hasConceptScore W2963574857C102894143 @default.
- W2963574857 hasConceptScore W2963574857C28490314 @default.
- W2963574857 hasConceptScore W2963574857C41008148 @default.
- W2963574857 hasLocation W29635748571 @default.
- W2963574857 hasLocation W29635748572 @default.
- W2963574857 hasOpenAccess W2963574857 @default.
- W2963574857 hasPrimaryLocation W29635748571 @default.
- W2963574857 hasRelatedWork W2043642831 @default.
- W2963574857 hasRelatedWork W2368779261 @default.
- W2963574857 hasRelatedWork W2401567014 @default.
- W2963574857 hasRelatedWork W2794438528 @default.
- W2963574857 hasRelatedWork W2889698889 @default.
- W2963574857 hasRelatedWork W2893763841 @default.
- W2963574857 hasRelatedWork W2900114706 @default.
- W2963574857 hasRelatedWork W2921683566 @default.
- W2963574857 hasRelatedWork W2980451698 @default.
- W2963574857 hasRelatedWork W3016163030 @default.
- W2963574857 isParatext "false" @default.
- W2963574857 isRetracted "false" @default.
- W2963574857 magId "2963574857" @default.
- W2963574857 workType "article" @default.