NHSS: A Speech and Singing Parallel Database

TL;DR

This paper introduces the NHSS database, a comprehensive collection of parallel speech and singing recordings designed to facilitate research in voice conversion, synthesis, and comparative analysis of speech and singing attributes.

Contribution

The paper presents a new publicly available parallel speech and singing database with detailed annotations and benchmark systems for speech-to-singing conversion tasks.

Findings

Analysis of acoustic similarities and differences between speech and singing voices.

Development of benchmark systems for speech-to-singing alignment and spectral mapping.

Provision of a large, annotated dataset for research in voice conversion and synthesis.

Abstract

We present a database of parallel recordings of speech and singing, collected and released by the Human Language Technology (HLT) laboratory at the National University of Singapore (NUS), that is called NUS-HLT Speak-Sing (NHSS) database. We release this database to the public to support research activities, that include, but not limited to comparative studies of acoustic attributes of speech and singing signals, cooperative synthesis of speech and singing voices, and speech-to-singing conversion. This database consists of recordings of sung vocals of English pop songs, the spoken counterpart of lyrics of the songs read by the singers in their natural reading manner, and manually prepared utterance-level and word-level annotations. 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. There are 5 male and 5 female singers, singing and reading the lyrics of 10 songs each. In this paper, we discuss the design methodology of the database, analyse the similarities and dissimilarities in characteristics of speech and singing voices, and provide some strategies to address relationships between these characteristics for converting one to another. We develop benchmark systems, which can be used as reference for speech-to-singing alignment, spectral mapping, and conversion using the NHSS database.