Using Activation Functions for Improving Measure-Level Audio Synchronization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F22%3APU146440" target="_blank" >RIV/00216305:26220/22:PU146440 - isvavai.cz</a>

Výsledek na webu

<a href="https://ismir2022program.ismir.net/poster_195.html" target="_blank" >https://ismir2022program.ismir.net/poster_195.html</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Using Activation Functions for Improving Measure-Level Audio Synchronization

Popis výsledku v původním jazyce

Audio synchronization aims at aligning multiple recordings of the same piece of music. Traditional synchronization approaches are often based on dynamic time warping using chroma features as an input representation. Previous work has shown how one can integrate onset cues into this pipeline for improving the alignment’s temporal accuracy. Furthermore, recent work based on deep neural networks has led to significant improvements for learning onset, beat, and downbeat activation functions. However, for music with soft onsets and abrupt tempo changes, these functions may be unreliable, leading to unstable results. As the main contribution of this paper, we introduce a combined approach that integrates activation functions into the synchronization pipeline. We show that this approach improves the temporal accuracy thanks to the activation cues while inheriting the robustness of the traditional synchronization approach. Conducting experiments based on string quartet recordings, we evaluate our combined app

Název v anglickém jazyce

Using Activation Functions for Improving Measure-Level Audio Synchronization

Popis výsledku anglicky

Audio synchronization aims at aligning multiple recordings of the same piece of music. Traditional synchronization approaches are often based on dynamic time warping using chroma features as an input representation. Previous work has shown how one can integrate onset cues into this pipeline for improving the alignment’s temporal accuracy. Furthermore, recent work based on deep neural networks has led to significant improvements for learning onset, beat, and downbeat activation functions. However, for music with soft onsets and abrupt tempo changes, these functions may be unreliable, leading to unstable results. As the main contribution of this paper, we introduce a combined approach that integrates activation functions into the synchronization pipeline. We show that this approach improves the temporal accuracy thanks to the activation cues while inheriting the robustness of the traditional synchronization approach. Conducting experiments based on string quartet recordings, we evaluate our combined app

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

20203 - Telecommunications

Projekt

<a href="/cs/project/EF19_073%2F0016948" target="_blank" >EF19_073/0016948: Kvalitní interní granty VUT</a><br>

Návaznosti

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

Rok uplatnění

2022

Kód důvěrnosti údajů

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