@inproceedings{dutta-vishwakarma-2026-cbal,
title = "{CBAL}: Context-Based Agentic Learning for Speaker Diarization Segmentation Refinement",
author = "Dutta, Odwitiyo and
Vishwakarma, Dinesh K",
editor = "T.Y.S.S., Santosh and
Rodriguez, Juan Diego and
de Gibert, Ona",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-srw.58/",
pages = "632--647",
ISBN = "979-8-89176-393-7",
abstract = "Speaker diarization systems produce segmentation errors, such as false splits and boundary misplacements, that degrade transcript readability and downstream applications. We present CBAL (Context-Based Agentic Learning), a post-processing framework that refines segmentation boundaries in diarized scripts through targeted error correction. CBAL detects potential segmentation errors using acoustic and temporal heuristics and employs a lightweight LLM agent to reason about merge decisions, validating corrections through uncertainty-aware filtering with signal-based constraints. CBAL achieves 93.4{\%} accuracy across 359 applied merges and reduces segment count by 6.1{\%}. We demonstrate that our framework identifies and corrects high-confidence errors while maintaining 0{\%} degradation in terms of concatenated minimum-permutation Word Error Rate (cpWER). An ablation study confirms that each component contributes non-redundantly, demonstrating the viability of interpretable refinement frameworks that use the strengths of acoustic models and language understanding without requiring end-to-end retraining."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dutta-vishwakarma-2026-cbal">
<titleInfo>
<title>CBAL: Context-Based Agentic Learning for Speaker Diarization Segmentation Refinement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Odwitiyo</namePart>
<namePart type="family">Dutta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dinesh</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Vishwakarma</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 (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Diego</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">de Gibert</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">979-8-89176-393-7</identifier>
</relatedItem>
<abstract>Speaker diarization systems produce segmentation errors, such as false splits and boundary misplacements, that degrade transcript readability and downstream applications. We present CBAL (Context-Based Agentic Learning), a post-processing framework that refines segmentation boundaries in diarized scripts through targeted error correction. CBAL detects potential segmentation errors using acoustic and temporal heuristics and employs a lightweight LLM agent to reason about merge decisions, validating corrections through uncertainty-aware filtering with signal-based constraints. CBAL achieves 93.4% accuracy across 359 applied merges and reduces segment count by 6.1%. We demonstrate that our framework identifies and corrects high-confidence errors while maintaining 0% degradation in terms of concatenated minimum-permutation Word Error Rate (cpWER). An ablation study confirms that each component contributes non-redundantly, demonstrating the viability of interpretable refinement frameworks that use the strengths of acoustic models and language understanding without requiring end-to-end retraining.</abstract>
<identifier type="citekey">dutta-vishwakarma-2026-cbal</identifier>
<location>
<url>https://aclanthology.org/2026.acl-srw.58/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>632</start>
<end>647</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CBAL: Context-Based Agentic Learning for Speaker Diarization Segmentation Refinement
%A Dutta, Odwitiyo
%A Vishwakarma, Dinesh K.
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F dutta-vishwakarma-2026-cbal
%X Speaker diarization systems produce segmentation errors, such as false splits and boundary misplacements, that degrade transcript readability and downstream applications. We present CBAL (Context-Based Agentic Learning), a post-processing framework that refines segmentation boundaries in diarized scripts through targeted error correction. CBAL detects potential segmentation errors using acoustic and temporal heuristics and employs a lightweight LLM agent to reason about merge decisions, validating corrections through uncertainty-aware filtering with signal-based constraints. CBAL achieves 93.4% accuracy across 359 applied merges and reduces segment count by 6.1%. We demonstrate that our framework identifies and corrects high-confidence errors while maintaining 0% degradation in terms of concatenated minimum-permutation Word Error Rate (cpWER). An ablation study confirms that each component contributes non-redundantly, demonstrating the viability of interpretable refinement frameworks that use the strengths of acoustic models and language understanding without requiring end-to-end retraining.
%U https://aclanthology.org/2026.acl-srw.58/
%P 632-647
Markdown (Informal)
[CBAL: Context-Based Agentic Learning for Speaker Diarization Segmentation Refinement](https://aclanthology.org/2026.acl-srw.58/) (Dutta & Vishwakarma, ACL 2026)
ACL