High-Quality voice model for STatistical parametric speech Synthesis

Objective

A speech analysis/synthesis method aims at representing a speech waveform, produced by a person speaking, as a time sequence of parameters. Based on this time sequence, the speech waveform can be resynthesized. The analysis/synthesis methods are cornerstones for many speech technologies (e.g. text-to-speech, telecommunications, voice restoration). For the majority of applications, these methods need to have two key properties: (i) a high perceived quality of the speech sound, and, (ii) a statistical characterization of the parameters' sequence necessary for statistical approaches, which have attracted great interest during the last decades in speech technologies. The current analysis/synthesis methods that provide a statistical characterization exhibit however a lack of perceived quality. This issue does not pose a problem in applications designed for noisy environments (e.g. navigation devices, smart-phone applications, announcements in train stations). On the contrary, it prohibits the use of statistical approaches in quiet environments, e.g. in the music, cinema and video game industries, where the listener is fully aware of all the details of the sound. This problem is mainly due to the lack of an accurate representation of the phase information and its correlation with the amplitude information. Indeed, recent phase processing tools allowed the description of the phase spectrum properties in a way that shows the drawbacks and limits of current analysis/synthesis methods. Additionally, these same tools are also promising means for modeling the phase information, which is paramount for good quality. The primary goal of the HQSTS project is to create a high-quality analysis/synthesis method that will broaden the applications of statistical approaches of speech technologies in quiet environments, where a high-quality is an absolute necessity.

Fields of science

• engineering and technology › electrical engineering, electronic engineering, information engineering › information engineering › telecommunications
• natural sciences › computer and information sciences › software › software applications › video games
• humanities › languages and literature › linguistics › phonetics

Programme(s)

• H2020-EU.1.3.2. - Nurturing excellence by means of cross-border and cross-sector mobility

Topic(s)

• MSCA-IF-2014-EF - Marie Skłodowska-Curie Individual Fellowships (IF-EF)

Call for proposal

H2020-MSCA-IF-2014
See other projects for this call

Funding Scheme

MSCA-IF-EF-ST - Standard EF

Coordinator

THE CHANCELLOR MASTERS AND SCHOLARS OF THE UNIVERSITY OF CAMBRIDGE

Address

Trinity Lane The Old Schools
CB2 1TN Cambridge
United Kingdom

Activity type

Higher or Secondary Education Establishments

EU contribution

€ 183 454,80