Identifying Cover Songs Using Information-Theoretic Measures of Similarity

Abstract

This paper investigates methods for quantifying similarity between audio signals, specifically for the task of of cover song detection. We consider an information-theoretic approach, where we compute pairwise measures of predictability between time series. We compare discrete-valued approaches operating on quantised audio features, to continuous-valued approaches. In the discrete case, we propose a method for computing the normalised compression distance, where we account for correlation between time series. In the continuous case, we propose to compute information-based measures of similarity as statistics of the prediction error between time series. We evaluate our methods on two cover song identification tasks using a data set comprised of 300 Jazz standards and using the Million Song Dataset. For both datasets, we observe that continuous-valued approaches outperform discrete-valued approaches. We consider approaches to estimating the normalised compression distance (NCD) based on string compression and prediction, where we observe that our proposed normalised compression distance with alignment (NCDA) improves average performance over NCD, for sequential compression algorithms. Finally, we demonstrate that continuousvalued distances may be combined to improve performance with respect to baseline approaches. Using a large-scale filter-andrefine approach, we demonstrate state-of-the-art performance for cover song identification using the Million Song Dataset.

Music fingerprinting based on bhattacharya distance for song and cover song recognition

“…The testing data used were 30 seconds of randomly cut training data. The accuracy of the song recognition method was calculated using (11). 11Where TRUE is the total of valid predictions and DATA is the total number of testing data.…”

“…This chroma can be used to recognize a cover song with 62% accuracy [5]- [7]. Other experiments used pitch [8]- [10], Information-Theoretic Measures of Similarity [11], music structure segmentation [12] and 2D Fourier Transform [13] to recognize cover songs. In a previous experiment, fingerprinting has been used to identify the title of a song based on the raw signal of the music.…”

Evaluation of Chord and Chroma Features and Dynamic Time Warping Scores on Cover Song Identification Task

“…The most recent trend in CSI is to pioneer new ways of feature extraction (2D Fourier Transform Magnitude [4], usage of MFCC [24]), new similarity measures (Shannon information [10]), or database pruning and combining various features based on machine learning [19]). The focus is shifting to the large-scale methods rather than outperforming the results on the smaller benchmarking datasets.…”

Effective and Fast Near Duplicate Detection via Signature-Based Compression Metrics

“…Kolmogorov complexity-based similarity metric has been used in several domains involving image [30], audio [31], and time series [32]. A dictionary-based compression dissimilarity measure was proposed for multitask clustering [33].…”