Matches in SemOpenAlex for { <https://semopenalex.org/work/W3191555358> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3191555358 endingPage "2763" @default.
- W3191555358 startingPage "2753" @default.
- W3191555358 abstract "In speech separation, the identities of the speakers may be an important cue to discriminate speeches in the mixture and separate them better. A few recent researches used the speaker embedding as an additional information, but they often require prior information about the target speaker or used noisy speaker embedding extracted from the mixture signal. In this article, we propose monaural speech separation that utilizes the speaker embedding in the later separator blocks, which is extracted from the intermediate separated results obtained by the early stages of the separator network. The later blocks in the separator networks consisting of repeated blocks such as the fully-convolutional time-domain audio separation network (Conv-TasNet) or the successive downsampling and resampling of multi-resolution features (SuDoRM-RF) are modified to take the speaker information as a form of affine transformation or addition to the original input tensor. The experimental results showed that the proposed methods significantly improved the performances of existing separation systems with a moderate number of additional parameters." @default.
- W3191555358 created "2021-08-16" @default.
- W3191555358 creator A5034409385 @default.
- W3191555358 creator A5054155133 @default.
- W3191555358 date "2021-01-01" @default.
- W3191555358 modified "2023-09-30" @default.
- W3191555358 title "Monaural Speech Separation Using Speaker Embedding From Preliminary Separation" @default.
- W3191555358 cites W1494198834 @default.
- W3191555358 cites W1677182931 @default.
- W3191555358 cites W1997528538 @default.
- W3191555358 cites W2077799289 @default.
- W3191555358 cites W2134706965 @default.
- W3191555358 cites W2194775991 @default.
- W3191555358 cites W2221409856 @default.
- W3191555358 cites W2344461865 @default.
- W3191555358 cites W2479176461 @default.
- W3191555358 cites W2609317876 @default.
- W3191555358 cites W2610852352 @default.
- W3191555358 cites W2669032454 @default.
- W3191555358 cites W2734774145 @default.
- W3191555358 cites W2735663686 @default.
- W3191555358 cites W2794506738 @default.
- W3191555358 cites W2808631503 @default.
- W3191555358 cites W2890964092 @default.
- W3191555358 cites W2947942791 @default.
- W3191555358 cites W2952218014 @default.
- W3191555358 cites W2958305995 @default.
- W3191555358 cites W2962898354 @default.
- W3191555358 cites W2962935966 @default.
- W3191555358 cites W2963177459 @default.
- W3191555358 cites W2963371159 @default.
- W3191555358 cites W2963420686 @default.
- W3191555358 cites W2963843276 @default.
- W3191555358 cites W2964058413 @default.
- W3191555358 cites W2971758476 @default.
- W3191555358 cites W2972460025 @default.
- W3191555358 cites W2978032182 @default.
- W3191555358 cites W2981436548 @default.
- W3191555358 cites W2990666817 @default.
- W3191555358 cites W3013020904 @default.
- W3191555358 cites W3015199127 @default.
- W3191555358 cites W3015306128 @default.
- W3191555358 cites W3015372568 @default.
- W3191555358 cites W3016048045 @default.
- W3191555358 cites W3016232124 @default.
- W3191555358 cites W3022595508 @default.
- W3191555358 cites W3089552252 @default.
- W3191555358 cites W3094607766 @default.
- W3191555358 cites W3095717210 @default.
- W3191555358 cites W3096796823 @default.
- W3191555358 cites W3097609423 @default.
- W3191555358 cites W3097653961 @default.
- W3191555358 cites W3097797867 @default.
- W3191555358 cites W3112893973 @default.
- W3191555358 doi "https://doi.org/10.1109/taslp.2021.3101617" @default.
- W3191555358 hasPublicationYear "2021" @default.
- W3191555358 type Work @default.
- W3191555358 sameAs 3191555358 @default.
- W3191555358 citedByCount "5" @default.
- W3191555358 countsByYear W31915553582022 @default.
- W3191555358 countsByYear W31915553582023 @default.
- W3191555358 crossrefType "journal-article" @default.
- W3191555358 hasAuthorship W3191555358A5034409385 @default.
- W3191555358 hasAuthorship W3191555358A5054155133 @default.
- W3191555358 hasConcept C102894143 @default.
- W3191555358 hasConcept C119857082 @default.
- W3191555358 hasConcept C2776061190 @default.
- W3191555358 hasConcept C28490314 @default.
- W3191555358 hasConcept C41008148 @default.
- W3191555358 hasConceptScore W3191555358C102894143 @default.
- W3191555358 hasConceptScore W3191555358C119857082 @default.
- W3191555358 hasConceptScore W3191555358C2776061190 @default.
- W3191555358 hasConceptScore W3191555358C28490314 @default.
- W3191555358 hasConceptScore W3191555358C41008148 @default.
- W3191555358 hasFunder F4320322120 @default.
- W3191555358 hasLocation W31915553581 @default.
- W3191555358 hasOpenAccess W3191555358 @default.
- W3191555358 hasPrimaryLocation W31915553581 @default.
- W3191555358 hasRelatedWork W1964208564 @default.
- W3191555358 hasRelatedWork W2062801241 @default.
- W3191555358 hasRelatedWork W2148286861 @default.
- W3191555358 hasRelatedWork W2401567014 @default.
- W3191555358 hasRelatedWork W2406185883 @default.
- W3191555358 hasRelatedWork W2889698889 @default.
- W3191555358 hasRelatedWork W2893763841 @default.
- W3191555358 hasRelatedWork W2900114706 @default.
- W3191555358 hasRelatedWork W2921683566 @default.
- W3191555358 hasRelatedWork W2980451698 @default.
- W3191555358 hasVolume "29" @default.
- W3191555358 isParatext "false" @default.
- W3191555358 isRetracted "false" @default.
- W3191555358 magId "3191555358" @default.
- W3191555358 workType "article" @default.