DeepAI AI Chat
Log In Sign Up

Convolutive Block-Matching Segmentation Algorithm with Application to Music Structure Analysis

by   Axel Marmoret, et al.

Music Structure Analysis (MSA) consists of representing a song in sections (such as “chorus”, “verse”, “solo” etc), and can be seen as the retrieval of a simplified organization of the song. This work presents a new algorithm, called Convolutive Block-Matching (CBM) algorithm, devoted to MSA. In particular, the CBM algorithm is a dynamic programming algorithm, applying on autosimilarity matrices, a standard tool in MSA. In this work, autosimilarity matrices are computed from the feature representation of an audio signal, and time is sampled on the barscale. We study three different similarity functions for the computation of autosimilarity matrices. We report that the proposed algorithm achieves a level of performance competitive to that of supervised state-of-the-art methods on 3 among 4 metrics, while being fully unsupervised.


page 2

page 3


Barwise Compression Schemes for Audio-Based Music Structure Analysis

Music Structure Analysis (MSA) consists in segmenting a music piece in s...

Exploring single-song autoencoding schemes for audio-based music structure analysis

The ability of deep neural networks to learn complex data relations and ...

Towards Linking the Lakh and IMSLP Datasets

This paper investigates the problem of matching a MIDI file against a la...

Similarity graphs for the concealment of long duration data loss in music

We present a novel method for the compensation of long duration data gap...

MIDI Passage Retrieval Using Cell Phone Pictures of Sheet Music

This paper investigates a cross-modal retrieval problem in which a user ...

Meta-Model Structure Selection: Building Polynomial NARX Model for Regression and Classification

This work presents a new meta-heuristic approach to select the structure...

Detecting Generic Music Features with Single Layer Feedforward Network using Unsupervised Hebbian Computation

With the ever-increasing number of digital music and vast music track fe...