DeepAI AI Chat
Log In Sign Up

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

by   Axel Marmoret, et al.

The ability of deep neural networks to learn complex data relations and representations is established nowadays, but it generally relies on large sets of training data. This work explores a "piece-specific" autoencoding scheme, in which a low-dimensional autoencoder is trained to learn a latent/compressed representation specific to a given song, which can then be used to infer the song structure. Such a model does not rely on supervision nor annotations, which are well-known to be tedious to collect and often ambiguous in Music Structure Analysis. We report that the proposed unsupervised auto-encoding scheme achieves the level of performance of supervised state-of-the-art methods with 3 seconds tolerance when using a Log Mel spectrogram representation on the RWC-Pop dataset.


page 3

page 4


Barwise Compression Schemes for Audio-Based Music Structure Analysis

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

DLR : Toward a deep learned rhythmic representation for music content analysis

In the use of deep neural networks, it is crucial to provide appropriate...

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

Music Structure Analysis (MSA) consists of representing a song in sectio...

Large-Scale MIDI-based Composer Classification

Music classification is a task to classify a music piece into labels suc...

Deep Music Analogy Via Latent Representation Disentanglement

Analogy is a key solution to automated music generation, featured by its...

Invariances and Data Augmentation for Supervised Music Transcription

This paper explores a variety of models for frame-based music transcript...

Genre-Agnostic Key Classification With Convolutional Neural Networks

We propose modifications to the model structure and training procedure t...