Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288889606> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4288889606 abstract "This paper describes our speaker diarization system submitted to the Multi-channel Multi-party Meeting Transcription (M2MeT) challenge, where Mandarin meeting data were recorded in multi-channel format for diarization and automatic speech recognition (ASR) tasks. In these meeting scenarios, the uncertainty of the speaker number and the high ratio of overlapped speech present great challenges for diarization. Based on the assumption that there is valuable complementary information between acoustic features, spatial-related and speaker-related features, we propose a multi-level feature fusion mechanism based target-speaker voice activity detection (FFM-TS-VAD) system to improve the performance of the conventional TS-VAD system. Furthermore, we propose a data augmentation method during training to improve the system robustness when the angular difference between two speakers is relatively small. We provide comparisons for different sub-systems we used in M2MeT challenge. Our submission is a fusion of several sub-systems and ranks second in the diarization task." @default.
- W4288889606 created "2022-07-31" @default.
- W4288889606 creator A5011276883 @default.
- W4288889606 creator A5019458385 @default.
- W4288889606 creator A5021176244 @default.
- W4288889606 creator A5025119324 @default.
- W4288889606 creator A5031315906 @default.
- W4288889606 creator A5051324423 @default.
- W4288889606 creator A5062761975 @default.
- W4288889606 creator A5075183307 @default.
- W4288889606 creator A5077304193 @default.
- W4288889606 date "2022-02-04" @default.
- W4288889606 modified "2023-10-14" @default.
- W4288889606 title "The CUHK-TENCENT speaker diarization system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge" @default.
- W4288889606 doi "https://doi.org/10.48550/arxiv.2202.01986" @default.
- W4288889606 hasPublicationYear "2022" @default.
- W4288889606 type Work @default.
- W4288889606 citedByCount "0" @default.
- W4288889606 crossrefType "posted-content" @default.
- W4288889606 hasAuthorship W4288889606A5011276883 @default.
- W4288889606 hasAuthorship W4288889606A5019458385 @default.
- W4288889606 hasAuthorship W4288889606A5021176244 @default.
- W4288889606 hasAuthorship W4288889606A5025119324 @default.
- W4288889606 hasAuthorship W4288889606A5031315906 @default.
- W4288889606 hasAuthorship W4288889606A5051324423 @default.
- W4288889606 hasAuthorship W4288889606A5062761975 @default.
- W4288889606 hasAuthorship W4288889606A5075183307 @default.
- W4288889606 hasAuthorship W4288889606A5077304193 @default.
- W4288889606 hasBestOaLocation W42888896061 @default.
- W4288889606 hasConcept C104317684 @default.
- W4288889606 hasConcept C127162648 @default.
- W4288889606 hasConcept C133892786 @default.
- W4288889606 hasConcept C138885662 @default.
- W4288889606 hasConcept C149838564 @default.
- W4288889606 hasConcept C179926584 @default.
- W4288889606 hasConcept C185592680 @default.
- W4288889606 hasConcept C28490314 @default.
- W4288889606 hasConcept C41008148 @default.
- W4288889606 hasConcept C41895202 @default.
- W4288889606 hasConcept C55493867 @default.
- W4288889606 hasConcept C63479239 @default.
- W4288889606 hasConcept C76155785 @default.
- W4288889606 hasConceptScore W4288889606C104317684 @default.
- W4288889606 hasConceptScore W4288889606C127162648 @default.
- W4288889606 hasConceptScore W4288889606C133892786 @default.
- W4288889606 hasConceptScore W4288889606C138885662 @default.
- W4288889606 hasConceptScore W4288889606C149838564 @default.
- W4288889606 hasConceptScore W4288889606C179926584 @default.
- W4288889606 hasConceptScore W4288889606C185592680 @default.
- W4288889606 hasConceptScore W4288889606C28490314 @default.
- W4288889606 hasConceptScore W4288889606C41008148 @default.
- W4288889606 hasConceptScore W4288889606C41895202 @default.
- W4288889606 hasConceptScore W4288889606C55493867 @default.
- W4288889606 hasConceptScore W4288889606C63479239 @default.
- W4288889606 hasConceptScore W4288889606C76155785 @default.
- W4288889606 hasLocation W42888896061 @default.
- W4288889606 hasOpenAccess W4288889606 @default.
- W4288889606 hasPrimaryLocation W42888896061 @default.
- W4288889606 hasRelatedWork W11060696 @default.
- W4288889606 hasRelatedWork W11798771 @default.
- W4288889606 hasRelatedWork W13110487 @default.
- W4288889606 hasRelatedWork W1312587 @default.
- W4288889606 hasRelatedWork W14379828 @default.
- W4288889606 hasRelatedWork W14769199 @default.
- W4288889606 hasRelatedWork W34220 @default.
- W4288889606 hasRelatedWork W5064682 @default.
- W4288889606 hasRelatedWork W8493306 @default.
- W4288889606 hasRelatedWork W9143300 @default.
- W4288889606 isParatext "false" @default.
- W4288889606 isRetracted "false" @default.
- W4288889606 workType "article" @default.