A Flexible Front-End for HTS

Matthew Aylett, Rasmus Dall, Arnab Ghoshal, Gustav Eje Henter, Thomas Merritt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Parametric speech synthesis techniques depend on full context acoustic models generated by language front-ends, which analyse linguistic and phonetic structure. HTS, the leading parametric synthesis system, can use a number of different front-ends to generate full context models for synthesis and training. In this paper we explore the use of a new text processing front-end that has been added to the speech recognition toolkit Kaldi as part of an ongoing project to produce a new parametric speech synthesis system, Idlak. The use of XML specification files, a modular design, and modern coding and testing approaches, make the Idlak front-end ideal for adding, altering and experimenting with the contexts used in full context acoustic models. The Idlak front-end was evaluated against the standard Festival front-end in the HTS system. Results from the Idlak front-end compare well with the more mature Festival front-end (Idlak - 2.83 MOS vs Festival - 2.85 MOS), although a slight reduction in naturalness perceived by non-native English speakers can be attributed to Festival's insertion of non-punctuated pauses.
Original languageEnglish
Title of host publicationINTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association
PublisherInternational Speech Communication Association
Pages1283-1287
Number of pages5
Publication statusPublished - 2014

Fingerprint

Dive into the research topics of 'A Flexible Front-End for HTS'. Together they form a unique fingerprint.
  • Natural Speech Technology

    Renals, S. & King, S.

    EPSRC

    1/05/1131/07/16

    Project: Research

Cite this