@inproceedings{huang-etal-2026-cspb,
title = "{CSPB}: Conversational Speech Processing Benchmark for Self-supervised Speech Models",
author = "Huang, Zili and
Maciejewski, Matthew and
Garcia Perera, Leibny Paola and
Watanabe, Shinji and
Khudanpur, Sanjeev",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.275/",
pages = "5878--5893",
ISBN = "979-8-89176-380-7",
abstract = "Recent advances in self-supervised learning (SSL) have led to powerful speech representation models, yet their robustness in real-world conversational settings remains largely untested. Most existing benchmarks focus on clean, single-speaker, single-channel audio, failing to reflect the complexities of natural human interaction{---}where background noise, reverberation, and overlapping speech are the norm. To bridge these critical gaps, we present the Conversational Speech Processing Benchmark (CSPB), a new benchmark designed to assess the robustness of SSL speech models in realistic conversational scenarios. CSPB is constructed from four multi-party datasets{---}AMI, AliMeeting, MMCSG, and DiPCo{---}and supports both single-channel and multi-channel evaluation. By releasing CSPB as an open-source toolkit, we aim to establish a unified framework for evaluating and advancing robust, spatially-aware self-supervised speech models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-cspb">
<titleInfo>
<title>CSPB: Conversational Speech Processing Benchmark for Self-supervised Speech Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zili</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Maciejewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leibny</namePart>
<namePart type="given">Paola</namePart>
<namePart type="family">Garcia Perera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinji</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjeev</namePart>
<namePart type="family">Khudanpur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>Recent advances in self-supervised learning (SSL) have led to powerful speech representation models, yet their robustness in real-world conversational settings remains largely untested. Most existing benchmarks focus on clean, single-speaker, single-channel audio, failing to reflect the complexities of natural human interaction—where background noise, reverberation, and overlapping speech are the norm. To bridge these critical gaps, we present the Conversational Speech Processing Benchmark (CSPB), a new benchmark designed to assess the robustness of SSL speech models in realistic conversational scenarios. CSPB is constructed from four multi-party datasets—AMI, AliMeeting, MMCSG, and DiPCo—and supports both single-channel and multi-channel evaluation. By releasing CSPB as an open-source toolkit, we aim to establish a unified framework for evaluating and advancing robust, spatially-aware self-supervised speech models.</abstract>
<identifier type="citekey">huang-etal-2026-cspb</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.275/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>5878</start>
<end>5893</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CSPB: Conversational Speech Processing Benchmark for Self-supervised Speech Models
%A Huang, Zili
%A Maciejewski, Matthew
%A Garcia Perera, Leibny Paola
%A Watanabe, Shinji
%A Khudanpur, Sanjeev
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F huang-etal-2026-cspb
%X Recent advances in self-supervised learning (SSL) have led to powerful speech representation models, yet their robustness in real-world conversational settings remains largely untested. Most existing benchmarks focus on clean, single-speaker, single-channel audio, failing to reflect the complexities of natural human interaction—where background noise, reverberation, and overlapping speech are the norm. To bridge these critical gaps, we present the Conversational Speech Processing Benchmark (CSPB), a new benchmark designed to assess the robustness of SSL speech models in realistic conversational scenarios. CSPB is constructed from four multi-party datasets—AMI, AliMeeting, MMCSG, and DiPCo—and supports both single-channel and multi-channel evaluation. By releasing CSPB as an open-source toolkit, we aim to establish a unified framework for evaluating and advancing robust, spatially-aware self-supervised speech models.
%U https://aclanthology.org/2026.eacl-long.275/
%P 5878-5893
Markdown (Informal)
[CSPB: Conversational Speech Processing Benchmark for Self-supervised Speech Models](https://aclanthology.org/2026.eacl-long.275/) (Huang et al., EACL 2026)
ACL