- Acapela group – Voice synthesis – Text to Speech - http://www.acapela-group.com -

R&D Projects

Pushing the Boundaries of Voice.

R&D @ Acapela Group

Involvement in R&D funded projects and collaboration with high profile partners, organizations, universities and laboratories, are essential to helping us meet our goals, to fulfilling our role as ground breaking inventors of leading-edge speech solutions. As an expert and innovative bespoke player we push the boundaries of voice.

Projects involving Acapela Group since 2001:

Humanoid  intelligent companions, multilingual conversations, singing speech, expressive reading and transmission of emotions, Internet of Things, biometrics and multimodal man-machine interaction are some of the domains we have been seriously involved with for over a decade, partnering with experts worldwide.

2014 – ChaNTeR
2013 – PATH
2013- I-Treasures
2012 – DBOX
2012 – Mardi
2012 – Content4All
2011 – DIYSE
2010- EMOSPEECH
2010- BIOSPEAK
2010 – ROMEO
2009 – GVLEX
2009 – Franel
2008 – HMMTTS
2007 – INDIGO
2005 – BOON Companion
2004 – DIVINES
2003 – E! 2990- MAJORCALL Majordome CRM Call Centers
2003 – STOP
2003 – NORMALANGUE
2003 – ULYCES
2002 – EVASY
2001 – SYNFACE [1]

2013 – PATH

2013- I-Treasures

itreasures [6]

2012 – DBOX

21012 – Mardi: Man Robot Dialogue

2012 – Content4All

D2011 – DIYSE  (Do It Yourself)

2010- EMOSPEECH (EuroStar Project)

2010- BIOSPEAK (EuroStar Framework)

2010 – ROMEO

2009 – GVLEX, Gesture and Voice for expressive reading

2009 – Franel

2008 – HMMTTS

2007 – INDIGO

FORTH-ICS [93] (http://www.ics.forth.gr/cvrl),Univ Edinburgh [94] (http://www.iccs.inf.ed.ac.uk/),Uni Albert Ludwigs of Freiburg [95] (http://ais.informatik.uni-freiburg.de/),University of Athens [95] (http://ais.informatik.uni-freiburg.de/),University of Geneva [96] (http://www.miralab.ch/),NEOGPS [97] (http://www.neobotix.de/en/),HANSON [98] (http://hansonrobotics.wordpress.com/),Fondation Hellenic World [99] (http://www.fhw.gr/index_en.html),NCSR [100] (http://www.iit.demokritos.gr/skel/)

2005 – BOON Companion (ITEA project)

2004 – DIVINES

European Project FP6-IST-2002-002034 DIVINES: Diagnostic and Intrinsic Variabilities in Natural Speech

The goal of DIVINES is to develop some new knowledge towards renewed feature extraction and modelling techniques that would have better capacities, particularly in handling speech intrinsic variabilities. First, human and machine performance and the effect of intrinsic variabilities will be compared based on a diagnostic procedure. The outcomes of this analysis will then be exploited to target feature extraction, acoustic and lexical modelling. Compatibility with techniques dealing with noise and integration within current systems are also part of the objectives.

The project is relevant to the “multimodal interfaces” objective as it concerns more accurate and adaptable recognition of spoken language. This is central to the concept of multimodal man-machine interaction where the speech understanding service is likely to remain an independent component in a modular design. Advances in this field could be decisive in realizing the vision of natural interactivity.

  • Partners:THE ROYAL INSTITUTION FOR THE ADVANCEMENT OF LEARNING (MCGILL UNIVERSITY) (http://www.mcgill.ca/fr),FRANCE TELECOM SA (http://www.orange.fr/),LOQUENDO SPA (http://www.loquendo.com/en/), UNIVERSITE D’AVIGNON ET DU PAYS-VAUCLUSE (http://www.univ-avignon.fr/),INSTITUT EURECOM (http://www.eurecom.fr/),CARL VON OSSIETZKY UNIVERSITAET OLDENBURG (http://www.uni-oldenburg.de/),POLITECNICO DI TORINO (http://www.polito.it/

2003 – E! 2990- MAJORCALL Majordome CRM Call Centers

2003 – STOP : http://tcts.fpms.ac.be/projects/stop/index.html

2003 – NORMALANGUE

2003 – ULYCES ULYCES [117] :

BABEL Technologies (Now Acapela Group) and EZOS (with Twin Development and Automobile Gillet) were working  together on the UlyCEs project, which aimed to develop a Telematic platform for the automotive industry, based on Win CE technology.

EVASY

– evaluation of the grapheme-to-phoneme module,
– evaluation of prosody and expressivity,
– global evaluation of the quality of the synthesised speech.

6 systems have been evaluated: three systems based on diphones (marked D1, D2 and D3 as before), and 3 systems based on the unit selection method (S1, S2 and S3). It came from the following entites: Acapela Group, Multitel, CRISCO, ELAN, ICP, LIMSI-CNRS.

ELDA  [121](Evaluations and Language Resources distribution Agency)  http://www.elda.org, LIMSI  [74](Laboratoire d’Informatique pour la Mécanique et les Sciences de l’Ingénieur) (http://www.limsi.fr/), Equipe de recherche DELIC [122] (Description Linguistique Informatisée sur Corpus), Université de Provence (http://www.up.univ-mrs.fr/delic/), CRISCO [123] (Centre de Recherches Inter-langues sur la Signification en Contexte) (http://elsap1.unicaen.fr/), ICP (Institut de la Communication Parlée), LIA (Laboratoire Informatique d’Avignon), MULTITEL [4] ASBL http://www.multitel.be/

2001 – SYNFACE
Synthesised talking face derived from speech for hearing disabled users of voice channels [1]