Matches in SemOpenAlex for { <https://semopenalex.org/work/W3023271093> ?p ?o ?g. }
- W3023271093 abstract "Speaker extraction aims to extract the target speech signal from a multi-talker environment given a target speaker's reference speech. We recently proposed a time-domain solution, SpEx, that avoids the phase estimation in frequency-domain approaches. Unfortunately, SpEx is not fully a time-domain solution since it performs time-domain speech encoding for speaker extraction, while taking frequency-domain speaker embedding as the reference. The size of the analysis window for time-domain and the size for frequency-domain input are also different. Such mismatch has an adverse effect on the system performance. To eliminate such mismatch, we propose a complete time-domain speaker extraction solution, that is called SpEx+. Specifically, we tie the weights of two identical speech encoder networks, one for the encoder-extractor-decoder pipeline, another as part of the speaker encoder. Experiments show that the SpEx+ achieves 0.8dB and 2.1dB SDR improvement over the state-of-the-art SpEx baseline, under different and same gender conditions on WSJ0-2mix-extr database respectively." @default.
- W3023271093 created "2020-05-13" @default.
- W3023271093 creator A5017251198 @default.
- W3023271093 creator A5032690182 @default.
- W3023271093 creator A5041413629 @default.
- W3023271093 creator A5050763764 @default.
- W3023271093 creator A5071074013 @default.
- W3023271093 creator A5080053477 @default.
- W3023271093 date "2020-05-10" @default.
- W3023271093 modified "2023-10-18" @default.
- W3023271093 title "SpEx+: A Complete Time Domain Speaker Extraction Network" @default.
- W3023271093 cites W2221409856 @default.
- W3023271093 cites W2460742184 @default.
- W3023271093 cites W2465050681 @default.
- W3023271093 cites W2529093176 @default.
- W3023271093 cites W2558649592 @default.
- W3023271093 cites W2734774145 @default.
- W3023271093 cites W2735663686 @default.
- W3023271093 cites W2749510669 @default.
- W3023271093 cites W2799119527 @default.
- W3023271093 cites W2800022361 @default.
- W3023271093 cites W2800664709 @default.
- W3023271093 cites W2889540509 @default.
- W3023271093 cites W2891405874 @default.
- W3023271093 cites W2891833136 @default.
- W3023271093 cites W2895807593 @default.
- W3023271093 cites W2897924318 @default.
- W3023271093 cites W2924115626 @default.
- W3023271093 cites W2939771864 @default.
- W3023271093 cites W2951130829 @default.
- W3023271093 cites W2952218014 @default.
- W3023271093 cites W2973054998 @default.
- W3023271093 cites W3008400075 @default.
- W3023271093 cites W3015199127 @default.
- W3023271093 cites W3015636705 @default.
- W3023271093 cites W3103434036 @default.
- W3023271093 cites W3105928222 @default.
- W3023271093 doi "https://doi.org/10.48550/arxiv.2005.04686" @default.
- W3023271093 hasPublicationYear "2020" @default.
- W3023271093 type Work @default.
- W3023271093 sameAs 3023271093 @default.
- W3023271093 citedByCount "6" @default.
- W3023271093 countsByYear W30232710932020 @default.
- W3023271093 countsByYear W30232710932021 @default.
- W3023271093 crossrefType "posted-content" @default.
- W3023271093 hasAuthorship W3023271093A5017251198 @default.
- W3023271093 hasAuthorship W3023271093A5032690182 @default.
- W3023271093 hasAuthorship W3023271093A5041413629 @default.
- W3023271093 hasAuthorship W3023271093A5050763764 @default.
- W3023271093 hasAuthorship W3023271093A5071074013 @default.
- W3023271093 hasAuthorship W3023271093A5080053477 @default.
- W3023271093 hasBestOaLocation W30232710931 @default.
- W3023271093 hasConcept C103824480 @default.
- W3023271093 hasConcept C111919701 @default.
- W3023271093 hasConcept C11413529 @default.
- W3023271093 hasConcept C118505674 @default.
- W3023271093 hasConcept C133892786 @default.
- W3023271093 hasConcept C134306372 @default.
- W3023271093 hasConcept C154945302 @default.
- W3023271093 hasConcept C185592680 @default.
- W3023271093 hasConcept C19118579 @default.
- W3023271093 hasConcept C199360897 @default.
- W3023271093 hasConcept C2779843651 @default.
- W3023271093 hasConcept C28490314 @default.
- W3023271093 hasConcept C2982762665 @default.
- W3023271093 hasConcept C31972630 @default.
- W3023271093 hasConcept C33923547 @default.
- W3023271093 hasConcept C36503486 @default.
- W3023271093 hasConcept C41008148 @default.
- W3023271093 hasConcept C41608201 @default.
- W3023271093 hasConcept C43521106 @default.
- W3023271093 hasConcept C43617362 @default.
- W3023271093 hasConcept C4725764 @default.
- W3023271093 hasConcept C57273362 @default.
- W3023271093 hasConceptScore W3023271093C103824480 @default.
- W3023271093 hasConceptScore W3023271093C111919701 @default.
- W3023271093 hasConceptScore W3023271093C11413529 @default.
- W3023271093 hasConceptScore W3023271093C118505674 @default.
- W3023271093 hasConceptScore W3023271093C133892786 @default.
- W3023271093 hasConceptScore W3023271093C134306372 @default.
- W3023271093 hasConceptScore W3023271093C154945302 @default.
- W3023271093 hasConceptScore W3023271093C185592680 @default.
- W3023271093 hasConceptScore W3023271093C19118579 @default.
- W3023271093 hasConceptScore W3023271093C199360897 @default.
- W3023271093 hasConceptScore W3023271093C2779843651 @default.
- W3023271093 hasConceptScore W3023271093C28490314 @default.
- W3023271093 hasConceptScore W3023271093C2982762665 @default.
- W3023271093 hasConceptScore W3023271093C31972630 @default.
- W3023271093 hasConceptScore W3023271093C33923547 @default.
- W3023271093 hasConceptScore W3023271093C36503486 @default.
- W3023271093 hasConceptScore W3023271093C41008148 @default.
- W3023271093 hasConceptScore W3023271093C41608201 @default.
- W3023271093 hasConceptScore W3023271093C43521106 @default.
- W3023271093 hasConceptScore W3023271093C43617362 @default.
- W3023271093 hasConceptScore W3023271093C4725764 @default.
- W3023271093 hasConceptScore W3023271093C57273362 @default.
- W3023271093 hasLocation W30232710931 @default.
- W3023271093 hasOpenAccess W3023271093 @default.
- W3023271093 hasPrimaryLocation W30232710931 @default.
- W3023271093 hasRelatedWork W1950712214 @default.