# Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation

arXiv: https://arxiv.org/abs/2407.10303 · HTML: https://mlsanity.com/paper/2407.10303/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 42 references that are in the map.
- First posted on arXiv 14 Jul 2024.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion](https://mlsanity.com/paper/2104.02194/) (2021)
- [Contextual RNN-T For Open Domain ASR](https://mlsanity.com/paper/2006.03411/) (2020)
- [Zipformer: A faster and better encoder for automatic speech recognition](https://mlsanity.com/paper/2310.11230/) (2023)
- [SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition](https://mlsanity.com/paper/2104.02014/) (2021)
- [SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation](https://mlsanity.com/paper/2310.09424/) (2023)
- [Deep Shallow Fusion for RNN-T Personalization](https://mlsanity.com/paper/2011.07754/) (2020)
- [Earnings-21: A Practical Benchmark for ASR in the Wild](https://mlsanity.com/paper/2104.11348/) (2021)
- [Contextual Adapters for Personalized Speech Recognition in Neural Transducers](https://mlsanity.com/paper/2205.13660/) (2022)
- [Context-Aware Transformer Transducer for Speech Recognition](https://mlsanity.com/paper/2111.03250/) (2021)
- [Class LM and word mapping for contextual biasing in End-to-End ASR](https://mlsanity.com/paper/2007.05609/) (2020)
- [Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition](https://mlsanity.com/paper/2107.02268/) (2021)
- [Contextual Speech Recognition with Difficult Negative Training Examples](https://mlsanity.com/paper/1810.12170/) (2018)
- [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)
- [Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems](https://mlsanity.com/paper/2203.00888/) (2022)
- [Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Model](https://mlsanity.com/paper/2209.01250/) (2022)
- [Improving ASR Contextual Biasing with Guided Attention](https://mlsanity.com/paper/2401.08835/) (2024)
- [Phoneme-aware Encoding for Prefix-tree-based Contextual ASR](https://mlsanity.com/paper/2312.09582/) (2023)
- [G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR](https://mlsanity.com/paper/1910.12612/) (2019)
- [Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator](https://mlsanity.com/paper/2205.09058/) (2022)
- [PROCTER: PROnunciation-aware ConTextual adaptER for personalized speech recognition in neural transducers](https://mlsanity.com/paper/2303.17131/) (2023)
- [Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm](https://mlsanity.com/paper/2310.00178/) (2023)
- [Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks](https://mlsanity.com/paper/2401.02921/) (2024)
- [End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention system](https://mlsanity.com/paper/2202.09003/) (2022)
- [Contextual Biasing of Named-Entities with Large Language Models](https://mlsanity.com/paper/2309.00723/) (2023)
- [Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization](https://mlsanity.com/paper/2310.09988/) (2023)

## Built on by (most cited first, 11 of 11)

- [TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree](https://mlsanity.com/paper/2508.07014/) (2025)
- [Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval](https://mlsanity.com/paper/2411.00664/) (2024)
- [PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decoding](https://mlsanity.com/paper/2506.11064/) (2025)
- [PAC: Pronunciation-Aware Contextualized Large Language Model-based Automatic Speech Recognition](https://mlsanity.com/paper/2509.12647/) (2025)
- [Retrieval Augmented Generation based context discovery for ASR](https://mlsanity.com/paper/2509.19567/) (2025)
- [A Neural Model for Contextual Biasing Score Learning and Filtering](https://mlsanity.com/paper/2510.23849/) (2025)
- [MGSC: A Multi-granularity Consistency Framework for Robust End-to-end Asr](https://mlsanity.com/paper/2508.15853/) (2025)
- [PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation](https://mlsanity.com/paper/2509.04357/) (2025)
- [Peeking Into The Future For Contextual Biasing](https://mlsanity.com/paper/2512.17657/) (2025)
- [From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMs](https://mlsanity.com/paper/2603.24034/) (2026)
- [TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems](https://mlsanity.com/paper/2608.21343/) (2026)

## Abstract (arXiv)

Existing research suggests that automatic speech recognition (ASR) models can benefit from additional contexts (e.g., contact lists, user specified vocabulary). Rare words and named entities can be better recognized with contexts. In this work, we propose two simple yet effective techniques to improve context-aware ASR models. First, we inject contexts into the encoders at an early stage instead of merely at their last layers. Second, to enforce the model to leverage the contexts during training, we perturb the reference transcription with alternative spellings so that the model learns to rely on the contexts to make correct predictions. On LibriSpeech, our techniques together reduce the rare word error rate by 60% and 25% relatively compared to no biasing and shallow fusion, making the new state-of-the-art performance. On SPGISpeech and a real-world dataset ConEC, our techniques also yield good improvements over the baselines.