Wavelet-Based Time-Frequency Fingerprinting for Feature Extraction of Traditional Irish Music

TL;DR

This paper introduces a wavelet-based time-frequency fingerprinting method for identifying traditional Irish tunes from live recordings, demonstrating high accuracy and efficiency in audio identification and potential applications in other time series domains.

Contribution

The study presents a novel wavelet-based approach for feature extraction and comparison in audio identification, leveraging wavelet coherence and synthetic tune generation from ABC notation.

Findings

Accurate identification of Irish tunes from recordings.

Wavelet coherence outperforms other spectral analysis methods.

Method applicable to EEG and financial time series analysis.

Abstract

This work presents a wavelet-based approach to time-frequency fingerprinting for time series feature extraction, with a focus on audio identification from live recordings of traditional Irish tunes. The challenges of identifying features in time-series data are addressed by employing a continuous wavelet transform to extract spectral features and wavelet coherence analysis is used to compare recorded audio spectrograms to synthetically generated tunes. The synthetic tunes are derived from ABC notation, which is a common symbolic representation for Irish music. Experimental results demonstrate that the wavelet-based method can accurately and efficiently identify recorded tunes. This research study also details the performance of the wavelet coherence model, highlighting its strengths over other methods of time-frequency decomposition. Additionally, we discuss and deploy the model on several applications beyond music, including in EEG signal analysis and financial time series forecasting.