@inproceedings{shim-etal-2026-whisper,
title = "Whisper-Style Speech Encoders Align Semantically Beyond Phonetic Cues",
author = "Shim, Ryan Soh-Eun and
de Cristofaro, Domenico and
Hu, Chengzhi Martin and
Vietti, Alessandro and
Plank, Barbara",
editor = "Adelani, David Ifeoluwa and
Alabi, Jesujoba and
Arnett, Catherine and
Chang, Tyler and
Downey, C.M. and
Goldman, Omer and
Li, Senyu and
Miranda, Lester James Validad and
Qi, Jirui and
Stap, David and
Winata, Genta Indra and
Zhang, Xinyu Crystina",
booktitle = "Proceedings of the 6th Workshop on Multilingual Representation Learning ({MRL} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mrl-1.32/",
pages = "394--403",
ISBN = "979-8-89176-469-9",
abstract = "Recent work suggests that Whisper-style speech encoders exhibit semantic alignment across languages, based on spoken translation retrieval using representational similarity. If so, this would enable Whisper-style encoders as a viable way to obtain acoustic representations with semantic knowledge, enabling downstream semantic tasks with speech input. However, prior work does not control for phonetic overlap between equivalent utterances, which may artificially support retrieval. We therefore conduct pronunciation-controlled experiments to test whether cross-lingual alignment arises from semantic rather than phonetic similarity, and further probe semantic information in the encoder by way of lexical semantic analogy tasks. Results show that spoken translation retrieval remains strongly above chance with substantially reduced phonetic cues in the final layers of Whisper{'}s encoder. Furthermore, for both word-level and utterance-level input, Whisper{'}s encoder representations exhibit non-trivial analogy performance, attaining as high as 25.98{\%} accuracy in an analogy test set. Motivated by this layerwise semantic specialization, we test whether earlier encoder layers preserve representations better suited to ASR in unsupported low-resource languages. Our results confirm it to enable performance gains in automatic speech recognition on low-resource languages unseen during training."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shim-etal-2026-whisper">
<titleInfo>
<title>Whisper-Style Speech Encoders Align Semantically Beyond Phonetic Cues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="given">Soh-Eun</namePart>
<namePart type="family">Shim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Domenico</namePart>
<namePart type="family">de Cristofaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengzhi</namePart>
<namePart type="given">Martin</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Vietti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Arnett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Downey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="given">Validad</namePart>
<namePart type="family">Miranda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jirui</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Stap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="given">Crystina</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-469-9</identifier>
</relatedItem>
<abstract>Recent work suggests that Whisper-style speech encoders exhibit semantic alignment across languages, based on spoken translation retrieval using representational similarity. If so, this would enable Whisper-style encoders as a viable way to obtain acoustic representations with semantic knowledge, enabling downstream semantic tasks with speech input. However, prior work does not control for phonetic overlap between equivalent utterances, which may artificially support retrieval. We therefore conduct pronunciation-controlled experiments to test whether cross-lingual alignment arises from semantic rather than phonetic similarity, and further probe semantic information in the encoder by way of lexical semantic analogy tasks. Results show that spoken translation retrieval remains strongly above chance with substantially reduced phonetic cues in the final layers of Whisper’s encoder. Furthermore, for both word-level and utterance-level input, Whisper’s encoder representations exhibit non-trivial analogy performance, attaining as high as 25.98% accuracy in an analogy test set. Motivated by this layerwise semantic specialization, we test whether earlier encoder layers preserve representations better suited to ASR in unsupported low-resource languages. Our results confirm it to enable performance gains in automatic speech recognition on low-resource languages unseen during training.</abstract>
<identifier type="citekey">shim-etal-2026-whisper</identifier>
<location>
<url>https://aclanthology.org/2026.mrl-1.32/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>394</start>
<end>403</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Whisper-Style Speech Encoders Align Semantically Beyond Phonetic Cues
%A Shim, Ryan Soh-Eun
%A de Cristofaro, Domenico
%A Hu, Chengzhi Martin
%A Vietti, Alessandro
%A Plank, Barbara
%Y Adelani, David Ifeoluwa
%Y Alabi, Jesujoba
%Y Arnett, Catherine
%Y Chang, Tyler
%Y Downey, C. M.
%Y Goldman, Omer
%Y Li, Senyu
%Y Miranda, Lester James Validad
%Y Qi, Jirui
%Y Stap, David
%Y Winata, Genta Indra
%Y Zhang, Xinyu Crystina
%S Proceedings of the 6th Workshop on Multilingual Representation Learning (MRL 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-469-9
%F shim-etal-2026-whisper
%X Recent work suggests that Whisper-style speech encoders exhibit semantic alignment across languages, based on spoken translation retrieval using representational similarity. If so, this would enable Whisper-style encoders as a viable way to obtain acoustic representations with semantic knowledge, enabling downstream semantic tasks with speech input. However, prior work does not control for phonetic overlap between equivalent utterances, which may artificially support retrieval. We therefore conduct pronunciation-controlled experiments to test whether cross-lingual alignment arises from semantic rather than phonetic similarity, and further probe semantic information in the encoder by way of lexical semantic analogy tasks. Results show that spoken translation retrieval remains strongly above chance with substantially reduced phonetic cues in the final layers of Whisper’s encoder. Furthermore, for both word-level and utterance-level input, Whisper’s encoder representations exhibit non-trivial analogy performance, attaining as high as 25.98% accuracy in an analogy test set. Motivated by this layerwise semantic specialization, we test whether earlier encoder layers preserve representations better suited to ASR in unsupported low-resource languages. Our results confirm it to enable performance gains in automatic speech recognition on low-resource languages unseen during training.
%U https://aclanthology.org/2026.mrl-1.32/
%P 394-403
Markdown (Informal)
[Whisper-Style Speech Encoders Align Semantically Beyond Phonetic Cues](https://aclanthology.org/2026.mrl-1.32/) (Shim et al., MRL 2026)
ACL