@inproceedings{gorisch-schmidt-2024-evaluating,
title = "Evaluating Workflows for Creating Orthographic Transcripts for Oral Corpora by Transcribing from Scratch or Correcting {ASR}-Output",
author = "Gorisch, Jan and
Schmidt, Thomas",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.582",
pages = "6564--6574",
abstract = "Research projects incorporating spoken data require either a selection of existing speech corpora, or they plan to record new data. In both cases, recordings need to be transcribed to make them accessible to analysis. Underestimating the effort of transcribing can be risky. Automatic Speech Recognition (ASR) holds the promise to considerably reduce transcription effort. However, few studies have so far attempted to evaluate this potential. The present paper compares efforts for manual transcription vs. correction of ASR-output. We took recordings from corpora of varying settings (interview, colloquial talk, dialectal, historic) and (i) compared two methods for creating orthographic transcripts: transcribing from scratch vs. correcting automatically created transcripts. And (ii) we evaluated the influence of the corpus characteristics on the correcting efficiency. Results suggest that for the selected data and transcription conventions, transcribing and correcting still take equally long with 7 times real-time on average. The more complex the primary data, the more time has to be spent on corrections. Despite the impressive latest developments in speech technology, to be a real help for conversation analysts or dialectologists, ASR systems seem to require even more improvement, or we need sufficient and appropriate data for training such systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gorisch-schmidt-2024-evaluating">
<titleInfo>
<title>Evaluating Workflows for Creating Orthographic Transcripts for Oral Corpora by Transcribing from Scratch or Correcting ASR-Output</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Gorisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Schmidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Research projects incorporating spoken data require either a selection of existing speech corpora, or they plan to record new data. In both cases, recordings need to be transcribed to make them accessible to analysis. Underestimating the effort of transcribing can be risky. Automatic Speech Recognition (ASR) holds the promise to considerably reduce transcription effort. However, few studies have so far attempted to evaluate this potential. The present paper compares efforts for manual transcription vs. correction of ASR-output. We took recordings from corpora of varying settings (interview, colloquial talk, dialectal, historic) and (i) compared two methods for creating orthographic transcripts: transcribing from scratch vs. correcting automatically created transcripts. And (ii) we evaluated the influence of the corpus characteristics on the correcting efficiency. Results suggest that for the selected data and transcription conventions, transcribing and correcting still take equally long with 7 times real-time on average. The more complex the primary data, the more time has to be spent on corrections. Despite the impressive latest developments in speech technology, to be a real help for conversation analysts or dialectologists, ASR systems seem to require even more improvement, or we need sufficient and appropriate data for training such systems.</abstract>
<identifier type="citekey">gorisch-schmidt-2024-evaluating</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.582</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6564</start>
<end>6574</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Workflows for Creating Orthographic Transcripts for Oral Corpora by Transcribing from Scratch or Correcting ASR-Output
%A Gorisch, Jan
%A Schmidt, Thomas
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F gorisch-schmidt-2024-evaluating
%X Research projects incorporating spoken data require either a selection of existing speech corpora, or they plan to record new data. In both cases, recordings need to be transcribed to make them accessible to analysis. Underestimating the effort of transcribing can be risky. Automatic Speech Recognition (ASR) holds the promise to considerably reduce transcription effort. However, few studies have so far attempted to evaluate this potential. The present paper compares efforts for manual transcription vs. correction of ASR-output. We took recordings from corpora of varying settings (interview, colloquial talk, dialectal, historic) and (i) compared two methods for creating orthographic transcripts: transcribing from scratch vs. correcting automatically created transcripts. And (ii) we evaluated the influence of the corpus characteristics on the correcting efficiency. Results suggest that for the selected data and transcription conventions, transcribing and correcting still take equally long with 7 times real-time on average. The more complex the primary data, the more time has to be spent on corrections. Despite the impressive latest developments in speech technology, to be a real help for conversation analysts or dialectologists, ASR systems seem to require even more improvement, or we need sufficient and appropriate data for training such systems.
%U https://aclanthology.org/2024.lrec-main.582
%P 6564-6574
Markdown (Informal)
[Evaluating Workflows for Creating Orthographic Transcripts for Oral Corpora by Transcribing from Scratch or Correcting ASR-Output](https://aclanthology.org/2024.lrec-main.582) (Gorisch & Schmidt, LREC-COLING 2024)
ACL