Unifying Global and Near-Context Biasing in a Single Trie Pass

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F26%3A0201441" target="_blank" >RIV/00216305:26230/26:0201441 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.fit.vut.cz/research/group/speech/public/publi/2025/Iuliia_TSD2025_2025_co-author_Motlicek.pdf" target="_blank" >https://www.fit.vut.cz/research/group/speech/public/publi/2025/Iuliia_TSD2025_2025_co-author_Motlicek.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-032-02548-7_15" target="_blank" >10.1007/978-3-032-02548-7_15</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Unifying Global and Near-Context Biasing in a Single Trie Pass

Popis výsledku v původním jazyce

Despite the success of end-to-end automatic speech recognition (ASR) models, challenges persist in recognizing rare, out-of-vocabulary wordsincluding named entities (NE)-and in adapting to new domains using only text data. This work presents a practical approach to address these challenges through an unexplored combination of an NE bias list and a word-level n-gram language model (LM). This solution balances simplicity and effectiveness, improving entities' recognition while maintaining or even enhancing overall ASR performance. We efficiently integrate this enriched biasing method into a transducer-based ASR system, enabling context adaptation with almost no computational overhead. We present our results on three datasets spanning four languages and compare them to state-of-the-art biasing strategies We demonstrate that the proposed combination of keyword biasing and n-gram LM improves entity recognition by up to 32% relative and reduces overall WER by up to a 12% relative.

Název v anglickém jazyce

Unifying Global and Near-Context Biasing in a Single Trie Pass

Popis výsledku anglicky

Despite the success of end-to-end automatic speech recognition (ASR) models, challenges persist in recognizing rare, out-of-vocabulary wordsincluding named entities (NE)-and in adapting to new domains using only text data. This work presents a practical approach to address these challenges through an unexplored combination of an NE bias list and a word-level n-gram language model (LM). This solution balances simplicity and effectiveness, improving entities' recognition while maintaining or even enhancing overall ASR performance. We efficiently integrate this enriched biasing method into a transducer-based ASR system, enabling context adaptation with almost no computational overhead. We present our results on three datasets spanning four languages and compare them to state-of-the-art biasing strategies We demonstrate that the proposed combination of keyword biasing and n-gram LM improves entity recognition by up to 32% relative and reduces overall WER by up to a 12% relative.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2026

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Lecture Notes in Artificial Intelligence

ISBN

978-3-032-02547-0

ISSN

—

e-ISSN

1611-3349

Počet stran výsledku

12

Strana od-do

170-181

Název nakladatele

Springer Nature

Místo vydání

CHAM

Místo konání akce

Nürmberg, Německo

Datum konání akce

25. 8. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001576343000015