elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Semi-supervised Adaptation of Assistant Based Speech Recognition Models for different Approach Areas

Kleinert, Matthias and Helmke, Hartmut and Siol, Gerald and Ehr, Heiko and Cerna, Aneta and Kern, Christian and Klakow, Dietrich and Motlice, Petr and Oualil, Youssef and Singh, Mittul and Srinivasamurthy, Ajay (2018) Semi-supervised Adaptation of Assistant Based Speech Recognition Models for different Approach Areas. In: 37th IEEE/AIAA Digital Avionics Systems Conference, DASC 2018. 37th AIAA/IEEE Digital Avionics Systems Conference (DASC), 23. - 27. Sep. 2018, London, England.

[img] PDF
448kB

Abstract

Air Navigation Service Providers (ANSPs) replace paper flight strips through different digital solutions. The instructed com-mands from an air traffic controller (ATCos) are then available in computer readable form. However, those systems require manual controller inputs, i.e. ATCos workload increases. The Active Listening Assistant (AcListant®) project has shown that Assistant Based Speech Recognition (ABSR) is a potential solution to reduce this additional workload. However, the development of an ABSR application for a specific target-domain usually requires a large amount of manually transcribed audio data in order to achieve task-sufficient recognition accuracies. MALORCA project developed an initial basic ABSR system and semi-automatically tailored its recognition models for both Prague and Vienna approaches by machine learning from automatically transcribed audio data. Command recognition error rates were reduced from 7.9% to under 0.6% for Prague and from 18.9% to 3.2% for Vienna.

Item URL in elib:https://elib.dlr.de/123238/
Document Type:Conference or Workshop Item (Speech)
Title:Semi-supervised Adaptation of Assistant Based Speech Recognition Models for different Approach Areas
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Kleinert, MatthiasMatthias.Kleinert (at) dlr.deUNSPECIFIED
Helmke, HartmutHartmut.Helmke (at) dlr.deUNSPECIFIED
Siol, GeraldGerald.Siol (at) dlr.deUNSPECIFIED
Ehr, HeikoHeiko.Ehr (at) dlr.deUNSPECIFIED
Cerna, AnetaAneta.Cerna (at) ans.czUNSPECIFIED
Kern, ChristianChristian.Kern (at) austrocontrol.atUNSPECIFIED
Klakow, Dietrichdietrich.klakow (at) lsv.uni-saarland.deUNSPECIFIED
Motlice, Petrpetr.motlicek (at) idiap.chUNSPECIFIED
Oualil, Youssefyoualil (at) lsv.uni-saarland.deUNSPECIFIED
Singh, Mittulmittul.singh (at) lsv.uni-saarland.deUNSPECIFIED
Srinivasamurthy, Ajayajay.srinivasamurthy (at) idiap.chUNSPECIFIED
Date:September 2018
Journal or Publication Title:37th IEEE/AIAA Digital Avionics Systems Conference, DASC 2018
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Status:Published
Keywords:Machine Learning, Assistant Based Speech Recognition, Unsupervised Learning, Command Prediction Model, Automatic Speech Recognition
Event Title:37th AIAA/IEEE Digital Avionics Systems Conference (DASC)
Event Location:London, England
Event Type:international Conference
Event Dates:23. - 27. Sep. 2018
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Aeronautics
HGF - Program Themes:air traffic management and operations
DLR - Research area:Aeronautics
DLR - Program:L AO - Air Traffic Management and Operation
DLR - Research theme (Project):L - Efficient Flight Guidance
Location: Braunschweig
Institutes and Institutions:Institute of Flight Control > Controller Assistance
Deposited By: Kleinert, Matthias
Deposited On:26 Nov 2018 14:39
Last Modified:31 Jul 2019 20:20

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.