@inproceedings{chirkova-etal-2025-comparing,
title = "Comparing efficacy of {IPA} vs {P}inyin romanisation transcriptions for complex tonal languages: A case study in {B}aima",
author = "Chirkova, Katia and
Coto-Solano, Rolando and
Griffiths, Rachael and
Meelen, Marieke",
editor = "Lachler, Jordan and
Agyapong, Godfred and
Arppe, Antti and
Moeller, Sarah and
Chaudhary, Aditi and
Rijhwani, Shruti and
Rosenblum, Daisy",
booktitle = "Proceedings of the Eight Workshop on the Use of Computational Methods in the Study of Endangered Languages",
month = mar,
year = "2025",
address = "Honolulu, Hawaii, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.computel-main.20/",
pages = "170--181",
abstract = "How is automated tone transcription affected by the choice of transcription orthography? In this paper we present a range of experiments that indicate that, even when the tonal repre- sentations are kept the same, the way vowels and consonants are transcribed can affect tonal character outputs. Our results also indicate that using a Language Model (LM) for decoding can mitigate problems with tonal outputs, but tones remain the most difficult part of the tran- scription. In doing this we also present the first Automatic Speech Recognition (ASR) models for the Baima language, spoken in Sichuan and Gansu, China. We hope to use these models to contribute to ongoing documentation efforts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chirkova-etal-2025-comparing">
<titleInfo>
<title>Comparing efficacy of IPA vs Pinyin romanisation transcriptions for complex tonal languages: A case study in Baima</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katia</namePart>
<namePart type="family">Chirkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rolando</namePart>
<namePart type="family">Coto-Solano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachael</namePart>
<namePart type="family">Griffiths</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marieke</namePart>
<namePart type="family">Meelen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eight Workshop on the Use of Computational Methods in the Study of Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Lachler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Godfred</namePart>
<namePart type="family">Agyapong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antti</namePart>
<namePart type="family">Arppe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Moeller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditi</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisy</namePart>
<namePart type="family">Rosenblum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Honolulu, Hawaii, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>How is automated tone transcription affected by the choice of transcription orthography? In this paper we present a range of experiments that indicate that, even when the tonal repre- sentations are kept the same, the way vowels and consonants are transcribed can affect tonal character outputs. Our results also indicate that using a Language Model (LM) for decoding can mitigate problems with tonal outputs, but tones remain the most difficult part of the tran- scription. In doing this we also present the first Automatic Speech Recognition (ASR) models for the Baima language, spoken in Sichuan and Gansu, China. We hope to use these models to contribute to ongoing documentation efforts.</abstract>
<identifier type="citekey">chirkova-etal-2025-comparing</identifier>
<location>
<url>https://aclanthology.org/2025.computel-main.20/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>170</start>
<end>181</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing efficacy of IPA vs Pinyin romanisation transcriptions for complex tonal languages: A case study in Baima
%A Chirkova, Katia
%A Coto-Solano, Rolando
%A Griffiths, Rachael
%A Meelen, Marieke
%Y Lachler, Jordan
%Y Agyapong, Godfred
%Y Arppe, Antti
%Y Moeller, Sarah
%Y Chaudhary, Aditi
%Y Rijhwani, Shruti
%Y Rosenblum, Daisy
%S Proceedings of the Eight Workshop on the Use of Computational Methods in the Study of Endangered Languages
%D 2025
%8 March
%I Association for Computational Linguistics
%C Honolulu, Hawaii, USA
%F chirkova-etal-2025-comparing
%X How is automated tone transcription affected by the choice of transcription orthography? In this paper we present a range of experiments that indicate that, even when the tonal repre- sentations are kept the same, the way vowels and consonants are transcribed can affect tonal character outputs. Our results also indicate that using a Language Model (LM) for decoding can mitigate problems with tonal outputs, but tones remain the most difficult part of the tran- scription. In doing this we also present the first Automatic Speech Recognition (ASR) models for the Baima language, spoken in Sichuan and Gansu, China. We hope to use these models to contribute to ongoing documentation efforts.
%U https://aclanthology.org/2025.computel-main.20/
%P 170-181
Markdown (Informal)
[Comparing efficacy of IPA vs Pinyin romanisation transcriptions for complex tonal languages: A case study in Baima](https://aclanthology.org/2025.computel-main.20/) (Chirkova et al., ComputEL 2025)
ACL