@inproceedings{mittal-etal-2025-recast,
title = "{RECAST}: Retrieval-Augmented Contextual {ASR} via Decoder-State Keyword Spotting",
author = "Mittal, Ashish and
Sarawagi, Sunita and
Jyothi, Preethi",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.203/",
pages = "3780--3793",
ISBN = "979-8-89176-335-7",
abstract = "Contextual biasing in ASR systems is critical for recognizing rare, domain-specific terms but becomes impractical with large keyword dictionaries due to prompt size and latency constraints. We present RECAST{--}a lightweight retrieval-augmented approach that repurposes decoder states of a pretrained ASR model to retrieve relevant keywords without requiring audio exemplars. RECAST introduces a contrastively trained retriever that aligns decoder-state embeddings with textual keyword representations, enabling fast token-level retrieval over large dictionaries. Retrieved keywords are ranked and formatted into a prompt to guide a downstream speech language model. Trained solely on LibriSpeech and evaluated on out-of-domain benchmarks covering up to 4,000 keywords across diverse domains, RECAST consistently outperforms full-list prompt biasing and strong phonetic/text baselines. It achieves up to 54.3{\%} relative reduction in entity WER and 41.3{\%} overall WER improvement over the baseline, along with up to 2.5x higher recall in challenging settings. Furthermore, RECAST remains effective for diverse languages such as Hindi, demonstrating its scalability, language-agnostic design, and practicality for real-world contextual ASR."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mittal-etal-2025-recast">
<titleInfo>
<title>RECAST: Retrieval-Augmented Contextual ASR via Decoder-State Keyword Spotting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunita</namePart>
<namePart type="family">Sarawagi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Jyothi</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>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Contextual biasing in ASR systems is critical for recognizing rare, domain-specific terms but becomes impractical with large keyword dictionaries due to prompt size and latency constraints. We present RECAST–a lightweight retrieval-augmented approach that repurposes decoder states of a pretrained ASR model to retrieve relevant keywords without requiring audio exemplars. RECAST introduces a contrastively trained retriever that aligns decoder-state embeddings with textual keyword representations, enabling fast token-level retrieval over large dictionaries. Retrieved keywords are ranked and formatted into a prompt to guide a downstream speech language model. Trained solely on LibriSpeech and evaluated on out-of-domain benchmarks covering up to 4,000 keywords across diverse domains, RECAST consistently outperforms full-list prompt biasing and strong phonetic/text baselines. It achieves up to 54.3% relative reduction in entity WER and 41.3% overall WER improvement over the baseline, along with up to 2.5x higher recall in challenging settings. Furthermore, RECAST remains effective for diverse languages such as Hindi, demonstrating its scalability, language-agnostic design, and practicality for real-world contextual ASR.</abstract>
<identifier type="citekey">mittal-etal-2025-recast</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.203/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>3780</start>
<end>3793</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RECAST: Retrieval-Augmented Contextual ASR via Decoder-State Keyword Spotting
%A Mittal, Ashish
%A Sarawagi, Sunita
%A Jyothi, Preethi
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F mittal-etal-2025-recast
%X Contextual biasing in ASR systems is critical for recognizing rare, domain-specific terms but becomes impractical with large keyword dictionaries due to prompt size and latency constraints. We present RECAST–a lightweight retrieval-augmented approach that repurposes decoder states of a pretrained ASR model to retrieve relevant keywords without requiring audio exemplars. RECAST introduces a contrastively trained retriever that aligns decoder-state embeddings with textual keyword representations, enabling fast token-level retrieval over large dictionaries. Retrieved keywords are ranked and formatted into a prompt to guide a downstream speech language model. Trained solely on LibriSpeech and evaluated on out-of-domain benchmarks covering up to 4,000 keywords across diverse domains, RECAST consistently outperforms full-list prompt biasing and strong phonetic/text baselines. It achieves up to 54.3% relative reduction in entity WER and 41.3% overall WER improvement over the baseline, along with up to 2.5x higher recall in challenging settings. Furthermore, RECAST remains effective for diverse languages such as Hindi, demonstrating its scalability, language-agnostic design, and practicality for real-world contextual ASR.
%U https://aclanthology.org/2025.findings-emnlp.203/
%P 3780-3793
Markdown (Informal)
[RECAST: Retrieval-Augmented Contextual ASR via Decoder-State Keyword Spotting](https://aclanthology.org/2025.findings-emnlp.203/) (Mittal et al., Findings 2025)
ACL