@inproceedings{guo-etal-2025-effective,
title = "Effective Speaker Diarization Leveraging Multi-task Logarithmic Loss Objectives",
author = "Guo, Jhih-Rong and
Lo, Tien-Hong and
Tsao, Yu-Sheng and
Lee, Pei-Ying and
Hsu, Yung-Chang and
Chen, Berlin",
editor = "Chang, Kai-Wei and
Lu, Ke-Han and
Yang, Chih-Kai and
Tam, Zhi-Rui and
Chang, Wen-Yu and
Wang, Chung-Che",
booktitle = "Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)",
month = nov,
year = "2025",
address = "National Taiwan University, Taipei City, Taiwan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.rocling-main.17/",
pages = "140--145",
ISBN = "979-8-89176-379-1",
abstract = "End-to-End Neural Diarization (EEND) has undergone substantial development, particularly with powerset classification methods that enhance performance but can exacerbate speaker confusion. To address this, we propose a novel training strategy that complements the standard cross entropy loss with an auxiliary ordinal log loss, guided by a distance matrix of speaker combinations. Our experiments reveal that while this approach yields significant relative improvements of 15.8{\%} in false alarm rate and 10.0{\%} in confusion error rate, it also uncovers a critical trade-off with an increased missed error rate. The primary contribution of this work is the identification and analysis of this trade-off, which stems from the model adopting a more conservative prediction strategy. This insight is crucial for designing more balanced and effective loss functions in speaker diarization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2025-effective">
<titleInfo>
<title>Effective Speaker Diarization Leveraging Multi-task Logarithmic Loss Objectives</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jhih-Rong</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tien-Hong</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Sheng</namePart>
<namePart type="family">Tsao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pei-Ying</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yung-Chang</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berlin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ke-Han</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chih-Kai</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhi-Rui</namePart>
<namePart type="family">Tam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen-Yu</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Che</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">National Taiwan University, Taipei City, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-379-1</identifier>
</relatedItem>
<abstract>End-to-End Neural Diarization (EEND) has undergone substantial development, particularly with powerset classification methods that enhance performance but can exacerbate speaker confusion. To address this, we propose a novel training strategy that complements the standard cross entropy loss with an auxiliary ordinal log loss, guided by a distance matrix of speaker combinations. Our experiments reveal that while this approach yields significant relative improvements of 15.8% in false alarm rate and 10.0% in confusion error rate, it also uncovers a critical trade-off with an increased missed error rate. The primary contribution of this work is the identification and analysis of this trade-off, which stems from the model adopting a more conservative prediction strategy. This insight is crucial for designing more balanced and effective loss functions in speaker diarization.</abstract>
<identifier type="citekey">guo-etal-2025-effective</identifier>
<location>
<url>https://aclanthology.org/2025.rocling-main.17/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>140</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effective Speaker Diarization Leveraging Multi-task Logarithmic Loss Objectives
%A Guo, Jhih-Rong
%A Lo, Tien-Hong
%A Tsao, Yu-Sheng
%A Lee, Pei-Ying
%A Hsu, Yung-Chang
%A Chen, Berlin
%Y Chang, Kai-Wei
%Y Lu, Ke-Han
%Y Yang, Chih-Kai
%Y Tam, Zhi-Rui
%Y Chang, Wen-Yu
%Y Wang, Chung-Che
%S Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C National Taiwan University, Taipei City, Taiwan
%@ 979-8-89176-379-1
%F guo-etal-2025-effective
%X End-to-End Neural Diarization (EEND) has undergone substantial development, particularly with powerset classification methods that enhance performance but can exacerbate speaker confusion. To address this, we propose a novel training strategy that complements the standard cross entropy loss with an auxiliary ordinal log loss, guided by a distance matrix of speaker combinations. Our experiments reveal that while this approach yields significant relative improvements of 15.8% in false alarm rate and 10.0% in confusion error rate, it also uncovers a critical trade-off with an increased missed error rate. The primary contribution of this work is the identification and analysis of this trade-off, which stems from the model adopting a more conservative prediction strategy. This insight is crucial for designing more balanced and effective loss functions in speaker diarization.
%U https://aclanthology.org/2025.rocling-main.17/
%P 140-145
Markdown (Informal)
[Effective Speaker Diarization Leveraging Multi-task Logarithmic Loss Objectives](https://aclanthology.org/2025.rocling-main.17/) (Guo et al., ROCLING 2025)
ACL