# Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducer

arXiv: https://arxiv.org/abs/2301.06735 · HTML: https://mlsanity.com/paper/2301.06735/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 17 Jan 2023.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [On Using Monolingual Corpora in Neural Machine Translation](https://mlsanity.com/paper/1503.03535/) (2015)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [Contextual RNN-T For Open Domain ASR](https://mlsanity.com/paper/2006.03411/) (2020)
- [Context-Aware Transformer Transducer for Speech Recognition](https://mlsanity.com/paper/2111.03250/) (2021)
- [Cascaded encoders for unifying streaming and non-streaming ASR](https://mlsanity.com/paper/2010.14606/) (2020)
- [Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection](https://mlsanity.com/paper/2201.12806/) (2022)
- [Tiny Transducer: A Highly-efficient Speech Recognition Model on Edge Devices](https://mlsanity.com/paper/2101.06856/) (2021)

## Built on by (most cited first, 12 of 12)

- [Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network](https://mlsanity.com/paper/2305.12493/) (2023)
- [CTC-Assisted LLM-Based Contextual ASR](https://mlsanity.com/paper/2411.06437/) (2024)
- [Improving ASR Contextual Biasing with Guided Attention](https://mlsanity.com/paper/2401.08835/) (2024)
- [CopyNE: Better Contextual ASR by Copying Named Entities](https://mlsanity.com/paper/2305.12839/) (2023)
- [Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognition](https://mlsanity.com/paper/2306.00804/) (2023)
- [Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning](https://mlsanity.com/paper/2506.05671/) (2025)
- [Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR](https://mlsanity.com/paper/2404.10180/) (2024)
- [SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings](https://mlsanity.com/paper/2306.02317/) (2023)
- [Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval](https://mlsanity.com/paper/2411.00664/) (2024)
- [CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models](https://mlsanity.com/paper/2506.12059/) (2025)
- [Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modeling](https://mlsanity.com/paper/2509.05908/) (2025)
- [H-PRM: A Pluggable Hotword Pre-Retrieval Module for Various Speech Recognition Systems](https://mlsanity.com/paper/2508.18295/) (2025)

## Abstract (arXiv)

It is difficult for an E2E ASR system to recognize words such as entities appearing infrequently in the training data. A widely used method to mitigate this issue is feeding contextual information into the acoustic model. Previous works have proven that a compact and accurate contextual list can boost the performance significantly. In this paper, we propose an efficient approach to obtain a high quality contextual list for a unified streaming/non-streaming based E2E model. Specifically, we make use of the phone-level streaming output to first filter the predefined contextual word list then fuse it into non-casual encoder and decoder to generate the final recognition results. Our approach improve the accuracy of the contextual ASR system and speed up the inference process. Experiments on two datasets demonstrates over 20% CER reduction comparing to the baseline system. Meanwhile, the RTF of our system can be stabilized within 0.15 when the size of the contextual word list grows over 6,000.