# Deep Shallow Fusion for RNN-T Personalization

arXiv: https://arxiv.org/abs/2011.07754 · HTML: https://mlsanity.com/paper/2011.07754/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2020.

## Built on by (most cited first, 30 of 64)

- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion](https://mlsanity.com/paper/2104.02194/) (2021)
- [Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting](https://mlsanity.com/paper/2309.15649/) (2023)
- [Contextual Adapters for Personalized Speech Recognition in Neural Transducers](https://mlsanity.com/paper/2205.13660/) (2022)
- [Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding](https://mlsanity.com/paper/2104.02138/) (2021)
- [Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection](https://mlsanity.com/paper/2201.12806/) (2022)
- [Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition](https://mlsanity.com/paper/2109.00627/) (2021)
- [End-to-End Speech Recognition Contextualization with Large Language Models](https://mlsanity.com/paper/2309.10917/) (2023)
- [Can Contextual Biasing Remain Effective with Whisper and GPT-2?](https://mlsanity.com/paper/2306.01942/) (2023)
- [Dissecting User-Perceived Latency of On-Device E2E Speech Recognition](https://mlsanity.com/paper/2104.02207/) (2021)
- [Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition](https://mlsanity.com/paper/2305.05271/) (2023)
- [Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems](https://mlsanity.com/paper/2203.00888/) (2022)
- [Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition](https://mlsanity.com/paper/2207.00857/) (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)
- [A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems](https://mlsanity.com/paper/2108.07493/) (2021)
- [Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator](https://mlsanity.com/paper/2205.09058/) (2022)
- [CB-Conformer: Contextual biasing Conformer for biased word recognition](https://mlsanity.com/paper/2304.09607/) (2023)
- [Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation](https://mlsanity.com/paper/2407.10303/) (2024)
- [Spell my name: keyword boosted speech recognition](https://mlsanity.com/paper/2110.02791/) (2021)
- [Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Loss](https://mlsanity.com/paper/2406.16120/) (2024)
- [Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentation](https://mlsanity.com/paper/2302.11192/) (2023)
- [Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition](https://mlsanity.com/paper/2304.08862/) (2023)
- [Contextual Biasing of Named-Entities with Large Language Models](https://mlsanity.com/paper/2309.00723/) (2023)
- [ed-cec: improving rare word recognition using asr postprocessing based on error detection and context-aware error correction](https://mlsanity.com/paper/2310.05129/) (2023)
- [Neural-FST Class Language Model for End-to-End Speech Recognition](https://mlsanity.com/paper/2201.11867/) (2022)
- [End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator](https://mlsanity.com/paper/2210.16554/) (2022)
- [Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generator](https://mlsanity.com/paper/2305.18824/) (2023)
- [Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducer](https://mlsanity.com/paper/2311.08966/) (2023)

## Abstract (arXiv)

End-to-end models in general, and Recurrent Neural Network Transducer (RNN-T) in particular, have gained significant traction in the automatic speech recognition community in the last few years due to their simplicity, compactness, and excellent performance on generic transcription tasks. However, these models are more challenging to personalize compared to traditional hybrid systems due to the lack of external language models and difficulties in recognizing rare long-tail words, specifically entity names. In this work, we present novel techniques to improve RNN-T's ability to model rare WordPieces, infuse extra information into the encoder, enable the use of alternative graphemic pronunciations, and perform deep fusion with personalized language models for more robust biasing. We show that these combined techniques result in 15.4%-34.5% relative Word Error Rate improvement compared to a strong RNN-T baseline which uses shallow fusion and text-to-speech augmentation. Our work helps push the boundary of RNN-T personalization and close the gap with hybrid systems on use cases where biasing and entity recognition are crucial.