Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312095890> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4312095890 abstract "In recent years, significant success has been made in single-channel speech enhancement using the deep neural networks. These approaches trained a model on synthetic noisy speech corpus, which was created by adding noise to clean speech. Because there is a mismatch between synthetic training data and the actual application environment, the model's performance is not guaranteed. This paper proposes to use a multi-channel speech enhancement teacher model to guide a single-channel noise suppression student model. We set the multi-channel teacher's processed signal as the single-channel student's training target. With our proposed approach, the single-channel speech enhancement model can be trained using real noisy speech and performed as well as a multi-channel speech enhancement model. Experimental results on CHIME-3 demonstrate that our proposed approach can achieve competitive performance both in speech enhancement and automatic speech recognition tasks, even without ground truth signals." @default.
- W4312095890 created "2023-01-04" @default.
- W4312095890 creator A5003759585 @default.
- W4312095890 creator A5045708462 @default.
- W4312095890 creator A5087214271 @default.
- W4312095890 date "2022-11-07" @default.
- W4312095890 modified "2023-09-26" @default.
- W4312095890 title "Single-channel Speech Enhancement Student under Multi-channel Speech Enhancement Teacher" @default.
- W4312095890 cites W1570694229 @default.
- W4312095890 cites W2045325572 @default.
- W4312095890 cites W2052539752 @default.
- W4312095890 cites W2059045901 @default.
- W4312095890 cites W2060108923 @default.
- W4312095890 cites W2060422862 @default.
- W4312095890 cites W2070707809 @default.
- W4312095890 cites W2100375013 @default.
- W4312095890 cites W2100818340 @default.
- W4312095890 cites W2128653836 @default.
- W4312095890 cites W2130357996 @default.
- W4312095890 cites W2148613904 @default.
- W4312095890 cites W2291877678 @default.
- W4312095890 cites W2711861986 @default.
- W4312095890 cites W2889442120 @default.
- W4312095890 cites W2919115771 @default.
- W4312095890 cites W2933708090 @default.
- W4312095890 cites W2952218014 @default.
- W4312095890 cites W2991361823 @default.
- W4312095890 cites W3015337486 @default.
- W4312095890 cites W3122264812 @default.
- W4312095890 cites W3147966746 @default.
- W4312095890 cites W3162341667 @default.
- W4312095890 cites W4245919820 @default.
- W4312095890 doi "https://doi.org/10.23919/apsipaasc55919.2022.9980275" @default.
- W4312095890 hasPublicationYear "2022" @default.
- W4312095890 type Work @default.
- W4312095890 citedByCount "0" @default.
- W4312095890 crossrefType "proceedings-article" @default.
- W4312095890 hasAuthorship W4312095890A5003759585 @default.
- W4312095890 hasAuthorship W4312095890A5045708462 @default.
- W4312095890 hasAuthorship W4312095890A5087214271 @default.
- W4312095890 hasConcept C100675267 @default.
- W4312095890 hasConcept C115961682 @default.
- W4312095890 hasConcept C127162648 @default.
- W4312095890 hasConcept C154945302 @default.
- W4312095890 hasConcept C155635449 @default.
- W4312095890 hasConcept C163294075 @default.
- W4312095890 hasConcept C177264268 @default.
- W4312095890 hasConcept C199360897 @default.
- W4312095890 hasConcept C204201278 @default.
- W4312095890 hasConcept C2776182073 @default.
- W4312095890 hasConcept C28490314 @default.
- W4312095890 hasConcept C29265498 @default.
- W4312095890 hasConcept C41008148 @default.
- W4312095890 hasConcept C51632099 @default.
- W4312095890 hasConcept C61328038 @default.
- W4312095890 hasConcept C76155785 @default.
- W4312095890 hasConcept C99498987 @default.
- W4312095890 hasConceptScore W4312095890C100675267 @default.
- W4312095890 hasConceptScore W4312095890C115961682 @default.
- W4312095890 hasConceptScore W4312095890C127162648 @default.
- W4312095890 hasConceptScore W4312095890C154945302 @default.
- W4312095890 hasConceptScore W4312095890C155635449 @default.
- W4312095890 hasConceptScore W4312095890C163294075 @default.
- W4312095890 hasConceptScore W4312095890C177264268 @default.
- W4312095890 hasConceptScore W4312095890C199360897 @default.
- W4312095890 hasConceptScore W4312095890C204201278 @default.
- W4312095890 hasConceptScore W4312095890C2776182073 @default.
- W4312095890 hasConceptScore W4312095890C28490314 @default.
- W4312095890 hasConceptScore W4312095890C29265498 @default.
- W4312095890 hasConceptScore W4312095890C41008148 @default.
- W4312095890 hasConceptScore W4312095890C51632099 @default.
- W4312095890 hasConceptScore W4312095890C61328038 @default.
- W4312095890 hasConceptScore W4312095890C76155785 @default.
- W4312095890 hasConceptScore W4312095890C99498987 @default.
- W4312095890 hasLocation W43120958901 @default.
- W4312095890 hasOpenAccess W4312095890 @default.
- W4312095890 hasPrimaryLocation W43120958901 @default.
- W4312095890 hasRelatedWork W1581699318 @default.
- W4312095890 hasRelatedWork W1995638733 @default.
- W4312095890 hasRelatedWork W2188881610 @default.
- W4312095890 hasRelatedWork W2248536413 @default.
- W4312095890 hasRelatedWork W2355125052 @default.
- W4312095890 hasRelatedWork W2418631473 @default.
- W4312095890 hasRelatedWork W2485008119 @default.
- W4312095890 hasRelatedWork W2753197815 @default.
- W4312095890 hasRelatedWork W2810291168 @default.
- W4312095890 hasRelatedWork W4312095890 @default.
- W4312095890 isParatext "false" @default.
- W4312095890 isRetracted "false" @default.
- W4312095890 workType "article" @default.