Symbol Generation via Autoencoders for Handwritten Music Synthesis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475731" target="_blank" >RIV/00216208:11320/23:10475731 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Symbol Generation via Autoencoders for Handwritten Music Synthesis

Popis výsledku v původním jazyce

Optical Music Recognition is one of the fields where synthetic data is effectively utilized for training deep learning recognition models. Due to the lack of manually annotated data, the training data is generated by an automatic procedure which produces real-looking images of music scores in large quantities. Mashcima, a system for synthesizing training data for handwritten music recognition, generates complete music scores but the individual symbols are not synthetic, they are sampled from real symbol datasets. In this paper, we explore the impact of utilizing an adversarial autoencoder within the symbol synthesis pipeline. We show that in some cases the use of an autoencoder may not only be motivated by the creation of latent-space symbol embeddings but also by improved recognition accuracy.

Název v anglickém jazyce

Symbol Generation via Autoencoders for Handwritten Music Synthesis

Popis výsledku anglicky

Optical Music Recognition is one of the fields where synthetic data is effectively utilized for training deep learning recognition models. Due to the lack of manually annotated data, the training data is generated by an automatic procedure which produces real-looking images of music scores in large quantities. Mashcima, a system for synthesizing training data for handwritten music recognition, generates complete music scores but the individual symbols are not synthetic, they are sampled from real symbol datasets. In this paper, we explore the impact of utilizing an adversarial autoencoder within the symbol synthesis pipeline. We show that in some cases the use of an autoencoder may not only be motivated by the creation of latent-space symbol embeddings but also by improved recognition accuracy.

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů