Learning a Joint Embedding Space of Monophonic and Mixed Music Signals for Singing Voice

Previous approaches in singer identification have used one of monophonic vocal tracks or mixed tracks containing multiple instruments, leaving a semantic gap between these two domains of audio. In this paper, we present a system to learn a joint embedding space of monophonic and mixed tracks for sin...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Lee, Kyungyun, Nam, Juhan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 26.06.2019
Subjects
Domains
Embedded systems
Embedding
Learning
Music
Musical performances
Musicians & conductors
Singers
Singing
Online AccessGet full text

Cover

More Information
Summary:Previous approaches in singer identification have used one of monophonic vocal tracks or mixed tracks containing multiple instruments, leaving a semantic gap between these two domains of audio. In this paper, we present a system to learn a joint embedding space of monophonic and mixed tracks for singing voice. We use a metric learning method, which ensures that tracks from both domains of the same singer are mapped closer to each other than those of different singers. We train the system on a large synthetic dataset generated by music mashup to reflect real-world music recordings. Our approach opens up new possibilities for cross-domain tasks, e.g., given a monophonic track of a singer as a query, retrieving mixed tracks sung by the same singer from the database. Also, it requires no additional vocal enhancement steps such as source separation. We show the effectiveness of our system for singer identification and query-by-singer in both the same-domain and cross-domain tasks.
ISSN:2331-8422