BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU149419" target="_blank" >RIV/00216305:26230/23:PU149419 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/10022718" target="_blank" >https://ieeexplore.ieee.org/document/10022718</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/SLT54892.2023.10022718" target="_blank" >10.1109/SLT54892.2023.10022718</a>

Jazyk výsledku

angličtina

Název v původním jazyce

BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications

Popis výsledku v původním jazyce

Automatic speech recognition (ASR) allows transcribing the communications between air traffic controllers (ATCOs) and aircraft pilots. The transcriptions are used later to extract ATC named entities, e.g., aircraft callsigns. One common challenge is speech activity detection (SAD) and speaker diarization (SD). In the failure condition, two or more segments remain in the same recording, jeopardizing the overall performance. We propose a system that combines SAD and a BERT model to perform speaker change detection and speaker role detection (SRD) by chunking ASR transcripts, i.e., SD with a defined number of speakers together with SRD. The proposed model is evaluated on real-life public ATC databases. Our BERT SD model baseline reaches up to 10% and 20% token-based Jaccard error rate (JER) in public and private ATC databases. We also achieved relative improvements of 32% and 7.7% in JERs and SD error rate (DER), respectively, compared to VBx, a well-known SD system.1

Název v anglickém jazyce

BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control Communications

Popis výsledku anglicky

Automatic speech recognition (ASR) allows transcribing the communications between air traffic controllers (ATCOs) and aircraft pilots. The transcriptions are used later to extract ATC named entities, e.g., aircraft callsigns. One common challenge is speech activity detection (SAD) and speaker diarization (SD). In the failure condition, two or more segments remain in the same recording, jeopardizing the overall performance. We propose a system that combines SAD and a BERT model to perform speaker change detection and speaker role detection (SRD) by chunking ASR transcripts, i.e., SD with a defined number of speakers together with SRD. The proposed model is evaluated on real-life public ATC databases. Our BERT SD model baseline reaches up to 10% and 20% token-based Jaccard error rate (JER) in public and private ATC databases. We also achieved relative improvements of 32% and 7.7% in JERs and SD error rate (DER), respectively, compared to VBx, a well-known SD system.1

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings

ISBN

978-1-6654-7189-3

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

633-640

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Doha

Místo konání akce

Doha

Datum konání akce

9. 1. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000968851900086