Learning Transposition-Invariant Interval Features from Symbolic Music and Audio

06/21/2018
by   Stefan Lattner, et al.
0

Many music theoretical constructs (such as scale types, modes, cadences, and chord types) are defined in terms of pitch intervals---relative distances between pitches. Therefore, when computer models are employed in music tasks, it can be useful to operate on interval representations rather than on the raw musical surface. Moreover, interval representations are transposition-invariant, valuable for tasks like audio alignment, cover song detection and music structure analysis. We employ a gated autoencoder to learn fixed-length, invertible and transposition-invariant interval representations from polyphonic music in the symbolic domain and in audio. An unsupervised training method is proposed yielding an organization of intervals in the representation space which is musically plausible. Based on the representations, a transposition-invariant self-similarity matrix is constructed and used to determine repeated sections in symbolic music and in audio, yielding competitive results in the MIREX task "Discovery of Repeated Themes and Sections".

READ FULL TEXT

page 4

page 5

research
07/19/2018

Audio-to-Score Alignment using Transposition-invariant Features

Audio-to-score alignment is an important pre-processing step for in-dept...
research
07/13/2019

Learning Complex Basis Functions for Invariant Representations of Audio

Learning features from data has shown to be more successful than using h...
research
01/06/2020

Modeling Musical Structure with Artificial Neural Networks

In recent years, artificial neural networks (ANNs) have become a univers...
research
02/22/2020

DECIBEL: Improving Audio Chord Estimation for Popular Music by Alignment and Integration of Crowd-Sourced Symbolic Representations

Automatic Chord Estimation (ACE) is a fundamental task in Music Informat...
research
11/15/2022

SSM-Net: feature learning for Music Structure Analysis using a Self-Similarity-Matrix based loss

In this paper, we propose a new paradigm to learn audio features for Mus...
research
06/22/2018

A Predictive Model for Music Based on Learned Interval Representations

Connectionist sequence models (e.g., RNNs) applied to musical sequences ...
research
10/31/2022

Self-Supervised Hierarchical Metrical Structure Modeling

We propose a novel method to model hierarchical metrical structures for ...

Please sign up or login with your details

Forgot password? Click here to reset