An Introduction to Signal Processing for Singing-Voice Analysis High notes in the effort to automate the understanding of vocals in music

被引:16
作者
Hmpuhrey, Eric J. [1 ,2 ]
Reddy, Sravana [3 ]
Seetharaman, Prem [4 ]
Kumar, Aparna [1 ]
Bittner, Rachel M. [1 ,5 ]
Demetriou, Andrew [6 ]
Gulati, Sankalp [7 ]
Jansson, Andreas [1 ,8 ,9 ]
Jehan, Tristan [3 ,8 ]
Lehner, Bernhard [10 ,11 ,12 ,13 ,14 ]
Kruspe, Anna [15 ,16 ,17 ,18 ]
Yang, Luwei [19 ]
机构
[1] NYU, Mus & Audio Res Lab, New York, NY 10003 USA
[2] Spotify, New York, NY 10011 USA
[3] Spotify, Boston, MA USA
[4] Northwestern Univ, Evanston, IL 60208 USA
[5] NASA, Ames Res Ctr, Adv Controls & Displays Lab, Washington, DC 20546 USA
[6] Delft Univ Technol, Multimedia Comp Grp, Delft, Netherlands
[7] Univ Pompeu Fabra, Mus Technol Grp, CompMus Project, Barcelona, Spain
[8] Echo Nest, Somerville, MA USA
[9] This My Jam, London, England
[10] Johannes Kepler Univ Linz, Linz, Austria
[11] Virginia Polytech Inst & State Univ, Blacksburg, VA 24061 USA
[12] Lenze, Uxbridge, MA USA
[13] Siemens, Munich, Germany
[14] Infineon, Neubiberg, Germany
[15] German Aerosp Ctr, Cologne, Germany
[16] Fraunhofer Inst Digital Media Technol, Ilmenau, Germany
[17] Johns Hopkins Univ, Baltimore, MD USA
[18] Natl Inst Adv Ind Sci & Technol, Tsukuba, Ibaraki, Japan
[19] Alibaba Grp, Hangzhou, Zhejiang, Peoples R China
关键词
PERFORMANCE;
D O I
10.1109/MSP.2018.2875133
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Humans have devised a vast array of musical instruments, but the most prevalent instrument remains the human voice. Thus, techniques for applying audio signal processing methods to the singing voice are receiving much attention as the world continues to move toward music-streaming services and as researchers seek to unlock the deep content understanding necessary to enable personalized listening experiences on a large scale. This article provides an introduction to the topic of singing-voice analysis. It surveys the foundations and state of the art in computational modeling across three main categories of singing: general vocalizations, the musical function of voice, and the singing of lyrics. We aim to establish a starting point for practitioners new to this field and frame near-field opportunities and challenges on the horizon. © 1991-2012 IEEE.
引用
收藏
页码:82 / 94
页数:13
相关论文
共 43 条
[1]  
[Anonymous], 2016, Proceedings of the 17th International Society for Music Information Retrieval Conference, DOI [DOI 10.5281/ZENODO.1418051, 10.5281/zenodo.1418051]
[2]  
[Anonymous], 2018, WIMP
[3]  
Balke S, 2017, INT CONF ACOUST SPEE, P196, DOI 10.1109/ICASSP.2017.7952145
[4]  
Bittner R. M., 2017, Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), P63, DOI DOI 10.5281/ZENODO.1417937
[5]   Synthesis of the singing voice by performance sampling and spectral models [J].
Bonada, Jordi ;
Serra, Xavier .
IEEE SIGNAL PROCESSING MAGAZINE, 2007, 24 (02) :67-79
[6]  
Chandrasekhar V, 2011, INT CONF ACOUST SPEE, P5724
[7]  
Demetriou A. M., 2018, ISMIR, P514
[8]  
Dixon S., 2015, P 16 C INT SOC MUS I
[9]  
Driedger J, 2015, INT CONF ACOUST SPEE, P126, DOI 10.1109/ICASSP.2015.7177945
[10]   Content-based retrieval of music and audio [J].
Foote, JT .
MULTIMEDIA STORAGE AND ARCHIVING SYSTEMS II, 1997, 3229 :138-147