Please use this identifier to cite or link to this item:
|Title:||SALSA: spatial cue-augmented log-spectrogram features for polyphonic sound event localization and detection||Authors:||Nguyen, Thi Ngoc Tho
Watcharasupat, Karn N.
Nguyen, Ngoc Khanh
Jones, Douglas L.
|Keywords:||Engineering::Electrical and electronic engineering||Issue Date:||2022||Source:||Nguyen, T. N. T., Watcharasupat, K. N., Nguyen, N. K., Jones, D. L. & Gan, W. (2022). SALSA: spatial cue-augmented log-spectrogram features for polyphonic sound event localization and detection. IEEE/ACM Transactions On Audio, Speech, and Language Processing, 30, 1749-1762. https://dx.doi.org/10.1109/TASLP.2022.3173054||Project:||MOE2017-T2-2-060
|Journal:||IEEE/ACM Transactions on Audio, Speech, and Language Processing||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 Spatial cue-Augmented Log-SpectrogrAm (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 TAUNIGENS 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 6 % 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 16 % and 7 %, respectively, compared to using multichannel logmel spectrograms with generalized cross-correlation spectra.||URI:||https://hdl.handle.net/10356/157118||ISSN:||2329-9290||DOI:||10.1109/TASLP.2022.3173054||Rights:||© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TASLP.2022.3173054.||Fulltext Permission:||open||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Journal Articles|
Files in This Item:
|TASLP2021_SALSA__Spatial_cue_augmented_log_spectrogram_feature_for_polyphonic_sound_event_localization_and_detection.pdf||3.46 MB||Adobe PDF||View/Open|
Updated on Aug 12, 2022
Updated on Aug 12, 2022
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.