How reliable are posterior class probabilities in automatic music classification?

Author:

Lukashevich Hanna1ORCID,Grollmisch Sascha1ORCID,Abeßer Jakob1ORCID,Stober Sebastian2ORCID,Bös Joachim3ORCID

Affiliation:

1. Fraunhofer Institute for Digital Media Technology IDMT, Germany

2. Otto-von-Guericke-University Magdeburg, Germany

3. Fraunhofer Institute for Digital Media Technology IDMT, Germany and Industrial Applications of Media Technology IAM group, Technische Universität Ilmenau, Germany

Funder

German Research Foundation

H2020 EU project AI4Media

Publisher

ACM

Reference17 articles.

1. Look, Listen, and Learn More: Design Choices for Deep Audio Embeddings

2. Michaël Defferrard , Kirell Benzi , Pierre Vandergheynst , and Xavier Bresson . 2017 . FMA: A dataset for music analysis . In Proc. of the 18th International Society for Music Information Retrieval Conference. Michaël Defferrard, Kirell Benzi, Pierre Vandergheynst, and Xavier Bresson. 2017. FMA: A dataset for music analysis. In Proc. of the 18th International Society for Music Information Retrieval Conference.

3. Classifier conditional posterior probabilities

4. Jesse Engel , Cinjon Resnick , Adam Roberts , Sander Dieleman , Mohammad Norouzi , Douglas Eck , and Karen Simonyan . 2017 . Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders . In Proceedings of the International Conference on Machine Learning (ICML) . Sydney, Australia, 1068–1077. Jesse Engel, Cinjon Resnick, Adam Roberts, Sander Dieleman, Mohammad Norouzi, Douglas Eck, and Karen Simonyan. 2017. Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders. In Proceedings of the International Conference on Machine Learning (ICML). Sydney, Australia, 1068–1077.

5. Yarin Gal and Zoubin Ghahramani . 2016 . Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning . In Proc. of International conference on machine learning (ICML) ( New York, NY, USA). 1050–1059. Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In Proc. of International conference on machine learning (ICML) (New York, NY, USA). 1050–1059.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3