arrow
返回

Identifying Missing and Extra Notes in Piano Recordings Using Score-Informed Dictionary Learning

delete2017-10-01
delete8
delete
OA
AI
S
Siying Wang *
S
Sebastian Ewert
S
Simon Dixon
DOI:10.1109/TASLP.2017.2724203delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
The goal of automatic music transcription (AMT) is to obtain a high-level symbolic representation of the notes played in a given audio recording. Despite being researched for several decades, current methods are still inadequate for many applications. To boost the accuracy in a music tutoring scenario, we exploit that the score to be played is specified and we only need to detect the differences to the actual performance. In contrast to previous work that uses score information for postprocessing, we employ the score to construct a transcription method that is tailored to the given audio recording. By adapting a score-informed dictionary learning technique as used for source separation, we learn for each score pitch a spectral pattern describing the energy distribution of associated notes in the recording. In this paper, we identify several systematic weaknesses in our previous approach and introduce three extensions to improve its performance. First, we extend our dictionary of spectral templates to a dictionary of variable-length spectrotemporal patterns. Second, we integrate the score information using soft rather than hard constraints, to better take into account that differences from the score indeed occur. Third, we introduce new regularizers to guide the learning process. Our experiments show that these extensions particularly improve the accuracy for identifying extra notes, while the accuracy for correct and missing notes remains at a similar level. The influence of each extension is demonstrated with further experiments.
Keyword:
Music transcription
music tutoring
nonnegative matrix factorization
score-informed dictionary learning
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

I
IEEE-ACM Transactions on Audio Speech and Language Processing
IF:
5.1
论文数:
2.6K
被引数:
1.1W

机构

U
university of london
学者数:
21.5W
论文数: 19.7W
被引数: 305
引用论文

引用论文

Potential ecological and socio-economic effects of a novel megaherbivore introduction: the hippopotamus in Colombia
errOryx
IF0
err2019-12-20
err0
errOAAI
errAmanda L. Subalusky; Elizabeth P. Anderson; Germán Jiménez; David M. Post; David Echeverri Lopez; Sebastián García-R.; Laura J. Nova León; Juan F. Reátiga Parrish; Ana Rojas; Sergio Solari; Luz F. Jiménez-Segura
err分享
err收藏
Correlative evidence for peroxidase involvement in disease resistance against Alternaria leaf blight of tomato
err2010-05-09
err0
PREAI
errAmjad Hameed; Khalid Pervaiz Akhtar; Muhammad Yussouf Saleem; Muhammad Asghar
err分享
err收藏
err分享
err收藏
学者 查看更多内容