Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319862462> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4319862462 abstract "There is a surge in interest in self-supervised learning approaches for end-to-end speech encoding in recent years as they have achieved great success. Especially, WavLM showed state-of-the-art performance on various speech processing tasks. To better understand the efficacy of self-supervised learning models for speech enhancement, in this work, we design and conduct a series of experiments with three resource conditions by combining WavLM and two high-quality speech enhancement systems. Also, We propose a regression-based WavLM training objective and a noise-mixing data configuration to further boost the downstream enhancement performance. The experiments on the DNS challenge dataset and a simulation dataset show that the WavLM benefits the speech enhancement task in terms of both speech quality and speech recognition accuracy, especially for low fine-tuning resources. For the high fine-tuning resource condition, only the word error rate is substantially improved." @default.
- W4319862462 created "2023-02-11" @default.
- W4319862462 creator A5017825677 @default.
- W4319862462 creator A5032260110 @default.
- W4319862462 creator A5034770439 @default.
- W4319862462 creator A5045556326 @default.
- W4319862462 creator A5048919230 @default.
- W4319862462 creator A5054155133 @default.
- W4319862462 creator A5073806960 @default.
- W4319862462 creator A5079533447 @default.
- W4319862462 date "2023-01-09" @default.
- W4319862462 modified "2023-10-16" @default.
- W4319862462 title "Exploring WavLM on Speech Enhancement" @default.
- W4319862462 cites W2995181338 @default.
- W4319862462 cites W3015337486 @default.
- W4319862462 cites W3031135612 @default.
- W4319862462 cites W3096408984 @default.
- W4319862462 cites W3097945073 @default.
- W4319862462 cites W3160129476 @default.
- W4319862462 cites W3163842642 @default.
- W4319862462 cites W3175898847 @default.
- W4319862462 cites W3191448984 @default.
- W4319862462 cites W3197042120 @default.
- W4319862462 cites W3197729725 @default.
- W4319862462 cites W3198680319 @default.
- W4319862462 cites W3206252155 @default.
- W4319862462 cites W3209059054 @default.
- W4319862462 cites W3209984917 @default.
- W4319862462 cites W4225302959 @default.
- W4319862462 cites W4226033575 @default.
- W4319862462 cites W4285258106 @default.
- W4319862462 cites W4292969786 @default.
- W4319862462 doi "https://doi.org/10.1109/slt54892.2023.10023356" @default.
- W4319862462 hasPublicationYear "2023" @default.
- W4319862462 type Work @default.
- W4319862462 citedByCount "1" @default.
- W4319862462 countsByYear W43198624622023 @default.
- W4319862462 crossrefType "proceedings-article" @default.
- W4319862462 hasAuthorship W4319862462A5017825677 @default.
- W4319862462 hasAuthorship W4319862462A5032260110 @default.
- W4319862462 hasAuthorship W4319862462A5034770439 @default.
- W4319862462 hasAuthorship W4319862462A5045556326 @default.
- W4319862462 hasAuthorship W4319862462A5048919230 @default.
- W4319862462 hasAuthorship W4319862462A5054155133 @default.
- W4319862462 hasAuthorship W4319862462A5073806960 @default.
- W4319862462 hasAuthorship W4319862462A5079533447 @default.
- W4319862462 hasBestOaLocation W43198624622 @default.
- W4319862462 hasConcept C115961682 @default.
- W4319862462 hasConcept C119857082 @default.
- W4319862462 hasConcept C125411270 @default.
- W4319862462 hasConcept C154945302 @default.
- W4319862462 hasConcept C162324750 @default.
- W4319862462 hasConcept C163294075 @default.
- W4319862462 hasConcept C187736073 @default.
- W4319862462 hasConcept C2776182073 @default.
- W4319862462 hasConcept C2780451532 @default.
- W4319862462 hasConcept C28490314 @default.
- W4319862462 hasConcept C40969351 @default.
- W4319862462 hasConcept C41008148 @default.
- W4319862462 hasConcept C61328038 @default.
- W4319862462 hasConcept C99498987 @default.
- W4319862462 hasConceptScore W4319862462C115961682 @default.
- W4319862462 hasConceptScore W4319862462C119857082 @default.
- W4319862462 hasConceptScore W4319862462C125411270 @default.
- W4319862462 hasConceptScore W4319862462C154945302 @default.
- W4319862462 hasConceptScore W4319862462C162324750 @default.
- W4319862462 hasConceptScore W4319862462C163294075 @default.
- W4319862462 hasConceptScore W4319862462C187736073 @default.
- W4319862462 hasConceptScore W4319862462C2776182073 @default.
- W4319862462 hasConceptScore W4319862462C2780451532 @default.
- W4319862462 hasConceptScore W4319862462C28490314 @default.
- W4319862462 hasConceptScore W4319862462C40969351 @default.
- W4319862462 hasConceptScore W4319862462C41008148 @default.
- W4319862462 hasConceptScore W4319862462C61328038 @default.
- W4319862462 hasConceptScore W4319862462C99498987 @default.
- W4319862462 hasLocation W43198624621 @default.
- W4319862462 hasLocation W43198624622 @default.
- W4319862462 hasOpenAccess W4319862462 @default.
- W4319862462 hasPrimaryLocation W43198624621 @default.
- W4319862462 hasRelatedWork W1570867132 @default.
- W4319862462 hasRelatedWork W2100534065 @default.
- W4319862462 hasRelatedWork W2117857642 @default.
- W4319862462 hasRelatedWork W2131674787 @default.
- W4319862462 hasRelatedWork W2408394826 @default.
- W4319862462 hasRelatedWork W2485008119 @default.
- W4319862462 hasRelatedWork W2786518799 @default.
- W4319862462 hasRelatedWork W2804490284 @default.
- W4319862462 hasRelatedWork W2926831050 @default.
- W4319862462 hasRelatedWork W3010889951 @default.
- W4319862462 isParatext "false" @default.
- W4319862462 isRetracted "false" @default.
- W4319862462 workType "article" @default.