<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chung-etal-2026-llm">
    <titleInfo>
        <title>LLM-Codec: Neural Audio Codec Meets Language Model Objectives</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ho-Lam</namePart>
        <namePart type="family">Chung</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yiming</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hung-yi</namePart>
        <namePart type="family">Lee</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Neural audio codecs are widely used as tokenizers for spoken language models, but they are optimized for waveform reconstruction rather than autoregressive prediction.This mismatch injects acoustically driven uncertainty into the discrete token space and increases language-model perplexity.We propose , which augments codec training with language-model-facing objectives while keeping both codec and LLM architectures unchanged.introduces (i) future token prediction with Medusa-style multi-step heads to encourage multi-step predictability, and (ii) semantic alignment that matches audio and text representations via a memory-bank contrastive loss.A differentiable Gumbel bridge enables end-to-end gradients from these objectives to the codec encoder.On SALMon speech coherence, token LMs trained on reach 61.6% accuracy (+12.1 points over AUV) while reducing perplexity 35\times.On Codec-SUPERB-tiny, improves speech Mel distance by 5.0% over AUV while simultaneously achieving the learnability gains, demonstrating that reconstruction fidelity and token predictability can be improved together.</abstract>
    <identifier type="citekey">chung-etal-2026-llm</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.1308/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>26251</start>
            <end>26265</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LLM-Codec: Neural Audio Codec Meets Language Model Objectives
%A Chung, Ho-Lam
%A Chen, Yiming
%A Lee, Hung-yi
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F chung-etal-2026-llm
%X Neural audio codecs are widely used as tokenizers for spoken language models, but they are optimized for waveform reconstruction rather than autoregressive prediction.This mismatch injects acoustically driven uncertainty into the discrete token space and increases language-model perplexity.We propose , which augments codec training with language-model-facing objectives while keeping both codec and LLM architectures unchanged.introduces (i) future token prediction with Medusa-style multi-step heads to encourage multi-step predictability, and (ii) semantic alignment that matches audio and text representations via a memory-bank contrastive loss.A differentiable Gumbel bridge enables end-to-end gradients from these objectives to the codec encoder.On SALMon speech coherence, token LMs trained on reach 61.6% accuracy (+12.1 points over AUV) while reducing perplexity 35\times.On Codec-SUPERB-tiny, improves speech Mel distance by 5.0% over AUV while simultaneously achieving the learnability gains, demonstrating that reconstruction fidelity and token predictability can be improved together.
%U https://aclanthology.org/2026.findings-acl.1308/
%P 26251-26265

Markdown (Informal)

[LLM-Codec: Neural Audio Codec Meets Language Model Objectives](https://aclanthology.org/2026.findings-acl.1308/) (Chung et al., Findings 2026)

• LLM-Codec: Neural Audio Codec Meets Language Model Objectives (Chung et al., Findings 2026)

ACL

• Ho-Lam Chung, Yiming Chen, and Hung-yi Lee. 2026. LLM-Codec: Neural Audio Codec Meets Language Model Objectives. In Findings of the Association for Computational Linguistics: ACL 2026, pages 26251–26265, San Diego, California, United States. Association for Computational Linguistics.