Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100336094> ?p ?o ?g. }
- W3100336094 endingPage "2012" @default.
- W3100336094 startingPage "1997" @default.
- W3100336094 abstract "This paper addresses the problem of multiple-speaker localization in noisy and reverberant environments, using binaural recordings of an acoustic scene. A complex-valued Gaussian mixture model (CGMM) is adopted, whose components correspond to all the possible candidate source locations defined on a grid. After optimizing the CGMM-based objective function, given an observed set of complex-valued binaural features, both the number of sources and their locations are estimated by selecting the CGMM components with the largest weights. An entropy-based penalty term is added to the likelihood to impose sparsity over the set of CGMM component weights. This favors a small number of detected speakers with respect to the large number of initial candidate source locations. In addition, the direct-path relative transfer function (DP-RTF) is used to build robust binaural features. The DP-RTF, recently proposed for single-source localization, encodes interchannel information corresponding to the direct path of sound propagation and is thus robust to reverberations. In this paper, we extend the DP-RTF estimation to the case of multiple sources. In the short-time Fourier transform domain, a consistency test is proposed to check whether a set of consecutive frames is associated with the same source or not. Reliable DP-RTF features are selected from the frames that pass the consistency test to be used for source localization. Experiments carried out using both simulation data and real data recorded with a robotic head confirm the efficiency of the proposed multisource localization method." @default.
- W3100336094 created "2020-11-23" @default.
- W3100336094 creator A5001052072 @default.
- W3100336094 creator A5020392160 @default.
- W3100336094 creator A5025270532 @default.
- W3100336094 creator A5078307335 @default.
- W3100336094 date "2017-10-01" @default.
- W3100336094 modified "2023-10-18" @default.
- W3100336094 title "Multiple-Speaker Localization Based on Direct-Path Features and Likelihood Maximization With Spatial Sparsity Regularization" @default.
- W3100336094 cites W1552633171 @default.
- W3100336094 cites W1555217905 @default.
- W3100336094 cites W1732489270 @default.
- W3100336094 cites W1772191655 @default.
- W3100336094 cites W1964998538 @default.
- W3100336094 cites W1966081805 @default.
- W3100336094 cites W1967504554 @default.
- W3100336094 cites W1981463705 @default.
- W3100336094 cites W1987906574 @default.
- W3100336094 cites W2000062601 @default.
- W3100336094 cites W2004140730 @default.
- W3100336094 cites W2015245929 @default.
- W3100336094 cites W2016637789 @default.
- W3100336094 cites W2025127228 @default.
- W3100336094 cites W2031744243 @default.
- W3100336094 cites W2037949455 @default.
- W3100336094 cites W2046791564 @default.
- W3100336094 cites W2050551142 @default.
- W3100336094 cites W2055218217 @default.
- W3100336094 cites W2055401280 @default.
- W3100336094 cites W2066947968 @default.
- W3100336094 cites W2075657928 @default.
- W3100336094 cites W2084637638 @default.
- W3100336094 cites W2096439661 @default.
- W3100336094 cites W2096855653 @default.
- W3100336094 cites W2103519107 @default.
- W3100336094 cites W2115969105 @default.
- W3100336094 cites W2124906580 @default.
- W3100336094 cites W2129171989 @default.
- W3100336094 cites W2130357996 @default.
- W3100336094 cites W2131968171 @default.
- W3100336094 cites W2135158232 @default.
- W3100336094 cites W2147665979 @default.
- W3100336094 cites W2153248083 @default.
- W3100336094 cites W2155323221 @default.
- W3100336094 cites W2156676906 @default.
- W3100336094 cites W2166682639 @default.
- W3100336094 cites W2166765763 @default.
- W3100336094 cites W2204714259 @default.
- W3100336094 cites W2221524898 @default.
- W3100336094 cites W2231821870 @default.
- W3100336094 cites W2509456128 @default.
- W3100336094 cites W2532891002 @default.
- W3100336094 cites W2538968649 @default.
- W3100336094 cites W2962800621 @default.
- W3100336094 cites W2962927162 @default.
- W3100336094 cites W3100871498 @default.
- W3100336094 cites W3111988325 @default.
- W3100336094 cites W4250589301 @default.
- W3100336094 doi "https://doi.org/10.1109/taslp.2017.2740001" @default.
- W3100336094 hasPublicationYear "2017" @default.
- W3100336094 type Work @default.
- W3100336094 sameAs 3100336094 @default.
- W3100336094 citedByCount "31" @default.
- W3100336094 countsByYear W31003360942018 @default.
- W3100336094 countsByYear W31003360942019 @default.
- W3100336094 countsByYear W31003360942020 @default.
- W3100336094 countsByYear W31003360942021 @default.
- W3100336094 countsByYear W31003360942022 @default.
- W3100336094 countsByYear W31003360942023 @default.
- W3100336094 crossrefType "journal-article" @default.
- W3100336094 hasAuthorship W3100336094A5001052072 @default.
- W3100336094 hasAuthorship W3100336094A5020392160 @default.
- W3100336094 hasAuthorship W3100336094A5025270532 @default.
- W3100336094 hasAuthorship W3100336094A5078307335 @default.
- W3100336094 hasBestOaLocation W31003360942 @default.
- W3100336094 hasConcept C11413529 @default.
- W3100336094 hasConcept C121332964 @default.
- W3100336094 hasConcept C151382886 @default.
- W3100336094 hasConcept C153180895 @default.
- W3100336094 hasConcept C154945302 @default.
- W3100336094 hasConcept C163716315 @default.
- W3100336094 hasConcept C201247586 @default.
- W3100336094 hasConcept C28490314 @default.
- W3100336094 hasConcept C41008148 @default.
- W3100336094 hasConcept C51432778 @default.
- W3100336094 hasConcept C62520636 @default.
- W3100336094 hasConceptScore W3100336094C11413529 @default.
- W3100336094 hasConceptScore W3100336094C121332964 @default.
- W3100336094 hasConceptScore W3100336094C151382886 @default.
- W3100336094 hasConceptScore W3100336094C153180895 @default.
- W3100336094 hasConceptScore W3100336094C154945302 @default.
- W3100336094 hasConceptScore W3100336094C163716315 @default.
- W3100336094 hasConceptScore W3100336094C201247586 @default.
- W3100336094 hasConceptScore W3100336094C28490314 @default.
- W3100336094 hasConceptScore W3100336094C41008148 @default.
- W3100336094 hasConceptScore W3100336094C51432778 @default.
- W3100336094 hasConceptScore W3100336094C62520636 @default.
- W3100336094 hasIssue "10" @default.