Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224927243> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4224927243 abstract "Speaker Change Detection (SCD) is a task of determining the time boundaries between speech segments of different speakers. SCD system can be applied to many tasks, such as speaker diarization, speaker tracking, and transcribing audio with multiple speakers. Recent advancements in deep learning lead to approaches that can directly detect the speaker change points from audio data at the frame-level based on neural network models. These approaches may be further improved by utilizing speaker information in the training data, and utilizing content information extracted in an unsupervised manner. This work proposes a novel framework for the SCD task, which utilizes a multitask learning architecture to leverage speaker information during the training stage, and adds the content information extracted from an unsupervised speech decomposition model to help detect the speaker change points. Experiment results show that the architecture of multitask learning with speaker information can improve the performance of SCD, and adding content information extracted from unsupervised speech decomposition model can further improve the performance. To the best of our knowledge, this work outperforms the state-of-the-art SCD results [1] on the AMI dataset." @default.
- W4224927243 created "2022-04-28" @default.
- W4224927243 creator A5019458385 @default.
- W4224927243 creator A5023737302 @default.
- W4224927243 creator A5025119324 @default.
- W4224927243 creator A5037109470 @default.
- W4224927243 creator A5069022903 @default.
- W4224927243 creator A5088623594 @default.
- W4224927243 creator A5089051100 @default.
- W4224927243 date "2022-05-23" @default.
- W4224927243 modified "2023-10-14" @default.
- W4224927243 title "A Multitask Learning Framework for Speaker Change Detection with Content Information from Unsupervised Speech Decomposition" @default.
- W4224927243 cites W1597208282 @default.
- W4224927243 cites W2052269122 @default.
- W4224927243 cites W2151299225 @default.
- W4224927243 cites W2159937480 @default.
- W4224927243 cites W2166980079 @default.
- W4224927243 cites W2405802804 @default.
- W4224927243 cites W2511082734 @default.
- W4224927243 cites W2618760106 @default.
- W4224927243 cites W2673722796 @default.
- W4224927243 cites W2690712642 @default.
- W4224927243 cites W2746241180 @default.
- W4224927243 cites W2746710273 @default.
- W4224927243 cites W2936794852 @default.
- W4224927243 cites W2963702081 @default.
- W4224927243 cites W2964052309 @default.
- W4224927243 cites W3015678936 @default.
- W4224927243 cites W3015783745 @default.
- W4224927243 cites W3099206234 @default.
- W4224927243 cites W3137585377 @default.
- W4224927243 doi "https://doi.org/10.1109/icassp43922.2022.9746116" @default.
- W4224927243 hasPublicationYear "2022" @default.
- W4224927243 type Work @default.
- W4224927243 citedByCount "1" @default.
- W4224927243 countsByYear W42249272432023 @default.
- W4224927243 crossrefType "proceedings-article" @default.
- W4224927243 hasAuthorship W4224927243A5019458385 @default.
- W4224927243 hasAuthorship W4224927243A5023737302 @default.
- W4224927243 hasAuthorship W4224927243A5025119324 @default.
- W4224927243 hasAuthorship W4224927243A5037109470 @default.
- W4224927243 hasAuthorship W4224927243A5069022903 @default.
- W4224927243 hasAuthorship W4224927243A5088623594 @default.
- W4224927243 hasAuthorship W4224927243A5089051100 @default.
- W4224927243 hasConcept C108583219 @default.
- W4224927243 hasConcept C133892786 @default.
- W4224927243 hasConcept C149838564 @default.
- W4224927243 hasConcept C153083717 @default.
- W4224927243 hasConcept C154945302 @default.
- W4224927243 hasConcept C162324750 @default.
- W4224927243 hasConcept C175154964 @default.
- W4224927243 hasConcept C187736073 @default.
- W4224927243 hasConcept C204201278 @default.
- W4224927243 hasConcept C2780451532 @default.
- W4224927243 hasConcept C28006648 @default.
- W4224927243 hasConcept C28490314 @default.
- W4224927243 hasConcept C41008148 @default.
- W4224927243 hasConcept C61328038 @default.
- W4224927243 hasConcept C8038995 @default.
- W4224927243 hasConceptScore W4224927243C108583219 @default.
- W4224927243 hasConceptScore W4224927243C133892786 @default.
- W4224927243 hasConceptScore W4224927243C149838564 @default.
- W4224927243 hasConceptScore W4224927243C153083717 @default.
- W4224927243 hasConceptScore W4224927243C154945302 @default.
- W4224927243 hasConceptScore W4224927243C162324750 @default.
- W4224927243 hasConceptScore W4224927243C175154964 @default.
- W4224927243 hasConceptScore W4224927243C187736073 @default.
- W4224927243 hasConceptScore W4224927243C204201278 @default.
- W4224927243 hasConceptScore W4224927243C2780451532 @default.
- W4224927243 hasConceptScore W4224927243C28006648 @default.
- W4224927243 hasConceptScore W4224927243C28490314 @default.
- W4224927243 hasConceptScore W4224927243C41008148 @default.
- W4224927243 hasConceptScore W4224927243C61328038 @default.
- W4224927243 hasConceptScore W4224927243C8038995 @default.
- W4224927243 hasLocation W42249272431 @default.
- W4224927243 hasOpenAccess W4224927243 @default.
- W4224927243 hasPrimaryLocation W42249272431 @default.
- W4224927243 hasRelatedWork W184144068 @default.
- W4224927243 hasRelatedWork W2020970176 @default.
- W4224927243 hasRelatedWork W2059891707 @default.
- W4224927243 hasRelatedWork W2111874347 @default.
- W4224927243 hasRelatedWork W2122924390 @default.
- W4224927243 hasRelatedWork W3003903817 @default.
- W4224927243 hasRelatedWork W3087422378 @default.
- W4224927243 hasRelatedWork W4224927243 @default.
- W4224927243 hasRelatedWork W4307478193 @default.
- W4224927243 hasRelatedWork W2733679854 @default.
- W4224927243 isParatext "false" @default.
- W4224927243 isRetracted "false" @default.
- W4224927243 workType "article" @default.