Learning Audio-Sheet Music Correspondences for Cross-Modal Retrieval and Piece Identification

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F18%3A10390078" target="_blank" >RIV/00216208:11320/18:10390078 - isvavai.cz</a>

Výsledek na webu

<a href="https://transactions.ismir.net/articles/10.5334/tismir.12/#" target="_blank" >https://transactions.ismir.net/articles/10.5334/tismir.12/#</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5334/tismir.12" target="_blank" >10.5334/tismir.12</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Learning Audio-Sheet Music Correspondences for Cross-Modal Retrieval and Piece Identification

Popis výsledku v původním jazyce

This work addresses the problem of matching musical audio directly to sheet music, without any higher-level abstract representation. We propose a method that learns joint embedding spaces for short excerpts of audio and their respective counterparts in sheet music images, using multimodal convolutional neural networks. Given the learned representations, we show how to utilize them for two sheet-music-related tasks: (1) piece/score identification from audio queries and (2) retrieving relevant performances given a score as a search query. All retrieval models are trained and evaluated on a new, large scale multimodal audio-sheet music dataset which is made publicly available along with this article. The dataset comprises 479 precisely annotated solo piano pieces by 53 composers, for a total of 1,129 pages of music and about 15 hours of aligned audio, which was synthesized from these scores. Going beyond this synthetic training data, we carry out first retrieval experiments using scans of real sheet musi

Název v anglickém jazyce

Learning Audio-Sheet Music Correspondences for Cross-Modal Retrieval and Piece Identification

Popis výsledku anglicky

This work addresses the problem of matching musical audio directly to sheet music, without any higher-level abstract representation. We propose a method that learns joint embedding spaces for short excerpts of audio and their respective counterparts in sheet music images, using multimodal convolutional neural networks. Given the learned representations, we show how to utilize them for two sheet-music-related tasks: (1) piece/score identification from audio queries and (2) retrieving relevant performances given a score as a search query. All retrieval models are trained and evaluated on a new, large scale multimodal audio-sheet music dataset which is made publicly available along with this article. The dataset comprises 479 precisely annotated solo piano pieces by 53 composers, for a total of 1,129 pages of music and about 15 hours of aligned audio, which was synthesized from these scores. Going beyond this synthetic training data, we carry out first retrieval experiments using scans of real sheet musi

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/GBP103%2F12%2FG084" target="_blank" >GBP103/12/G084: Centrum pro multi-modální interpretaci dat velkého rozsahu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název periodika

Transactions of the International Society for Music Information Retrieval

ISSN

2514-3298

e-ISSN

—

Svazek periodika

1

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

CA - Kanada

Počet stran výsledku

12

Strana od-do

22-33

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—