FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100871498> ?p ?o ?g. }

• W3100871498 endingPage "1440003" @default.
• W3100871498 startingPage "1440003" @default.
• W3100871498 abstract "In this paper, we address the problems of modeling the acoustic space generated by a full-spectrum sound source and using the learned model for the localization and separation of multiple sources that simultaneously emit sparse-spectrum sounds. We lay theoretical and methodological grounds in order to introduce the binaural manifold paradigm. We perform an in-depth study of the latent low-dimensional structure of the high-dimensional interaural spectral data, based on a corpus recorded with a human-like audiomotor robot head. A nonlinear dimensionality reduction technique is used to show that these data lie on a two-dimensional (2D) smooth manifold parameterized by the motor states of the listener, or equivalently, the sound-source directions. We propose a probabilistic piecewise affine mapping model (PPAM) specifically designed to deal with high-dimensional data exhibiting an intrinsic piecewise linear structure. We derive a closed-form expectation-maximization (EM) procedure for estimating the model parameters, followed by Bayes inversion for obtaining the full posterior density function of a sound-source direction. We extend this solution to deal with missing data and redundancy in real-world spectrograms, and hence for 2D localization of natural sound sources such as speech. We further generalize the model to the challenging case of multiple sound sources and we propose a variational EM framework. The associated algorithm, referred to as variational EM for source separation and localization (VESSL) yields a Bayesian estimation of the 2D locations and time-frequency masks of all the sources. Comparisons of the proposed approach with several existing methods reveal that the combination of acoustic-space learning with Bayesian inference enables our method to outperform state-of-the-art methods." @default.
• W3100871498 created "2020-11-23" @default.
• W3100871498 creator A5000981106 @default.
• W3100871498 creator A5078307335 @default.
• W3100871498 creator A5088691547 @default.
• W3100871498 date "2015-01-06" @default.
• W3100871498 modified "2023-10-14" @default.
• W3100871498 title "Acoustic Space Learning for Sound-Source Separation and Localization on Binaural Manifolds" @default.
• W3100871498 cites W1489347216 @default.
• W3100871498 cites W1673812739 @default.
• W3100871498 cites W1971830354 @default.
• W3100871498 cites W1974648697 @default.
• W3100871498 cites W1982854652 @default.
• W3100871498 cites W1987906574 @default.
• W3100871498 cites W1991139021 @default.
• W3100871498 cites W2030219534 @default.
• W3100871498 cites W2064039476 @default.
• W3100871498 cites W2072817066 @default.
• W3100871498 cites W2074335765 @default.
• W3100871498 cites W2104257868 @default.
• W3100871498 cites W2108766544 @default.
• W3100871498 cites W2109995759 @default.
• W3100871498 cites W2127851351 @default.
• W3100871498 cites W2129171989 @default.
• W3100871498 cites W2134642725 @default.
• W3100871498 cites W2137225583 @default.
• W3100871498 cites W2139190150 @default.
• W3100871498 cites W2143027228 @default.
• W3100871498 cites W2143169494 @default.
• W3100871498 cites W2151903317 @default.
• W3100871498 cites W2154830775 @default.
• W3100871498 cites W2156142001 @default.
• W3100871498 cites W2163490846 @default.
• W3100871498 cites W4233392025 @default.
• W3100871498 doi "https://doi.org/10.1142/s0129065714400036" @default.
• W3100871498 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/25164245" @default.
• W3100871498 hasPublicationYear "2015" @default.
• W3100871498 type Work @default.
• W3100871498 sameAs 3100871498 @default.
• W3100871498 citedByCount "55" @default.
• W3100871498 countsByYear W31008714982015 @default.
• W3100871498 countsByYear W31008714982016 @default.
• W3100871498 countsByYear W31008714982017 @default.
• W3100871498 countsByYear W31008714982018 @default.
• W3100871498 countsByYear W31008714982019 @default.
• W3100871498 countsByYear W31008714982020 @default.
• W3100871498 countsByYear W31008714982021 @default.
• W3100871498 countsByYear W31008714982022 @default.
• W3100871498 countsByYear W31008714982023 @default.
• W3100871498 crossrefType "journal-article" @default.
• W3100871498 hasAuthorship W3100871498A5000981106 @default.
• W3100871498 hasAuthorship W3100871498A5078307335 @default.
• W3100871498 hasAuthorship W3100871498A5088691547 @default.
• W3100871498 hasBestOaLocation W31008714982 @default.
• W3100871498 hasConcept C108250783 @default.
• W3100871498 hasConcept C11413529 @default.
• W3100871498 hasConcept C121332964 @default.
• W3100871498 hasConcept C201247586 @default.
• W3100871498 hasConcept C203718221 @default.
• W3100871498 hasConcept C24890656 @default.
• W3100871498 hasConcept C2776864781 @default.
• W3100871498 hasConcept C28490314 @default.
• W3100871498 hasConcept C33923547 @default.
• W3100871498 hasConcept C41008148 @default.
• W3100871498 hasConcept C93240960 @default.
• W3100871498 hasConceptScore W3100871498C108250783 @default.
• W3100871498 hasConceptScore W3100871498C11413529 @default.
• W3100871498 hasConceptScore W3100871498C121332964 @default.
• W3100871498 hasConceptScore W3100871498C201247586 @default.
• W3100871498 hasConceptScore W3100871498C203718221 @default.
• W3100871498 hasConceptScore W3100871498C24890656 @default.
• W3100871498 hasConceptScore W3100871498C2776864781 @default.
• W3100871498 hasConceptScore W3100871498C28490314 @default.
• W3100871498 hasConceptScore W3100871498C33923547 @default.
• W3100871498 hasConceptScore W3100871498C41008148 @default.
• W3100871498 hasConceptScore W3100871498C93240960 @default.
• W3100871498 hasIssue "01" @default.
• W3100871498 hasLocation W31008714981 @default.
• W3100871498 hasLocation W31008714982 @default.
• W3100871498 hasLocation W31008714983 @default.
• W3100871498 hasLocation W31008714984 @default.
• W3100871498 hasLocation W31008714985 @default.
• W3100871498 hasLocation W31008714986 @default.
• W3100871498 hasLocation W31008714987 @default.
• W3100871498 hasOpenAccess W3100871498 @default.
• W3100871498 hasPrimaryLocation W31008714981 @default.
• W3100871498 hasRelatedWork W1608003482 @default.
• W3100871498 hasRelatedWork W2015890751 @default.
• W3100871498 hasRelatedWork W2038743608 @default.
• W3100871498 hasRelatedWork W2074134755 @default.
• W3100871498 hasRelatedWork W2809056180 @default.
• W3100871498 hasRelatedWork W2903040254 @default.
• W3100871498 hasRelatedWork W2943743938 @default.
• W3100871498 hasRelatedWork W4226449293 @default.
• W3100871498 hasRelatedWork W4372260199 @default.
• W3100871498 hasRelatedWork W606675693 @default.
• W3100871498 hasVolume "25" @default.
• W3100871498 isParatext "false" @default.

• next