elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Easy Adaptation of Speech Recognition to Different Air Traffic Control Environments using the DeepSpeech Engine

Kleinert, Matthias und Venkatarathinam, Narasimman und Helmke, Hartmut und Ohneiser, Oliver und Strake, Maximilian und Fingscheidt, Tim (2021) Easy Adaptation of Speech Recognition to Different Air Traffic Control Environments using the DeepSpeech Engine. 11th SESAR Innovation Days, 2021-12-07 - 2021-12-09, Virtual.

Dieses Archiv kann nicht den Volltext zur Verfügung stellen.

Kurzfassung

Nowadays, recognizing and understanding human speech is quite popular through systems like Alexa®, the Google Assistant or Siri®. Speech also plays a major role in air traffic control (ATC) as voice communication between air traffic controllers (ATCos) and pilots is essential for ensuring safe and efficient air traffic. This communication is still analogue and ATCos are forced to enter the same communication content again into digital systems with additional input devices. Automatic speech recognition (ASR) is a solution to automate this digitization process and an important necessity in optimizing ATCo workflow. This paper investigates the applicability of DeepSpeech, an open source, easy to adapt, end-to-end speech recognition engine from the Mozilla Corporation, as a speech-to-text solution for ATC speech. Different training approaches such as training a model from scratch and adapting a model pre-trained on non-ATC speech are explored. Model adaptation is performed by employing techniques such as fine-tuning, transfer learning, and layer freezing. Furthermore, the effect of employing an additional language model in conjunction with the end-to-end trained model is evaluated and shown to lead to a considerable relative improvement of 61% in word error rate. Overall, a word error rate of 6.0% is achieved on voice recordings from operational and simulation environment of different airspaces, resulting in command recognition rates between 85% and 97%. The achieved results show that DeepSpeech is a highly relevant solution for ATC-speech, especially when considering that it includes easy to use adaptation mechanisms also for non-experts in speech recognition.

elib-URL des Eintrags:https://elib.dlr.de/145397/
Dokumentart:Konferenzbeitrag (Vortrag)
Titel:Easy Adaptation of Speech Recognition to Different Air Traffic Control Environments using the DeepSpeech Engine
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Kleinert, MatthiasMatthias.Kleinert (at) dlr.dehttps://orcid.org/0000-0002-0782-4147NICHT SPEZIFIZIERT
Venkatarathinam, NarasimmanNarasimman.Venkatarathinam (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Helmke, HartmutHartmut.Helmke (at) dlr.dehttps://orcid.org/0000-0002-1939-0200NICHT SPEZIFIZIERT
Ohneiser, OliverOliver.Ohneiser (at) dlr.dehttps://orcid.org/0000-0002-5411-691XNICHT SPEZIFIZIERT
Strake, Maximilianm.strake (at) tu-bs.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Fingscheidt, Timt.fingscheidt (at) tu-bs.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Datum:2021
Referierte Publikation:Ja
Open Access:Nein
Gold Open Access:Nein
In SCOPUS:Nein
In ISI Web of Science:Nein
Status:veröffentlicht
Stichwörter:automatic speech recognition; ASR; air traffic control; ATC; DeepSpeech; ontology; domain adaptation
Veranstaltungstitel:11th SESAR Innovation Days
Veranstaltungsort:Virtual
Veranstaltungsart:internationale Konferenz
Veranstaltungsbeginn:7 Dezember 2021
Veranstaltungsende:9 Dezember 2021
Veranstalter :SESAR Joint Undertaking
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Luftfahrt
HGF - Programmthema:keine Zuordnung
DLR - Schwerpunkt:Luftfahrt
DLR - Forschungsgebiet:L - keine Zuordnung
DLR - Teilgebiet (Projekt, Vorhaben):L - Managementaufgaben Luftfahrt
Standort: Braunschweig
Institute & Einrichtungen:Institut für Flugführung > Lotsenassistenz
Hinterlegt von: Kleinert, Matthias
Hinterlegt am:13 Dez 2021 09:44
Letzte Änderung:24 Apr 2024 20:44

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.