Unifying Global and Near-Context Biasing in a Single Trie Pass.
| Type of publication: | Conference paper |
| Citation: | Iuliia_TSD2025_2025 |
| Booktitle: | Text, Speech, and Dialogue. TSD 2025. Lecture Notes in Computer Science, Springer |
| Volume: | 16029 |
| Year: | 2025 |
| Month: | August |
| Publisher: | Springer |
| ISBN: | 978-3-032-02547-0 |
| URL: | https://link.springer.com/chap... |
| DOI: | doi.org/10.1007/978-3-032-02548-7_15 |
| Abstract: | Despite the success of end-to-end automatic speech recognition (ASR) models, challenges persist in recognizing rare, out-of-vocabulary words—including 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. |
| Main Research Program: | Human-AI Teaming |
| Additional Research Programs: |
AI for Everyone |
| Keywords: | Aho-Corasick algorithm, Contextualisation and adaptation of ASR, real-time ASR, transformer transducer |
| Projects: |
Idiap |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
