Salvato in:
Dettagli Bibliografici
Autori principali: Blatt, Alexander, Krishnan, Aravind, Klakow, Dietrich
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2406.13842
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914842064977920
author Blatt, Alexander
Krishnan, Aravind
Klakow, Dietrich
author_facet Blatt, Alexander
Krishnan, Aravind
Klakow, Dietrich
contents Utilizing air-traffic control (ATC) data for downstream natural-language processing tasks requires preprocessing steps. Key steps are the transcription of the data via automatic speech recognition (ASR) and speaker diarization, respectively speaker role detection (SRD) to divide the transcripts into pilot and air-traffic controller (ATCO) transcripts. While traditional approaches take on these tasks separately, we propose a transformer-based joint ASR-SRD system that solves both tasks jointly while relying on a standard ASR architecture. We compare this joint system against two cascaded approaches for ASR and SRD on multiple ATC datasets. Our study shows in which cases our joint system can outperform the two traditional approaches and in which cases the other architectures are preferable. We additionally evaluate how acoustic and lexical differences influence all architectures and show how to overcome them for our joint architecture.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13842
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Joint vs Sequential Speaker-Role Detection and Automatic Speech Recognition for Air-traffic Control
Blatt, Alexander
Krishnan, Aravind
Klakow, Dietrich
Computation and Language
Sound
Audio and Speech Processing
Utilizing air-traffic control (ATC) data for downstream natural-language processing tasks requires preprocessing steps. Key steps are the transcription of the data via automatic speech recognition (ASR) and speaker diarization, respectively speaker role detection (SRD) to divide the transcripts into pilot and air-traffic controller (ATCO) transcripts. While traditional approaches take on these tasks separately, we propose a transformer-based joint ASR-SRD system that solves both tasks jointly while relying on a standard ASR architecture. We compare this joint system against two cascaded approaches for ASR and SRD on multiple ATC datasets. Our study shows in which cases our joint system can outperform the two traditional approaches and in which cases the other architectures are preferable. We additionally evaluate how acoustic and lexical differences influence all architectures and show how to overcome them for our joint architecture.
title Joint vs Sequential Speaker-Role Detection and Automatic Speech Recognition for Air-traffic Control
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2406.13842