Enhancing access to Danish radio and television archives through advanced speech-to-text technologies

Lasse Rogers Nielsen; Lars Flemming  Mydtskov; Ditte Laursen

Enhancing access to Danish radio and television archives through advanced speech-to-text technologies

Lasse Rogers Nielsen
, Lars Flemming Mydtskov
, Ditte Laursen

Royal Danish Library

Research output: Contribution to conference › Conference abstract for conference › Research › peer-review

Abstract

This project aims to leverage the implementation of advanced Automatic Speech Recognition (ASR) systems to enable text-based searches within the Danish Royal Library’s extensive radio and television archives. Based on the Whisper ASR model, this research demonstrates how fine-tuning the model to Danish-language content can make these vast archives significantly more accessible and searchable for research.

Original language	English
Publication date	5 Dec 2024
Publication status	Published - 5 Dec 2024
Event	Computational Humanities Research Conference - Aarhus University, Aarhus, Denmark Duration: 4 Dec 2024 → 6 Dec 2024 https://2024.computational-humanities-research.org/

Conference

Conference	Computational Humanities Research Conference
Location	Aarhus University
Country/Territory	Denmark
City	Aarhus
Period	04/12/2024 → 06/12/2024
Internet address	https://2024.computational-humanities-research.org/

Cite this

@conference{970ab1a7b96f4f15877dcd4d3b850c71,

title = "Enhancing access to Danish radio and television archives through advanced speech-to-text technologies",

abstract = "This project aims to leverage the implementation of advanced Automatic Speech Recognition (ASR) systems to enable text-based searches within the Danish Royal Library{\textquoteright}s extensive radio and television archives. Based on the Whisper ASR model, this research demonstrates how fine-tuning the model to Danish-language content can make these vast archives significantly more accessible and searchable for research.",

author = "Nielsen, \{Lasse Rogers\} and Mydtskov, \{Lars Flemming\} and Ditte Laursen",

year = "2024",

month = dec,

day = "5",

language = "English",

note = "Computational Humanities Research Conference ; Conference date: 04-12-2024 Through 06-12-2024",

url = "https://2024.computational-humanities-research.org/",

}

TY - ABST

T1 - Enhancing access to Danish radio and television archives through advanced speech-to-text technologies

AU - Nielsen, Lasse Rogers

AU - Mydtskov, Lars Flemming

AU - Laursen, Ditte

PY - 2024/12/5

Y1 - 2024/12/5

N2 - This project aims to leverage the implementation of advanced Automatic Speech Recognition (ASR) systems to enable text-based searches within the Danish Royal Library’s extensive radio and television archives. Based on the Whisper ASR model, this research demonstrates how fine-tuning the model to Danish-language content can make these vast archives significantly more accessible and searchable for research.

AB - This project aims to leverage the implementation of advanced Automatic Speech Recognition (ASR) systems to enable text-based searches within the Danish Royal Library’s extensive radio and television archives. Based on the Whisper ASR model, this research demonstrates how fine-tuning the model to Danish-language content can make these vast archives significantly more accessible and searchable for research.

M3 - Conference abstract for conference

T2 - Computational Humanities Research Conference

Y2 - 4 December 2024 through 6 December 2024

ER -