FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203177955> ?p ?o ?g. }

• W3203177955 endingPage "1762" @default.
• W3203177955 startingPage "1749" @default.
• W3203177955 abstract "Sound event localization and detection (SELD) consists of two subtasks, which are sound event detection and direction-of-arrival estimation. While sound event detection mainly relies on time-frequency patterns to distinguish different sound classes, direction-of-arrival estimation uses amplitude and/or phase differences between microphones to estimate source directions. As a result, it is often difficult to jointly optimize these two subtasks. We propose a novel feature called <i>Spatial cue-Augmented Log-SpectrogrAm</i> (SALSA) with exact time-frequency mapping between the signal power and the source directional cues, which is crucial for resolving overlapping sound sources. The SALSA feature consists of multichannel log-spectrograms stacked along with the normalized principal eigenvector of the spatial covariance matrix at each corresponding time-frequency bin. Depending on the microphone array format, the principal eigenvector can be normalized differently to extract amplitude and/or phase differences between the microphones. As a result, SALSA features are applicable for different microphone array formats such as first-order ambisonics (FOA) and multichannel microphone array (MIC). Experimental results on the TAU-NIGENS Spatial Sound Events 2021 dataset with directional interferences showed that SALSA features outperformed other state-of-the-art features. Specifically, the use of SALSA features in the FOA format increased the F1 score and localization recall by <inline-formula><tex-math notation=LaTeX>$6 ,%$</tex-math></inline-formula> each, compared to the multichannel log-mel spectrograms with intensity vectors. For the MIC format, using SALSA features increased F1 score and localization recall by <inline-formula><tex-math notation=LaTeX>$16 ,%$</tex-math></inline-formula> and <inline-formula><tex-math notation=LaTeX>$7 ,%$</tex-math></inline-formula>, respectively, compared to using multichannel log-mel spectrograms with generalized cross-correlation spectra." @default.
• W3203177955 created "2021-10-11" @default.
• W3203177955 creator A5011788327 @default.
• W3203177955 creator A5039913415 @default.
• W3203177955 creator A5065667852 @default.
• W3203177955 creator A5072584895 @default.
• W3203177955 creator A5076817923 @default.
• W3203177955 date "2022-01-01" @default.
• W3203177955 modified "2023-10-16" @default.
• W3203177955 title "SALSA: Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detection" @default.
• W3203177955 cites W1964998538 @default.
• W3203177955 cites W1969299255 @default.
• W3203177955 cites W2025344720 @default.
• W3203177955 cites W2051428568 @default.
• W3203177955 cites W2085156437 @default.
• W3203177955 cites W2130121545 @default.
• W3203177955 cites W2139129402 @default.
• W3203177955 cites W2290075840 @default.
• W3203177955 cites W2292996718 @default.
• W3203177955 cites W2518102674 @default.
• W3203177955 cites W2640418943 @default.
• W3203177955 cites W2672714283 @default.
• W3203177955 cites W2810934215 @default.
• W3203177955 cites W2936774411 @default.
• W3203177955 cites W2942551338 @default.
• W3203177955 cites W2982382207 @default.
• W3203177955 cites W2982429715 @default.
• W3203177955 cites W2982680886 @default.
• W3203177955 cites W2998139081 @default.
• W3203177955 cites W2998508940 @default.
• W3203177955 cites W3081461453 @default.
• W3203177955 cites W3083274258 @default.
• W3203177955 cites W3094550259 @default.
• W3203177955 cites W3096287167 @default.
• W3203177955 cites W3098357269 @default.
• W3203177955 cites W3149712154 @default.
• W3203177955 cites W3163193264 @default.
• W3203177955 cites W3163206520 @default.
• W3203177955 cites W3163881933 @default.
• W3203177955 doi "https://doi.org/10.1109/taslp.2022.3173054" @default.
• W3203177955 hasPublicationYear "2022" @default.
• W3203177955 type Work @default.
• W3203177955 sameAs 3203177955 @default.
• W3203177955 citedByCount "6" @default.
• W3203177955 countsByYear W32031779552022 @default.
• W3203177955 countsByYear W32031779552023 @default.
• W3203177955 crossrefType "journal-article" @default.
• W3203177955 hasAuthorship W3203177955A5011788327 @default.
• W3203177955 hasAuthorship W3203177955A5039913415 @default.
• W3203177955 hasAuthorship W3203177955A5065667852 @default.
• W3203177955 hasAuthorship W3203177955A5072584895 @default.
• W3203177955 hasAuthorship W3203177955A5076817923 @default.
• W3203177955 hasBestOaLocation W32031779552 @default.
• W3203177955 hasConcept C138885662 @default.
• W3203177955 hasConcept C153180895 @default.
• W3203177955 hasConcept C154945302 @default.
• W3203177955 hasConcept C172051844 @default.
• W3203177955 hasConcept C21822782 @default.
• W3203177955 hasConcept C2776401178 @default.
• W3203177955 hasConcept C2778263558 @default.
• W3203177955 hasConcept C2778806681 @default.
• W3203177955 hasConcept C28490314 @default.
• W3203177955 hasConcept C33923547 @default.
• W3203177955 hasConcept C41008148 @default.
• W3203177955 hasConcept C41895202 @default.
• W3203177955 hasConcept C45273575 @default.
• W3203177955 hasConcept C68115822 @default.
• W3203177955 hasConcept C76155785 @default.
• W3203177955 hasConceptScore W3203177955C138885662 @default.
• W3203177955 hasConceptScore W3203177955C153180895 @default.
• W3203177955 hasConceptScore W3203177955C154945302 @default.
• W3203177955 hasConceptScore W3203177955C172051844 @default.
• W3203177955 hasConceptScore W3203177955C21822782 @default.
• W3203177955 hasConceptScore W3203177955C2776401178 @default.
• W3203177955 hasConceptScore W3203177955C2778263558 @default.
• W3203177955 hasConceptScore W3203177955C2778806681 @default.
• W3203177955 hasConceptScore W3203177955C28490314 @default.
• W3203177955 hasConceptScore W3203177955C33923547 @default.
• W3203177955 hasConceptScore W3203177955C41008148 @default.
• W3203177955 hasConceptScore W3203177955C41895202 @default.
• W3203177955 hasConceptScore W3203177955C45273575 @default.
• W3203177955 hasConceptScore W3203177955C68115822 @default.
• W3203177955 hasConceptScore W3203177955C76155785 @default.
• W3203177955 hasLocation W32031779551 @default.
• W3203177955 hasLocation W32031779552 @default.
• W3203177955 hasLocation W32031779553 @default.
• W3203177955 hasLocation W32031779554 @default.
• W3203177955 hasOpenAccess W3203177955 @default.
• W3203177955 hasPrimaryLocation W32031779551 @default.
• W3203177955 hasRelatedWork W1488173215 @default.
• W3203177955 hasRelatedWork W2116623987 @default.
• W3203177955 hasRelatedWork W2119838689 @default.
• W3203177955 hasRelatedWork W2161947961 @default.
• W3203177955 hasRelatedWork W2165869870 @default.
• W3203177955 hasRelatedWork W2382607599 @default.
• W3203177955 hasRelatedWork W2546942002 @default.
• W3203177955 hasRelatedWork W2900122540 @default.
• W3203177955 hasRelatedWork W2970216048 @default.

• next