钢琴复调转录的多任务学习:个案研究

2019 International Workshop on Multilayer Music Representation and Processing (MMRP) Pub Date : 2019-01-01 DOI:10.1109/MMRP.2019.8665372

Rainer Kelz, Sebastian Böck, G. Widmer

{"title":"钢琴复调转录的多任务学习:个案研究","authors":"Rainer Kelz, Sebastian Böck, G. Widmer","doi":"10.1109/MMRP.2019.8665372","DOIUrl":null,"url":null,"abstract":"Viewing polyphonic piano transcription as a multitask learning problem, where we need to simultaneously predict onsets, intermediate frames and offsets of notes, we investigate the performance impact of additional prediction targets, using a variety of suitable convolutional neural network architectures. We quantify performance differences of additional objectives on the larGe MAESTRO dataset.","PeriodicalId":441469,"journal":{"name":"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","volume":"351 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Multitask Learning for Polyphonic Piano Transcription, a Case Study\",\"authors\":\"Rainer Kelz, Sebastian Böck, G. Widmer\",\"doi\":\"10.1109/MMRP.2019.8665372\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Viewing polyphonic piano transcription as a multitask learning problem, where we need to simultaneously predict onsets, intermediate frames and offsets of notes, we investigate the performance impact of additional prediction targets, using a variety of suitable convolutional neural network architectures. We quantify performance differences of additional objectives on the larGe MAESTRO dataset.\",\"PeriodicalId\":441469,\"journal\":{\"name\":\"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)\",\"volume\":\"351 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/MMRP.2019.8665372\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 International Workshop on Multilayer Music Representation and Processing (MMRP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MMRP.2019.8665372","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 7

摘要

将复调钢琴转录视为一个多任务学习问题，我们需要同时预测音符的起始、中间帧和偏移，我们使用各种合适的卷积神经网络架构研究了额外的预测目标对性能的影响。我们量化了大型MAESTRO数据集上其他目标的性能差异。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Multitask Learning for Polyphonic Piano Transcription, a Case Study

Viewing polyphonic piano transcription as a multitask learning problem, where we need to simultaneously predict onsets, intermediate frames and offsets of notes, we investigate the performance impact of additional prediction targets, using a variety of suitable convolutional neural network architectures. We quantify performance differences of additional objectives on the larGe MAESTRO dataset.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2019 International Workshop on Multilayer Music Representation and Processing (MMRP)

自引率

0.00%

发文量