@inproceedings{pandey-etal-2026-whistle,
title = "{W}his{TLE}: Deeply Supervised, Text-Only Domain Adaptation for Small Pretrained Speech Recognition Transformers",
author = "Pandey, Akshat and
Kumar, Karun and
Tang, Raphael",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2516/",
pages = "57220--57230",
ISBN = "979-8-89176-459-0",
abstract = "Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance. In many real-world settings, collecting speech data is impractical, necessitating text-only adaptation. We propose WhisTLE, a deeply supervised, text-only adaptation method for pretrained encoder{--}decoder ASR models. WhisTLE trains a variational autoencoder (VAE) to model encoder outputs from text and fine-tunes the decoder using the learned text-to-latent encoder, optionally combined with text-to-speech (TTS) adaptation. At inference, the original encoder is restored, incurring no extra runtime cost. Across four datasets and four ASR models, WhisTLE alone helps in 28 of 32 (88{\%}) cases, with an average relative WER drop of 22{\%}. Using WhisTLE alone or in combination with other adaptation approaches helps in 116 of 144 (81{\%}) cases, with an average additional WER drop of 15{\%}. Given all treatments that improve on baseline scores, WhisTLE helps in 45 of 55 (82{\%}) cases, with an average additional relative WER drop of 16{\%}. WhisTLE with TTS reduces word error rate (WER) by a relative 49{\%} and outperforms all non-WhisTLE baselines in 100 of 112 scenarios. We also find that WhisTLE additively complements any combination of other domain adaptation approaches; we thus recommend the inclusion of WhisTLE during standard processes for adapting encoder{--}decoder ASR models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pandey-etal-2026-whistle">
<titleInfo>
<title>WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Small Pretrained Speech Recognition Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akshat</namePart>
<namePart type="family">Pandey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karun</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raphael</namePart>
<namePart type="family">Tang</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance. In many real-world settings, collecting speech data is impractical, necessitating text-only adaptation. We propose WhisTLE, a deeply supervised, text-only adaptation method for pretrained encoder–decoder ASR models. WhisTLE trains a variational autoencoder (VAE) to model encoder outputs from text and fine-tunes the decoder using the learned text-to-latent encoder, optionally combined with text-to-speech (TTS) adaptation. At inference, the original encoder is restored, incurring no extra runtime cost. Across four datasets and four ASR models, WhisTLE alone helps in 28 of 32 (88%) cases, with an average relative WER drop of 22%. Using WhisTLE alone or in combination with other adaptation approaches helps in 116 of 144 (81%) cases, with an average additional WER drop of 15%. Given all treatments that improve on baseline scores, WhisTLE helps in 45 of 55 (82%) cases, with an average additional relative WER drop of 16%. WhisTLE with TTS reduces word error rate (WER) by a relative 49% and outperforms all non-WhisTLE baselines in 100 of 112 scenarios. We also find that WhisTLE additively complements any combination of other domain adaptation approaches; we thus recommend the inclusion of WhisTLE during standard processes for adapting encoder–decoder ASR models.</abstract>
<identifier type="citekey">pandey-etal-2026-whistle</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2516/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>57220</start>
<end>57230</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Small Pretrained Speech Recognition Transformers
%A Pandey, Akshat
%A Kumar, Karun
%A Tang, Raphael
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F pandey-etal-2026-whistle
%X Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance. In many real-world settings, collecting speech data is impractical, necessitating text-only adaptation. We propose WhisTLE, a deeply supervised, text-only adaptation method for pretrained encoder–decoder ASR models. WhisTLE trains a variational autoencoder (VAE) to model encoder outputs from text and fine-tunes the decoder using the learned text-to-latent encoder, optionally combined with text-to-speech (TTS) adaptation. At inference, the original encoder is restored, incurring no extra runtime cost. Across four datasets and four ASR models, WhisTLE alone helps in 28 of 32 (88%) cases, with an average relative WER drop of 22%. Using WhisTLE alone or in combination with other adaptation approaches helps in 116 of 144 (81%) cases, with an average additional WER drop of 15%. Given all treatments that improve on baseline scores, WhisTLE helps in 45 of 55 (82%) cases, with an average additional relative WER drop of 16%. WhisTLE with TTS reduces word error rate (WER) by a relative 49% and outperforms all non-WhisTLE baselines in 100 of 112 scenarios. We also find that WhisTLE additively complements any combination of other domain adaptation approaches; we thus recommend the inclusion of WhisTLE during standard processes for adapting encoder–decoder ASR models.
%U https://aclanthology.org/2026.emnlp-main.2516/
%P 57220-57230
Markdown (Informal)
[WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Small Pretrained Speech Recognition Transformers](https://aclanthology.org/2026.emnlp-main.2516/) (Pandey et al., EMNLP 2026)
ACL