Dec 1, 2020 · The audio recordings in the NHSS database correspond to 100 songs sung and spoken by 10 singers, resulting in a total of 7 hours of audio data.

We present a database of parallel recordings of speech and singing, collected and released by the Human Language Technology (HLT) laboratory at the National ...

The NHSS database features English pop songs with parallel speech and singing audio, which is useful in the investigation of the properties of the vocal-tract ...

In this work, we particularly focus on template-based speech-to-singing conversion, where we keep the prosody same as that of the reference singing. We perform ...

The NHSS database consists of 100 songs from 10 professional singers, each of them singing and speaking 10 songs. The database provides 4.75 h of sung and 2.25 ...

Oct 1, 2021 · We present a database of parallel recordings of speech and singing, collected and released by the Human Language Technology (HLT) laboratory ...

This chapter describes various aspects of the human voice as a means of communication in speech and singing, including lung volume ranges, subglottal pressures.

Aug 25, 2021 · We present a database of parallel recordings of speech and singing, collected and released by the Human Language Technology (HLT) laboratory ...

NHSS: A speech and singing parallel database. https://doi.org/10.1016/j.specom.2021.07.002 ·. Journal: Speech Communication, 2021, p. 9-22. Publisher: Elsevier ...

Dec 1, 2020 · We develop benchmark systems for speech-to-singing alignment, spectral mapping and conversion using the NHSS database.