# How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMs

arXiv: https://arxiv.org/abs/2608.05759 · HTML: https://mlsanity.com/paper/2608.05759/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://mlsanity.com/paper/2008.00401/) (2020)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [An analysis of incorporating an external language model into a sequence-to-sequence model](https://mlsanity.com/paper/1712.01996/) (2017)
- [WavLLM: Towards Robust and Adaptive Speech Large Language Model](https://mlsanity.com/paper/2404.00656/) (2024)
- [Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion](https://mlsanity.com/paper/2104.02194/) (2021)
- [Cold Fusion: Training Seq2Seq Models Together with Language Models](https://mlsanity.com/paper/1708.06426/) (2017)
- [Contextual RNN-T For Open Domain ASR](https://mlsanity.com/paper/2006.03411/) (2020)
- [Earnings-21: A Practical Benchmark for ASR in the Wild](https://mlsanity.com/paper/2104.11348/) (2021)
- [YODAS: Youtube-Oriented Dataset for Audio and Speech](https://mlsanity.com/paper/2406.00899/) (2024)
- [Very Deep Self-Attention Networks for End-to-End Speech Recognition](https://mlsanity.com/paper/1904.13377/) (2019)
- [Class LM and word mapping for contextual biasing in End-to-End ASR](https://mlsanity.com/paper/2007.05609/) (2020)
- [Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection](https://mlsanity.com/paper/2201.12806/) (2022)
- [Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network](https://mlsanity.com/paper/2305.12493/) (2023)
- [Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition](https://mlsanity.com/paper/2107.02268/) (2021)
- [End-to-End Speech Recognition Contextualization with Large Language Models](https://mlsanity.com/paper/2309.10917/) (2023)
- [PromptASR for contextualized ASR with controllable style](https://mlsanity.com/paper/2309.07414/) (2023)
- [Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search](https://mlsanity.com/paper/2401.10449/) (2024)
- [VIBEVOICE-ASR Technical Report](https://mlsanity.com/paper/2601.18184/) (2026)
- [LCB-net: Long-Context Biasing for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2401.06390/) (2024)
- [OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary](https://mlsanity.com/paper/2506.09448/) (2025)

## Built on by (most cited first, 1 of 1)

- [Talk2Agent: Benchmarking Voice Interfaces for Text Agents](https://mlsanity.com/paper/2609.38867/) (2026)

## Abstract (arXiv)

Recognizing new and rare words - named entities, acronyms, domain specific special words, and other items scarce in training data - remains a key challenge for automatic speech recognition (ASR). We compare two strategies for this: context biasing methods, where an ASR model is extended such that during inference a word list can be supplied, and speech large language models (LLMs) prompted with context directly. We evaluate two context biasing methods based on Whisper against three speech LLMs across read and non-read speech, reporting biased, unbiased, and overall word error rate (WER). The context biasing methods cut biased WER by up to 88% relative while leaving other words largely unaffected. Speech LLMs excel on read speech but generalize less well to non-read speech, and prove sensitive to distractor count and prompt word order. We characterize the resulting trade-offs to guide method selection.