Measuring the Perceptual Effects of Modelling Assumptions in Speech Synthesis Using Stimuli Constructed from Repeated Natural Speech

Gustav Eje Henter, Thomas Merritt, Matt Shannon, Catherine Mayo, Simon King

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

Abstract

Acoustic models used for statistical parametric speech synthesis typically incorporate many modelling assumptions. It is an open question to what extent these assumptions limit the naturalness of synthesised speech. To investigate this question, we recorded a speech corpus where each prompt was read aloud multiple times. By combining speech parameter trajectories extracted from different repetitions, we were able to quantify the perceptual effects of certain commonly used modelling assumptions. Subjective listening tests show that taking the source and filter parameters to be conditionally independent, or using diagonal covariance matrices, significantly limits the naturalness that can be achieved. Our experimental results also demonstrate the shortcomings of mean-based parameter generation.
Original languageEnglish
Title of host publicationINTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association
PublisherInternational Speech Communication Association
Pages1504-1508
Number of pages5
Publication statusPublished - 2014

Fingerprint

Dive into the research topics of 'Measuring the Perceptual Effects of Modelling Assumptions in Speech Synthesis Using Stimuli Constructed from Repeated Natural Speech'. Together they form a unique fingerprint.

Cite this