Rethinking Evaluation Methodology for Audio-to-Score Alignment

09/30/2020
by   John Thickstun, et al.
0

This paper offers a precise, formal definition of an audio-to-score alignment. While the concept of an alignment is intuitively grasped, this precision affords us new insight into the evaluation of audio-to-score alignment algorithms. Motivated by these insights, we introduce new evaluation metrics for audio-to-score alignment. Using an alignment evaluation dataset derived from pairs of KernScores and MAESTRO performances, we study the behavior of our new metrics and the standard metrics on several classical alignment algorithms.

READ FULL TEXT
07/28/2020

A Hybrid Approach to Audio-to-Score Alignment

Audio-to-score alignment aims at generating an accurate mapping between ...
05/29/2019

A new definition of the distortion matrix for an audio-to-score alignment system

In this paper we present a new definition of the distortion matrix for a...
08/23/2022

Parameter Sensitivity of Deep-Feature based Evaluation Metrics for Audio Textures

Standard evaluation metrics such as the Inception score and Fréchet Audi...
02/16/2017

Evaluation of Trace Alignment Quality and its Application in Medical Process Mining

Trace alignment algorithms have been used in process mining for discover...
09/16/2017

Process-oriented Iterative Multiple Alignment for Medical Process Mining

Adapted from biological sequence alignment, trace alignment is a process...
10/12/2021

Are you doing what I say? On modalities alignment in ALFRED

ALFRED is a recently proposed benchmark that requires a model to complet...
04/19/2022

A Convolutional-Attentional Neural Framework for Structure-Aware Performance-Score Synchronization

Performance-score synchronization is an integral task in signal processi...

Code Repositories

alignment-eval

Dataset and evaluation pipeline for music-to-score alignment


view repo