#	Pagina
attuale pagina	/open-h2020/projects/200854/index.html

Opendata, web and dolomites

MALORCA SIGNED

Machine Learning of Speech Recognition Models for Controller Assistance

Total Cost €

EC-Contrib. €

Partnership

Views

Outcomes and
results

MALORCA project word cloud

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

issue levels ops cheap accents causes language communication never advantages proposes failures adapt saarland automated usaar exchange absr atm speech controllers capital integral learning world assistant link recognizer automatically intensive environment lack reg time space deployment sources sensor recognition hampering local acceptance data traffic operators below one natural media amount university air model search aclistant customisation transfer rates situation voice deviations combines automate 2 replace reduce machine understand misunderstandings advantage pilots laboratory re manual environments phraseology context solution assumed standard command whereas automatic models automation generates respective venture dlr algorithms error creates difference introduction rooms

Project "MALORCA" data sheet

The following table provides information about the project.

Coordinator	DEUTSCHES ZENTRUM FUER LUFT - UND RAUMFAHRT EV Organization address address: Linder Hoehe city: KOELN postcode: 51147 website: www.dlr.de 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	Germany [DE]
Project website	http://www.malorca-project.de/
Total cost	805˙587 €
EC max contribution	538˙103 € (67%)
Programme	1. H2020-EU.3.4.7.1 (Exploratory Research)
Code Call	H2020-SESAR-2015-1
Funding Scheme	SESAR-RIA
Starting year	2016
Duration (year-month-day)	from 2016-04-01 to 2018-03-31

Partnership

Take a look of project's partnership.

#	participants	country	role	EC contrib. [€]
1	DEUTSCHES ZENTRUM FUER LUFT - UND RAUMFAHRT EV DEUTSCHES ZENTRUM FUER LUFT - UND RAUMFAHRT EV Organization address address: Linder Hoehe city: KOELN postcode: 51147 website: www.dlr.de contact info title: n.a. name: n.a. surname: n.a. function: n.a. email: n.a. telephone: n.a. fax: n.a.	DE (KOELN)	coordinator	211˙887.00
2	UNIVERSITAT DES SAARLANDES UNIVERSITAT DES SAARLANDES Organization address address: CAMPUS city: SAARBRUCKEN postcode: 66123 website: www.uni-saarland.de contact info title: n.a. name: n.a. surname: n.a. function: n.a. email: n.a. telephone: n.a. fax: n.a.	DE (SAARBRUCKEN)	participant	187˙211.00
3	AUSTRO CONTROL OSTERREICHISCHE GESELLSCHAFT FUR ZIVILLUFTFAHRT MBH AUSTRO CONTROL OSTERREICHISCHE GESELLSCHAFT FUR ZIVILLUFTFAHRT MBH Organization address address: WAGRAMER STRASSE 19 city: WIEN postcode: 1220 website: n.a. contact info title: n.a. name: n.a. surname: n.a. function: n.a. email: n.a. telephone: n.a. fax: n.a.	AT (WIEN)	participant	86˙562.00
4	RIZENI LETOVEHO PROVOZU CESKE REPUBLIKY STATNI PODNIK RIZENI LETOVEHO PROVOZU CESKE REPUBLIKY STATNI PODNIK Organization address address: JENEC NAVIGACNI 787 city: JENEC postcode: 252 61 website: n.a. contact info title: n.a. name: n.a. surname: n.a. function: n.a. email: n.a. telephone: n.a. fax: n.a.	CZ (JENEC)	participant	52˙442.00
5	FONDATION DE L'INSTITUT DE RECHERCHE IDIAP FONDATION DE L'INSTITUT DE RECHERCHE IDIAP Organization address address: RUE MARCONI 19 city: MARTIGNY postcode: 1920 website: n.a. contact info title: n.a. name: n.a. surname: n.a. function: n.a. email: n.a. telephone: n.a. fax: n.a.	CH (MARTIGNY)	participant	0.00

Map

Project objective

One of the main causes hampering the introduction of higher levels of automation in the Air Traffic Management (ATM) world is the intensive use of spoken language as the natural way of communication. Data link will be another media of communication with its known advantages compared to voice communication but for the future it is still assumed that data link communication will increase but never fully replace voice communication. Particularly for the time being controllers and pilots exchange information by spoken language, whereas automated systems understand the situation based only on sensor information. This difference in the end creates misunderstandings between operators and systems which lead to failures and further on to a lack of acceptance for automation. One promising solution is the introduction of automatic speech recognition as an integral part of automation. Recently, the venture capital funded project AcListant® has achieved command error rates below 2% based on Assistant Based Speech Recognition (ABSR), developed by Saarland University (USAAR) and DLR. ABSR combines speech recognition with an assistant system, which generates context information to reduce the search space of the speech recognizer. One main issue to transfer ABSR from the laboratory to the ops-rooms is its costs of deployment. Each ABSR model must manual adapted to the local environment due to e.g. different accents and deviations from standard phraseology. This project proposes a general, cheap and effective solution to automate this re-learning, adaptation and customisation process to new environments, taking advantage of the large amount of speech data available in the ATM world. Machine learning algorithms using these data sources will automatically adapt the ABSR models to the respective environment.

Deliverables

List of deliverables.
System Requirement Document	Documents, reports	2019-05-31 12:00:56
Report on Stakeholder Workshop Results	Websites, patent fillings, videos etc.	2019-05-30 14:44:58
Gap Analysis Report (T0+24)	Documents, reports	2019-05-30 14:44:56
Operational Concept Description	Documents, reports	2019-05-30 14:44:56
Publishable Project Results final report	Documents, reports	2019-05-30 14:44:54

Take a look to the deliverables list in detail: detailed list of MALORCA deliverables.

Publications

List of publications.
year	authors and title	journal	last update
2017	Ajay Srinivasamurthy, Petr Motlicek, Ivan Himawan, Gyorgy Szaszak, Youssef Oualil, Hartmut Helmke Semi-supervised Learning with Semantic Knowledge Extraction for Improved Speech Recognition in Air Traffic Control published pages: , ISSN: , DOI:		2019-06-13
2017	M. Kleinert, H. Helmke, G. Siol, H. Ehr, M. Finke, Y. Oualil, A. Srinivasamurthy Machine Learning of Controller Command Prediction Models from Recorded Radar Dataand Controller Speech Utterances published pages: 8, ISSN: , DOI:	SESAR Innovation Days in Belgrade	2019-06-13
2017	Youssef Oualil, Dietrich Klakow, Gyorgy Szaszak, Ajay Srinivasamurthy, Hartmut Helmke, Petr Motlicek A CONTEXT-AWARE SPEECH RECOGNITION AND UNDERSTANDING SYSTEM FOR AIR TRAFFIC CONTROL DOMAIN published pages: , ISSN: , DOI:	Automatic Speech Recognition and Understanding Workshop	2019-06-13
2016	Hartmut Helmke, Petr Motlicek, Ivan Himawan, Oliver Ohneiser, Christian Windisch, Christian Kern, Aneta Cerna, Matej Nesvadba, Youssef Oualil, Dietrich Klakow, GyÃ¶rgy Szaszak MALORCA: Learning of Controllers\' Behaviour from Recorded Radar Data and Speech Utterances published pages: , ISSN: , DOI:	6th SESAR INNOVATION DAYS	2019-06-13

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "MALORCA" 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 "MALORCA" are provided by the European Opendata Portal: CORDIS opendata.