@inproceedings{udawatta-etal-2026-ttsvowelviz,
title = "{TTSV}owel{V}iz: A Tool for Visualising Text-to-Speech Model Training via Vowel Spaces",
author = "Udawatta, Pasindu and
James, Jesin and
B T, Balamurali and
Watson, Catherine Inez and
Nicholas, Ake and
Abeysinghe, Binu Nisal",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.375/",
doi = "10.63317/57peripccxqx",
pages = "4778--4786",
abstract = "In text-to-speech (TTS) model training, the saturation of the loss curve indicates how well a model learns the characteristics of the training dataset. But it does not reveal the linguistic properties learned by the model. Existing TTS approaches miss the potential to incorporate linguistic insights into model training. We introduce TTSVowelViz, a novel tool that visualises static and dynamic vowel spaces during model training, bridging linguistic knowledge and TTS model development. It helps identify which vowel sounds are accurately learned and how the vowel spaces are evolved during training. To assess TTSVowelViz, we fine-tuned a TTS model from General American English to New Zealand English and conducted a perception test. Our results show that the formants of specific vowels in the vowel spaces generated by TTSVowelViz align with human perception, effectively visualising the perceived accent shift. This work highlights vowel space visualisation as a valuable interpretability tool for TTS training."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="udawatta-etal-2026-ttsvowelviz">
<titleInfo>
<title>TTSVowelViz: A Tool for Visualising Text-to-Speech Model Training via Vowel Spaces</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pasindu</namePart>
<namePart type="family">Udawatta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesin</namePart>
<namePart type="family">James</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balamurali</namePart>
<namePart type="family">B T</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="given">Inez</namePart>
<namePart type="family">Watson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ake</namePart>
<namePart type="family">Nicholas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binu</namePart>
<namePart type="given">Nisal</namePart>
<namePart type="family">Abeysinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In text-to-speech (TTS) model training, the saturation of the loss curve indicates how well a model learns the characteristics of the training dataset. But it does not reveal the linguistic properties learned by the model. Existing TTS approaches miss the potential to incorporate linguistic insights into model training. We introduce TTSVowelViz, a novel tool that visualises static and dynamic vowel spaces during model training, bridging linguistic knowledge and TTS model development. It helps identify which vowel sounds are accurately learned and how the vowel spaces are evolved during training. To assess TTSVowelViz, we fine-tuned a TTS model from General American English to New Zealand English and conducted a perception test. Our results show that the formants of specific vowels in the vowel spaces generated by TTSVowelViz align with human perception, effectively visualising the perceived accent shift. This work highlights vowel space visualisation as a valuable interpretability tool for TTS training.</abstract>
<identifier type="citekey">udawatta-etal-2026-ttsvowelviz</identifier>
<identifier type="doi">10.63317/57peripccxqx</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.375/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>4778</start>
<end>4786</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TTSVowelViz: A Tool for Visualising Text-to-Speech Model Training via Vowel Spaces
%A Udawatta, Pasindu
%A James, Jesin
%A B T, Balamurali
%A Watson, Catherine Inez
%A Nicholas, Ake
%A Abeysinghe, Binu Nisal
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F udawatta-etal-2026-ttsvowelviz
%X In text-to-speech (TTS) model training, the saturation of the loss curve indicates how well a model learns the characteristics of the training dataset. But it does not reveal the linguistic properties learned by the model. Existing TTS approaches miss the potential to incorporate linguistic insights into model training. We introduce TTSVowelViz, a novel tool that visualises static and dynamic vowel spaces during model training, bridging linguistic knowledge and TTS model development. It helps identify which vowel sounds are accurately learned and how the vowel spaces are evolved during training. To assess TTSVowelViz, we fine-tuned a TTS model from General American English to New Zealand English and conducted a perception test. Our results show that the formants of specific vowels in the vowel spaces generated by TTSVowelViz align with human perception, effectively visualising the perceived accent shift. This work highlights vowel space visualisation as a valuable interpretability tool for TTS training.
%R 10.63317/57peripccxqx
%U https://aclanthology.org/2026.lrec-1.375/
%U https://doi.org/10.63317/57peripccxqx
%P 4778-4786
Markdown (Informal)
[TTSVowelViz: A Tool for Visualising Text-to-Speech Model Training via Vowel Spaces](https://aclanthology.org/2026.lrec-1.375/) (Udawatta et al., LREC 2026)
ACL