MALORCA: Machine Learning meets Automatic Speech Recognition in ATC

Rataj, Jürgen (2018) MALORCA: Machine Learning meets Automatic Speech Recognition in ATC. WAC-2018 WORKSHOP: DATA DRIVEN ATM: GOING DIGITAL, 06.-08. März 2018, Madrid, Spanien.

Full text not available from this repository.

Abstract

MALORCA developed a low cost mechanism to configure a speech recognizer to a specific airport Radar data improves unsupervised learning considerably Demonstration airport are Vienna and Prague An initial transcribed data set of 4 hours was used Recognition was increased by adding 21 hours of untranscribed data to 92% from 80% TRL 1 and 2 reached with the developed system

Item URL in elib:

https://elib.dlr.de/119520/

Document Type:

Conference or Workshop Item (Speech)

Title:

MALORCA: Machine Learning meets Automatic Speech Recognition in ATC

Authors:

Authors	Institution or Email of Authors	Authors ORCID iD
Rataj, Jürgen	juergen.rataj (at) dlr.de	UNSPECIFIED

Date:

8 March 2018

Refereed publication:

Open Access:

Gold Open Access:

In SCOPUS:

In ISI Web of Science:

Status:

Published

Keywords:

assistance based speech recognizer, learning mechanisms, AcListant, Controller assistance Systems, speech recognition

Event Title:

WAC-2018 WORKSHOP: DATA DRIVEN ATM: GOING DIGITAL

Event Location:

Madrid, Spanien

Event Type:

Workshop

Event Dates:

06.-08. März 2018

HGF - Research field:

Aeronautics, Space and Transport

HGF - Program:

Aeronautics

HGF - Program Themes:

other

DLR - Research area:

Aeronautics

DLR - Program:

L - no assignment

DLR - Research theme (Project):

L - Managementaufgaben Luftfahrt

Location:

Braunschweig

Institutes and Institutions:

Institute of Flight Control > Controller Assistance

Deposited By:

Diederich, Kerstin

Deposited On:

25 Sep 2018 14:39

Last Modified:

25 Sep 2018 14:39

Repository Staff Only: item control page