Matches in SemOpenAlex for { <https://semopenalex.org/work/W2013531086> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2013531086 abstract "Regarding the non-negativity property of the magnitude spectrogram of speech signals, nonnegative matrix factorization (NMF) has obtained promising performance for speech separation by independently learning a dictionary on the speech signals of each known speaker. However, traditional NM-F fails to represent the mixture signals accurately because the dictionaries for speakers are learned in the absence of mixture signals. In this paper, we propose a new transductive NMF algorithm (TNMF) to jointly learn a dictionary on both speech signals of each speaker and the mixture signals to be separated. Since TNMF learns a more descriptive dictionary by encoding the mixture signals than that learned by NMF, it significantly boosts the separation performance. Experiments results on a popular TIMIT dataset show that the proposed TNMF-based methods outperform traditional NMF-based methods for separating the monophonic mixtures of speech signals of known speakers." @default.
- W2013531086 created "2016-06-24" @default.
- W2013531086 creator A5060251766 @default.
- W2013531086 creator A5061811574 @default.
- W2013531086 creator A5061870286 @default.
- W2013531086 creator A5074103823 @default.
- W2013531086 creator A5075453082 @default.
- W2013531086 date "2014-05-01" @default.
- W2013531086 modified "2023-10-16" @default.
- W2013531086 title "Transductive nonnegative matrix factorization for semi-supervised high-performance speech separation" @default.
- W2013531086 cites W142485264 @default.
- W2013531086 cites W2013608223 @default.
- W2013531086 cites W2039844283 @default.
- W2013531086 cites W2045956438 @default.
- W2013531086 cites W2053023379 @default.
- W2013531086 cites W2097872774 @default.
- W2013531086 cites W2107008379 @default.
- W2013531086 cites W2114461480 @default.
- W2013531086 cites W2120865781 @default.
- W2013531086 cites W2121061347 @default.
- W2013531086 cites W2121281940 @default.
- W2013531086 cites W2124149378 @default.
- W2013531086 cites W2135104405 @default.
- W2013531086 cites W2141892084 @default.
- W2013531086 cites W2144719328 @default.
- W2013531086 cites W2155151262 @default.
- W2013531086 cites W2156448167 @default.
- W2013531086 doi "https://doi.org/10.1109/icassp.2014.6854057" @default.
- W2013531086 hasPublicationYear "2014" @default.
- W2013531086 type Work @default.
- W2013531086 sameAs 2013531086 @default.
- W2013531086 citedByCount "11" @default.
- W2013531086 countsByYear W20135310862015 @default.
- W2013531086 countsByYear W20135310862016 @default.
- W2013531086 countsByYear W20135310862017 @default.
- W2013531086 countsByYear W20135310862018 @default.
- W2013531086 countsByYear W20135310862020 @default.
- W2013531086 crossrefType "proceedings-article" @default.
- W2013531086 hasAuthorship W2013531086A5060251766 @default.
- W2013531086 hasAuthorship W2013531086A5061811574 @default.
- W2013531086 hasAuthorship W2013531086A5061870286 @default.
- W2013531086 hasAuthorship W2013531086A5074103823 @default.
- W2013531086 hasAuthorship W2013531086A5075453082 @default.
- W2013531086 hasConcept C121332964 @default.
- W2013531086 hasConcept C152671427 @default.
- W2013531086 hasConcept C153180895 @default.
- W2013531086 hasConcept C154945302 @default.
- W2013531086 hasConcept C158693339 @default.
- W2013531086 hasConcept C23224414 @default.
- W2013531086 hasConcept C2776864781 @default.
- W2013531086 hasConcept C2778724510 @default.
- W2013531086 hasConcept C28490314 @default.
- W2013531086 hasConcept C41008148 @default.
- W2013531086 hasConcept C42355184 @default.
- W2013531086 hasConcept C45273575 @default.
- W2013531086 hasConcept C61328038 @default.
- W2013531086 hasConcept C62520636 @default.
- W2013531086 hasConceptScore W2013531086C121332964 @default.
- W2013531086 hasConceptScore W2013531086C152671427 @default.
- W2013531086 hasConceptScore W2013531086C153180895 @default.
- W2013531086 hasConceptScore W2013531086C154945302 @default.
- W2013531086 hasConceptScore W2013531086C158693339 @default.
- W2013531086 hasConceptScore W2013531086C23224414 @default.
- W2013531086 hasConceptScore W2013531086C2776864781 @default.
- W2013531086 hasConceptScore W2013531086C2778724510 @default.
- W2013531086 hasConceptScore W2013531086C28490314 @default.
- W2013531086 hasConceptScore W2013531086C41008148 @default.
- W2013531086 hasConceptScore W2013531086C42355184 @default.
- W2013531086 hasConceptScore W2013531086C45273575 @default.
- W2013531086 hasConceptScore W2013531086C61328038 @default.
- W2013531086 hasConceptScore W2013531086C62520636 @default.
- W2013531086 hasLocation W20135310861 @default.
- W2013531086 hasOpenAccess W2013531086 @default.
- W2013531086 hasPrimaryLocation W20135310861 @default.
- W2013531086 hasRelatedWork W1488912948 @default.
- W2013531086 hasRelatedWork W1988401578 @default.
- W2013531086 hasRelatedWork W1995191535 @default.
- W2013531086 hasRelatedWork W2013531086 @default.
- W2013531086 hasRelatedWork W2152457943 @default.
- W2013531086 hasRelatedWork W2558565288 @default.
- W2013531086 hasRelatedWork W2760027020 @default.
- W2013531086 hasRelatedWork W2809053816 @default.
- W2013531086 hasRelatedWork W2903905581 @default.
- W2013531086 hasRelatedWork W2998100475 @default.
- W2013531086 isParatext "false" @default.
- W2013531086 isRetracted "false" @default.
- W2013531086 magId "2013531086" @default.
- W2013531086 workType "article" @default.