Abstract
Text-to-speech (TTS) synthesis systems have been widely used in general-purpose applications based on the generation of speech. Nonetheless, there are some domains, such as storytelling or voice output aid devices, which may also require singing. To enable a corpus-based TTS system to sing, a supplementary singing database should be recorded. This solution, however, might be too costly for eventual singing needs, or even unfeasible if the original speaker is unavailable or unable to sing properly. This work introduces a unit selection-based text-to-speech-and-singing (US-TTS&S) synthesis framework, which integrates speech-to-singing (STS) conversion to enable the generation of both speech and singing from an input text and a score, respectively, using the same neutral speech corpus. The viability of the proposal is evaluated considering three vocal ranges and two tempos on a proof-of-concept implementation using a 2.6-h Spanish neutral speech corpus. The experiments show that challenging STS transformation factors are required to sing beyond the corpus vocal range and/or with notes longer than 150 ms. While score-driven US configurations allow the reduction of pitch-scale factors, time-scale factors are not reduced due to the short length of the spoken vowels. Moreover, in the MUSHRA test, text-driven and score-driven US configurations obtain similar naturalness rates of around 40 for all the analysed scenarios. Although these naturalness scores are far from those of vocaloid, the singing scores of around 60 which were obtained validate that the framework could reasonably address eventual singing needs.
Highlights
Text-to-speech (TTS) synthesis systems have been widely used to generate speech in several general-purpose applications, such as call-centre automation, reading emails or news, or providing travel directions, among others [1]
It is worth mentioning that early works on speech synthesis already enabled the generation of both speech and singing, as they stood on a sourcefilter model inspired by the classical acoustic theory of voice production [1]
The speech synthesis investigations moved to corpus-based approaches, deploying TTS systems based on unit selection (US), hidden Markov models (HMM) or hybrid approaches, and more
Summary
Text-to-speech (TTS) synthesis systems have been widely used to generate speech in several general-purpose applications, such as call-centre automation, reading emails or news, or providing travel directions, among others [1]. A TTS with singing capabilities could be useful in assistive technologies, where the incorporation of songs has been proved to be an effective form of improving the. In this sense, it is worth mentioning that early works on speech synthesis already enabled the generation of both speech and singing (e.g. see [8]), as they stood on a sourcefilter model inspired by the classical acoustic theory of voice production [1]. Some approaches used diphonebased TTS systems to generate singing [9, 10], most works opted to use databases recorded for singing purposes [11,12,13]. The speech synthesis investigations moved to corpus-based approaches, deploying TTS systems based on unit selection (US), hidden Markov models (HMM) or hybrid approaches, and more
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: EURASIP Journal on Audio, Speech, and Music Processing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
