Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224291204> ?p ?o ?g. }
Showing items 1 to 46 of
46
with 100 items per page.
- W4224291204 abstract "End-to-end speaker diarization approaches have shown exceptional performance over the traditional modular approaches. To further improve the performance of the end-to-end speaker diarization for real speech recordings, recently works have been proposed which integrate unsupervised clustering algorithms with the end-to-end neural diarization models. However, these methods have a number of drawbacks: 1) The unsupervised clustering algorithms cannot leverage the supervision from the available datasets; 2) The K-means-based unsupervised algorithms that are explored often suffer from the constraint violation problem; 3) There is unavoidable mismatch between the supervised training and the unsupervised inference. In this paper, a robust generic neural clustering approach is proposed that can be integrated with any chunk-level predictor to accomplish a fully supervised end-to-end speaker diarization model. Also, by leveraging the sequence modelling ability of a recurrent neural network, the proposed neural clustering approach can dynamically estimate the number of speakers during inference. Experimental show that when integrating an attractor-based chunk-level predictor, the proposed neural clustering approach can yield better Diarization Error Rate (DER) than the constrained K-means-based clustering approaches under the mismatched conditions." @default.
- W4224291204 created "2022-04-26" @default.
- W4224291204 creator A5041026723 @default.
- W4224291204 creator A5079594267 @default.
- W4224291204 date "2022-09-18" @default.
- W4224291204 modified "2023-10-18" @default.
- W4224291204 title "Robust End-to-end Speaker Diarization with Generic Neural Clustering" @default.
- W4224291204 doi "https://doi.org/10.21437/interspeech.2022-10404" @default.
- W4224291204 hasPublicationYear "2022" @default.
- W4224291204 type Work @default.
- W4224291204 citedByCount "0" @default.
- W4224291204 crossrefType "proceedings-article" @default.
- W4224291204 hasAuthorship W4224291204A5041026723 @default.
- W4224291204 hasAuthorship W4224291204A5079594267 @default.
- W4224291204 hasBestOaLocation W42242912042 @default.
- W4224291204 hasConcept C133892786 @default.
- W4224291204 hasConcept C149838564 @default.
- W4224291204 hasConcept C154945302 @default.
- W4224291204 hasConcept C28490314 @default.
- W4224291204 hasConcept C41008148 @default.
- W4224291204 hasConcept C73555534 @default.
- W4224291204 hasConcept C74296488 @default.
- W4224291204 hasConceptScore W4224291204C133892786 @default.
- W4224291204 hasConceptScore W4224291204C149838564 @default.
- W4224291204 hasConceptScore W4224291204C154945302 @default.
- W4224291204 hasConceptScore W4224291204C28490314 @default.
- W4224291204 hasConceptScore W4224291204C41008148 @default.
- W4224291204 hasConceptScore W4224291204C73555534 @default.
- W4224291204 hasConceptScore W4224291204C74296488 @default.
- W4224291204 hasLocation W42242912041 @default.
- W4224291204 hasLocation W42242912042 @default.
- W4224291204 hasOpenAccess W4224291204 @default.
- W4224291204 hasPrimaryLocation W42242912041 @default.
- W4224291204 hasRelatedWork W1492025301 @default.
- W4224291204 hasRelatedWork W2171511892 @default.
- W4224291204 hasRelatedWork W2312116756 @default.
- W4224291204 hasRelatedWork W2890244912 @default.
- W4224291204 hasRelatedWork W3015923889 @default.
- W4224291204 hasRelatedWork W3025798172 @default.
- W4224291204 hasRelatedWork W4225792560 @default.
- W4224291204 hasRelatedWork W4287236246 @default.
- W4224291204 hasRelatedWork W4308164622 @default.
- W4224291204 hasRelatedWork W4319663602 @default.
- W4224291204 isParatext "false" @default.
- W4224291204 isRetracted "false" @default.
- W4224291204 workType "article" @default.