Matches in SemOpenAlex for { <https://semopenalex.org/work/W3145709712> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3145709712 abstract "Deep learning has shown a great potential for speech separation, especially for speech and non-speech separation. However, it encounters permutation problem for multi-speaker separation where both target and interference are speech. Permutation Invariant training (PIT) was proposed to solve this problem by permuting the order of the multiple speakers. Another way is to use an anchor speech, a short speech of the target speaker, to model the speaker identity. In this paper, we propose a simple strategy to train a long short-term memory (LSTM) model to solve the permutation problem in speaker separation. Specifically, we insert a short speech of target speaker at the beginning of a mixture as guide information. So, the first appearing speaker is defined as the target. Due to the powerful capability on sequence modeling, LSTM can use its memory cells to track and separate target speech from interfering speech. Experimental results show that the proposed training strategy is effective for speaker separation." @default.
- W3145709712 created "2021-04-13" @default.
- W3145709712 creator A5019560977 @default.
- W3145709712 creator A5045708462 @default.
- W3145709712 creator A5076174513 @default.
- W3145709712 date "2021-03-26" @default.
- W3145709712 modified "2023-09-26" @default.
- W3145709712 title "Guided Training: A Simple Method for Single-channel Speaker Separation." @default.
- W3145709712 cites W1482149378 @default.
- W3145709712 cites W1552314771 @default.
- W3145709712 cites W2064675550 @default.
- W3145709712 cites W2095705004 @default.
- W3145709712 cites W2127851351 @default.
- W3145709712 cites W2143612262 @default.
- W3145709712 cites W2144763279 @default.
- W3145709712 cites W2156387975 @default.
- W3145709712 cites W2221409856 @default.
- W3145709712 cites W2398972335 @default.
- W3145709712 cites W2460742184 @default.
- W3145709712 cites W2561557072 @default.
- W3145709712 cites W2610674366 @default.
- W3145709712 cites W2749510669 @default.
- W3145709712 cites W2749659773 @default.
- W3145709712 cites W2891283181 @default.
- W3145709712 cites W2891833136 @default.
- W3145709712 cites W2962866211 @default.
- W3145709712 cites W2964121744 @default.
- W3145709712 hasPublicationYear "2021" @default.
- W3145709712 type Work @default.
- W3145709712 sameAs 3145709712 @default.
- W3145709712 citedByCount "0" @default.
- W3145709712 crossrefType "posted-content" @default.
- W3145709712 hasAuthorship W3145709712A5019560977 @default.
- W3145709712 hasAuthorship W3145709712A5045708462 @default.
- W3145709712 hasAuthorship W3145709712A5076174513 @default.
- W3145709712 hasConcept C111472728 @default.
- W3145709712 hasConcept C119857082 @default.
- W3145709712 hasConcept C121332964 @default.
- W3145709712 hasConcept C127162648 @default.
- W3145709712 hasConcept C133892786 @default.
- W3145709712 hasConcept C138885662 @default.
- W3145709712 hasConcept C149838564 @default.
- W3145709712 hasConcept C154945302 @default.
- W3145709712 hasConcept C190470478 @default.
- W3145709712 hasConcept C21308566 @default.
- W3145709712 hasConcept C24890656 @default.
- W3145709712 hasConcept C2776061190 @default.
- W3145709712 hasConcept C2780586882 @default.
- W3145709712 hasConcept C28490314 @default.
- W3145709712 hasConcept C33923547 @default.
- W3145709712 hasConcept C37914503 @default.
- W3145709712 hasConcept C41008148 @default.
- W3145709712 hasConcept C76155785 @default.
- W3145709712 hasConceptScore W3145709712C111472728 @default.
- W3145709712 hasConceptScore W3145709712C119857082 @default.
- W3145709712 hasConceptScore W3145709712C121332964 @default.
- W3145709712 hasConceptScore W3145709712C127162648 @default.
- W3145709712 hasConceptScore W3145709712C133892786 @default.
- W3145709712 hasConceptScore W3145709712C138885662 @default.
- W3145709712 hasConceptScore W3145709712C149838564 @default.
- W3145709712 hasConceptScore W3145709712C154945302 @default.
- W3145709712 hasConceptScore W3145709712C190470478 @default.
- W3145709712 hasConceptScore W3145709712C21308566 @default.
- W3145709712 hasConceptScore W3145709712C24890656 @default.
- W3145709712 hasConceptScore W3145709712C2776061190 @default.
- W3145709712 hasConceptScore W3145709712C2780586882 @default.
- W3145709712 hasConceptScore W3145709712C28490314 @default.
- W3145709712 hasConceptScore W3145709712C33923547 @default.
- W3145709712 hasConceptScore W3145709712C37914503 @default.
- W3145709712 hasConceptScore W3145709712C41008148 @default.
- W3145709712 hasConceptScore W3145709712C76155785 @default.
- W3145709712 hasLocation W31457097121 @default.
- W3145709712 hasOpenAccess W3145709712 @default.
- W3145709712 hasPrimaryLocation W31457097121 @default.
- W3145709712 hasRelatedWork W2101404574 @default.
- W3145709712 hasRelatedWork W2562274522 @default.
- W3145709712 hasRelatedWork W2727354829 @default.
- W3145709712 hasRelatedWork W2735663686 @default.
- W3145709712 hasRelatedWork W2799930831 @default.
- W3145709712 hasRelatedWork W2939771864 @default.
- W3145709712 hasRelatedWork W2951295643 @default.
- W3145709712 hasRelatedWork W2952482988 @default.
- W3145709712 hasRelatedWork W2976460547 @default.
- W3145709712 hasRelatedWork W3011028252 @default.
- W3145709712 hasRelatedWork W3016048045 @default.
- W3145709712 hasRelatedWork W3029444444 @default.
- W3145709712 hasRelatedWork W3095082129 @default.
- W3145709712 hasRelatedWork W3097206043 @default.
- W3145709712 hasRelatedWork W3126427729 @default.
- W3145709712 hasRelatedWork W3133801870 @default.
- W3145709712 hasRelatedWork W3186843219 @default.
- W3145709712 hasRelatedWork W3198112783 @default.
- W3145709712 hasRelatedWork W3209238651 @default.
- W3145709712 hasRelatedWork W2299143375 @default.
- W3145709712 isParatext "false" @default.
- W3145709712 isRetracted "false" @default.
- W3145709712 magId "3145709712" @default.
- W3145709712 workType "article" @default.