# Fast and Robust Unsupervised Contextual Biasing for Speech Recognition

arXiv: https://arxiv.org/abs/2005.01677 · HTML: https://mlsanity.com/paper/2005.01677/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2020.

## Built on by (most cited first, 7 of 7)

- [Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition](https://mlsanity.com/paper/2109.00627/) (2021)
- [Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition](https://mlsanity.com/paper/2207.00857/) (2022)
- [Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator](https://mlsanity.com/paper/2205.09058/) (2022)
- [Spell my name: keyword boosted speech recognition](https://mlsanity.com/paper/2110.02791/) (2021)
- [Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generator](https://mlsanity.com/paper/2305.18824/) (2023)
- [Can Visual Context Improve Automatic Speech Recognition for an Embodied Agent?](https://mlsanity.com/paper/2210.13189/) (2022)
- [Locality enhanced dynamic biasing and sampling strategies for contextual ASR](https://mlsanity.com/paper/2401.13146/) (2024)

## Abstract (arXiv)

Automatic speech recognition (ASR) system is becoming a ubiquitous technology. Although its accuracy is closing the gap with that of human level under certain settings, one area that can further improve is to incorporate user-specific information or context to bias its prediction. A common framework is to dynamically construct a small language model from the provided contextual mini corpus and interpolate its score with the main language model during the decoding process. Here we propose an alternative approach that does not entail explicit contextual language model. Instead, we derive the bias score for every word in the system vocabulary from the training corpus. The method is unique in that 1) it does not require meta-data or class-label annotation for the context or the training corpus. 2) The bias score is proportional to the word's log-probability, thus not only would it bias the provided context, but also robust against irrelevant context (e.g. user mis-specified or in case where it is hard to quantify a tight scope). 3) The bias score for the entire vocabulary is pre-determined during the training stage, thereby eliminating computationally expensive language model construction during inference. We show significant improvement in recognition accuracy when the relevant context is available. Additionally, we also demonstrate that the proposed method exhibits high tolerance to false-triggering errors in the presence of irrelevant context.