<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kotoge-sasaki-2026-data">
    <titleInfo>
        <title>Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rikuto</namePart>
        <namePart type="family">Kotoge</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuichi</namePart>
        <namePart type="family">Sasaki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-391-3</identifier>
    </relatedItem>
    <abstract>Aligning text-to-speech (TTS) system outputs with human feedback through preference optimization has been shown to effectively improve the robustness and naturalness of LLM-based TTS models. Current approaches primarily require paired desirable and undesirable samples at the utterance level. However, such pairs are often limited in TTS output data, and utterance-level formulation prevents fine-grained token-level optimization needed for accurate pronunciation alignment. In this study, we propose TKTO that eliminates the need for paired data, enabling a more data-efficient training paradigm, and directly targets token-level units, automatically providing fine-grained alignment signals without token-level annotations. TKTO improves the challenging Japanese TTS accuracy by 39% and reduces CER by 54%, leveraging 6× more training data and assigning 12.8× stronger reward to targeted tokens.</abstract>
    <identifier type="citekey">kotoge-sasaki-2026-data</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-short.59/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>719</start>
            <end>726</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech
%A Kotoge, Rikuto
%A Sasaki, Yuichi
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-391-3
%F kotoge-sasaki-2026-data
%X Aligning text-to-speech (TTS) system outputs with human feedback through preference optimization has been shown to effectively improve the robustness and naturalness of LLM-based TTS models. Current approaches primarily require paired desirable and undesirable samples at the utterance level. However, such pairs are often limited in TTS output data, and utterance-level formulation prevents fine-grained token-level optimization needed for accurate pronunciation alignment. In this study, we propose TKTO that eliminates the need for paired data, enabling a more data-efficient training paradigm, and directly targets token-level units, automatically providing fine-grained alignment signals without token-level annotations. TKTO improves the challenging Japanese TTS accuracy by 39% and reduces CER by 54%, leveraging 6× more training data and assigning 12.8× stronger reward to targeted tokens.
%U https://aclanthology.org/2026.acl-short.59/
%P 719-726

Markdown (Informal)

[Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech](https://aclanthology.org/2026.acl-short.59/) (Kotoge & Sasaki, ACL 2026)

• Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech (Kotoge & Sasaki, ACL 2026)

ACL

• Rikuto Kotoge and Yuichi Sasaki. 2026. Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 719–726, San Diego, California, United States. Association for Computational Linguistics.