Paragraph prosodic patterns to enhance text-to-speech naturalness

Peiró Lilja, Àlex; Farrús, Mireia

doi:http://dx.doi.org/10.21437/SpeechProsody.2018-124

Paragraph prosodic patterns to enhance text-to-speech naturalness

Citation

Peiró-Lilja A, Farrús M. Paragraph prosodic patterns to enhance text-to-speech naturalness. In: Klessa K, Bachan J, Wagner A, Karpiński M, Śledziński D. Proceedings of the 9th International Conference on Speech Prosody; 2018 June 13-16; Poznań, Poland. [Lous Tourils]: ISCA; 2018. p. 512-6. DOI: 10.21437/SpeechProsody.2018-124

Abstract

Speech synthesis has reached a reasonable high quality in recent years. However, there is still room for improvement in terms of naturalness and expressiveness when dealing with large multisentential discourse, since most text-to-speech synthesizers do not fully take into account the prosodic differences that have been observed in discourse units such as paragraphs. This work presents an implementation of paragraph-based prosodic patterns into the open-source MARYTTS platform, enriching its prosody output by means of intra- and inter-paragraph prosodic features. The set of characteristics include pitch decay, pitch range and speech rate variation (as intra-paragraph features), as well as paragraph break pauses and speech rate variation (as inter-paragraph features), previously analyzed in a large set of TED Talks and read-speech sections of the Spoken Wikipedia Corpus. The perception tests, performed both in English and German parametric voices, suggest that paragraph-based features should be further studied and taken into account on future implementations to synthesize large discourse speech.