#	Pagina
attuale pagina	/open-h2020/projects/195167/index.html

Opendata, web and dolomites

HQSTS

High-Quality voice model for STatistical parametric speech Synthesis

Total Cost €

EC-Contrib. €

Partnership

Views

Outcomes and
results

HQSTS project word cloud

Explore the words cloud of the HQSTS project. It provides you a very rough idea of what is the project "HQSTS" about.

good resynthesized time spectrum contrary voice majority speaking technologies waveform shows tools telecommunications paramount phone designed mainly limits lack navigation characterization exhibit hqsts person broaden sequence create speech noisy primary accurate quality music cinema issue listener correlation stations video drawbacks environments statistical game industries announcements pose smart perceived train modeling sound additionally details representing allowed absolute description cornerstones synthesis decades last attracted amplitude representation quiet restoration prohibits

Project "HQSTS" data sheet

The following table provides information about the project.

Coordinator	THE CHANCELLOR MASTERS AND SCHOLARSOF THE UNIVERSITY OF CAMBRIDGE Organization address address: TRINITY LANE THE OLD SCHOOLS city: CAMBRIDGE postcode: CB2 1TN website: www.cam.ac.uk contact info title: n.a. name: n.a. surname: n.a. function: n.a. email: n.a. telephone: n.a. fax: n.a.
Coordinator Country	United Kingdom [UK]
Project website	http://gillesdegottex.eu/Demos/HQSTS/
Total cost	183˙454 €
EC max contribution	183˙454 € (100%)
Programme	1. H2020-EU.1.3.2. (Nurturing excellence by means of cross-border and cross-sector mobility)
Code Call	H2020-MSCA-IF-2014
Funding Scheme	MSCA-IF-EF-ST
Starting year	2015
Duration (year-month-day)	from 2015-10-01 to 2017-12-31

Partnership

Take a look of project's partnership.

#	participants	country	role	EC contrib. [€]
1	THE CHANCELLOR MASTERS AND SCHOLARSOF THE UNIVERSITY OF CAMBRIDGE THE CHANCELLOR MASTERS AND SCHOLARSOF THE UNIVERSITY OF CAMBRIDGE Organization address address: TRINITY LANE THE OLD SCHOOLS city: CAMBRIDGE postcode: CB2 1TN website: www.cam.ac.uk contact info title: n.a. name: n.a. surname: n.a. function: n.a. email: n.a. telephone: n.a. fax: n.a.	UK (CAMBRIDGE)	coordinator	183˙454.00

Map

Project 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.

Publications

List of publications.
year	authors and title	journal	last update
2018	Gilles Degottex, Pierre Lanchantin, Mark Gales A Log Domain Pulse Model for Parametric Speech Synthesis published pages: 57-70, ISSN: 2329-9290, DOI: 10.1109/TASLP.2017.2761546	IEEE/ACM Transactions on Audio, Speech, and Language Processing 26/1	2019-06-17
2017	Gilles Degottex Pierre Lanchantin Mark Gales Light Supervised Data Selection, Voice Quality Normalized Training and Log Domain Pulse Synthesis published pages: , ISSN: , DOI:	Proc. Blizzard Challenge 2017	2019-06-17
2017	Moquan Wan Gilles Degottex Mark Gales Integrated speaker-adaptive speech synthesis published pages: , ISSN: , DOI:	Proc. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)	2019-06-17
2016	Gilles Degottex Pierre Lanchantin Mark Gales A Pulse Model in Log-domain for a Uniform Synthesizer published pages: , ISSN: , DOI:	Proc. 9th Speech Synthesis Workshop (SSW9)	2019-06-17

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "HQSTS" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an email (fabio@fabiodisconzi.com) and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "HQSTS" are provided by the European Opendata Portal: CORDIS opendata.