{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/salsa-spatial-cue-augmented-log-spectrogram","title":"SALSA: Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detection","arxiv_id":"2110.00275","date":"2021-10-01","proceeding":null,"authors":["Thi Ngoc Tho Nguyen","Karn N. Watcharasupat","Ngoc Khanh Nguyen","Douglas L. Jones","Woon-Seng Gan"],"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 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 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 log-mel spectrograms with generalized cross-correlation spectra.","url_abs":"https://arxiv.org/abs/2110.00275v3","url_pdf":"https://arxiv.org/pdf/2110.00275v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"salsa-spatial-cue-augmented-log-spectrogram","repo_url":"https://github.com/thomeou/SALSA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"direction-of-arrival-estimation","task_name":"Direction of Arrival Estimation"},{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"sound-event-detection","task_name":"Sound Event Detection"},{"task_slug":"sound-event-localization-and-detection","task_name":"Sound Event Localization and Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sound-event-localization-and-detection-on-tau-1","task":"Sound Event Localization and Detection","dataset":"TAU-NIGENS Spatial Sound Events 2021","model":"SALSA-FOA","rank_in_archive_order":1,"of":1,"metrics":{"ER≤20°":"0.376","F1≤20°":"0.744","LE-CD":"11.1","LR-CD":"0.722"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.00275","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}