@inproceedings{park-etal-2024-hyper,
title = "Hyper-{BTS} Dataset: Scalability and Enhanced Analysis of Back {T}ran{S}cription ({BTS}) for {ASR} Post-Processing",
author = "Park, Chanjun and
Seo, Jaehyung and
Lee, Seolhwa and
Son, Junyoung and
Moon, Hyeonseok and
Eo, Sugyeong and
Lee, Chanhee and
Lim, Heuiseok",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2024",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-eacl.5",
pages = "67--78",
abstract = "The recent advancements in the realm of Automatic Speech Recognition (ASR) post-processing have been primarily driven by sequence-to-sequence paradigms. Despite their effectiveness, these methods often demand substantial amounts of data, necessitating the expensive recruitment of phonetic transcription experts to rectify the erroneous outputs of ASR systems, thereby creating the desired training data. Back TranScription (BTS) alleviates this issue by generating ASR inputs from clean text via a Text-to-Speech (TTS) system. While initial studies on BTS exhibited promise, they were constrained by a limited dataset of just 200,000 sentence pairs, leaving the scalability of this method in question. In this study, we delve into the potential scalability of BTS. We introduce the {``}Hyper-BTS{''} dataset, a corpus approximately five times larger than that utilized in prior research. Additionally, we present innovative criteria for categorizing error types within ASR post-processing. This not only facilitates a more comprehensive qualitative analysis, which was absent in preceding studies, but also enhances the understanding of ASR error patterns. Our empirical results, both quantitative and qualitative, suggest that the enlarged scale of the Hyper-BTS dataset sufficiently addresses a vast majority of the ASR error categories. We make the Hyper-BTS dataset publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2024-hyper">
<titleInfo>
<title>Hyper-BTS Dataset: Scalability and Enhanced Analysis of Back TranScription (BTS) for ASR Post-Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chanjun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaehyung</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seolhwa</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyoung</namePart>
<namePart type="family">Son</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyeonseok</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sugyeong</namePart>
<namePart type="family">Eo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chanhee</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heuiseok</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The recent advancements in the realm of Automatic Speech Recognition (ASR) post-processing have been primarily driven by sequence-to-sequence paradigms. Despite their effectiveness, these methods often demand substantial amounts of data, necessitating the expensive recruitment of phonetic transcription experts to rectify the erroneous outputs of ASR systems, thereby creating the desired training data. Back TranScription (BTS) alleviates this issue by generating ASR inputs from clean text via a Text-to-Speech (TTS) system. While initial studies on BTS exhibited promise, they were constrained by a limited dataset of just 200,000 sentence pairs, leaving the scalability of this method in question. In this study, we delve into the potential scalability of BTS. We introduce the “Hyper-BTS” dataset, a corpus approximately five times larger than that utilized in prior research. Additionally, we present innovative criteria for categorizing error types within ASR post-processing. This not only facilitates a more comprehensive qualitative analysis, which was absent in preceding studies, but also enhances the understanding of ASR error patterns. Our empirical results, both quantitative and qualitative, suggest that the enlarged scale of the Hyper-BTS dataset sufficiently addresses a vast majority of the ASR error categories. We make the Hyper-BTS dataset publicly available.</abstract>
<identifier type="citekey">park-etal-2024-hyper</identifier>
<location>
<url>https://aclanthology.org/2024.findings-eacl.5</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>67</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hyper-BTS Dataset: Scalability and Enhanced Analysis of Back TranScription (BTS) for ASR Post-Processing
%A Park, Chanjun
%A Seo, Jaehyung
%A Lee, Seolhwa
%A Son, Junyoung
%A Moon, Hyeonseok
%A Eo, Sugyeong
%A Lee, Chanhee
%A Lim, Heuiseok
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F park-etal-2024-hyper
%X The recent advancements in the realm of Automatic Speech Recognition (ASR) post-processing have been primarily driven by sequence-to-sequence paradigms. Despite their effectiveness, these methods often demand substantial amounts of data, necessitating the expensive recruitment of phonetic transcription experts to rectify the erroneous outputs of ASR systems, thereby creating the desired training data. Back TranScription (BTS) alleviates this issue by generating ASR inputs from clean text via a Text-to-Speech (TTS) system. While initial studies on BTS exhibited promise, they were constrained by a limited dataset of just 200,000 sentence pairs, leaving the scalability of this method in question. In this study, we delve into the potential scalability of BTS. We introduce the “Hyper-BTS” dataset, a corpus approximately five times larger than that utilized in prior research. Additionally, we present innovative criteria for categorizing error types within ASR post-processing. This not only facilitates a more comprehensive qualitative analysis, which was absent in preceding studies, but also enhances the understanding of ASR error patterns. Our empirical results, both quantitative and qualitative, suggest that the enlarged scale of the Hyper-BTS dataset sufficiently addresses a vast majority of the ASR error categories. We make the Hyper-BTS dataset publicly available.
%U https://aclanthology.org/2024.findings-eacl.5
%P 67-78
Markdown (Informal)
[Hyper-BTS Dataset: Scalability and Enhanced Analysis of Back TranScription (BTS) for ASR Post-Processing](https://aclanthology.org/2024.findings-eacl.5) (Park et al., Findings 2024)
ACL
- Chanjun Park, Jaehyung Seo, Seolhwa Lee, Junyoung Son, Hyeonseok Moon, Sugyeong Eo, Chanhee Lee, and Heuiseok Lim. 2024. Hyper-BTS Dataset: Scalability and Enhanced Analysis of Back TranScription (BTS) for ASR Post-Processing. In Findings of the Association for Computational Linguistics: EACL 2024, pages 67–78, St. Julian’s, Malta. Association for Computational Linguistics.