Time-Frequency Audio Similarity Using Optimal Transport

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2025-04-04

Major/Subject

Mcode

Degree programme

Language

en

Pages

4

Series

2024 58th Asilomar Conference on Signals, Systems, and Computers, pp. 1414-1417, Asilomar Conference on Signals, Systems, and Computers

Abstract

In audio signal processing, having an effective metric for comparing audio data is essential to ensure an accurate understanding of sound properties and attributes. In this work, we formulate two novel approaches for measuring the similarity between audio signals in the time-frequency domain, taking advantage of principles from classical optimal transport problems and sliced Wasserstein distances. Using optimal transport to construct the metric allows for a more robust signal content comparison, considering not only the signals' individual elements but also the global distribution in the signal space. Additionally, the sliced Wasserstein methods expand the use of the distances to high dimensional problems. By integrating both time and frequency aspects into our metrics, we aim for a more comprehensive comparison that can better handle various types of signal distortions. Results show promising behavior in accurately measuring distances for increasing signal differences and avoiding the presence of local minima in the loss curves.

Description

Keywords

Costs, Distortion, Distortion measurement, Loss measurement, MIMICs, Machine listening, Market research, Optimization, Spectrogram, Time-frequency analysis, similarity measure, optimal transport, optimization, audio-to-audio distance, Wasserstein distance

Other note

Citation

Fabiani, L, Schlecht, S J & Elvander, F 2025, Time-Frequency Audio Similarity Using Optimal Transport . in M B Matthews (ed.), 2024 58th Asilomar Conference on Signals, Systems, and Computers ., 10943074, Asilomar Conference on Signals, Systems, and Computers, IEEE, pp. 1414-1417, Asilomar Conference on Signals, Systems and Computers, Pacific Grove, California, United States, 27/10/2024 . https://doi.org/10.1109/IEEECONF60004.2024.10943074