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

Semi-supervised Learning with Semantic Knowledge Extraction for Improved Speech Recognition in Air Traffic Control

Srinivasamurthy, Ajay and Motlice, Petr and Himawan, Ivan and Szaszák, György and Oualil, Youssef and Helmke, Hartmut (2017) Semi-supervised Learning with Semantic Knowledge Extraction for Improved Speech Recognition in Air Traffic Control. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 1-5. Interspeech 2017, 20.-24. August 2017, Stockholm, Schweden.

Full text not available from this repository.

Abstract

Automatic Speech Recognition (ASR) can introduce higher levels of automation into Air Traffic Control (ATC), where spoken language is still the predominant form of communication. While ATC uses standard phraseology and a limited vocabulary, we need to adapt the speech recognition systems to local acoustic conditions and vocabularies at each airport to reach optimal performance. Due to continuous operation of ATC systems, a large and increasing amount of untranscribed speech data is available, allowing for semi-supervised learning methods to build and adapt ASR models. In this paper, we first identify the challenges in building ASR systems for specific ATC areas and propose to utilize out-of-domain data to build baseline ASR models. Then we explore different methods of data selection for adapting baseline models by exploiting the continuously increasing untranscribed data. We develop a basic approach capable of exploiting semantic representations of ATC commands. We achieve relative improvement in both word error rate (23.5%) and concept error rates (7%) when adapting ASR models to different ATC conditions in a semi-supervised manner.

Item URL in elib:https://elib.dlr.de/115318/
Document Type:Conference or Workshop Item (Speech)
Title:Semi-supervised Learning with Semantic Knowledge Extraction for Improved Speech Recognition in Air Traffic Control
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Srinivasamurthy, Ajayajay.srinivasamurthy (at) idiap.chUNSPECIFIED
Motlice, Petrpetr.motlicek (at) idiap.chUNSPECIFIED
Himawan, Ivanivan.himawan (at) idiap.chUNSPECIFIED
Szaszák, Györgygszaszak (at) lsv.uni-saarland.deUNSPECIFIED
Oualil, Youssefyoualil (at) lsv.uni-saarland.deUNSPECIFIED
Helmke, Hartmuthartmut.helmke (at) dlr.deUNSPECIFIED
Date:2017
Journal or Publication Title:Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
Page Range:pp. 1-5
Status:Published
Keywords:Speech Recognition, Air Traffic Control, Semisupervised learning
Event Title:Interspeech 2017
Event Location:Stockholm, Schweden
Event Type:international Conference
Event Dates:20.-24. August 2017
Organizer:Department of Linguistics, Stockholm University; Department of Speech, Music and Hearing, KTH Royal Institute of Technology; Division of Speech and Language Pathology, Karolinska Institutet PCO: Akademikonferens
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: Diederich, Kerstin
Deposited On:27 Nov 2017 10:00
Last Modified:14 May 2019 13:31

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.