NUS-HLT Spoken Lyrics and Singing (SLS) Corpus

Abstract

Despite speech-to-singing (STS) voice conversion has been widely studied, a large database for this task has not been constructed yet. We present a new Spoken Lyrics and Singing (SLS) corpus developed at NUS-HLT that can be useful for STS. In this work, the details of this database is reported that contains 3,058 utterances of 90 English songs from 10 professional singers collected in a recording studio environment. The spoken lyrics corresponding to the songs are also recorded from the singers to create the database, which we refer to as NUS-HLT SLS corpus. A comparison of spoken lyrics and singing speech from different speakers and the challenges associated with STS are discussed. We then highlight a few potential applications where this corpus can be used for future studies.