# PROCTER: PROnunciation-aware ConTextual adaptER for personalized speech recognition in neural transducers

arXiv: https://arxiv.org/abs/2303.17131 · HTML: https://mlsanity.com/paper/2303.17131/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2023.

## Built on by (most cited first, 10 of 10)

- [Low-rank Adaptation of Large Language Model Rescoring for Parameter-Efficient Speech Recognition](https://mlsanity.com/paper/2309.15223/) (2023)
- [Phoneme-aware Encoding for Prefix-tree-based Contextual ASR](https://mlsanity.com/paper/2312.09582/) (2023)
- [Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation](https://mlsanity.com/paper/2407.10303/) (2024)
- [Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Loss](https://mlsanity.com/paper/2406.16120/) (2024)
- [Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR](https://mlsanity.com/paper/2404.10180/) (2024)
- [Promptformer: Prompted Conformer Transducer for ASR](https://mlsanity.com/paper/2401.07360/) (2024)
- [Locality enhanced dynamic biasing and sampling strategies for contextual ASR](https://mlsanity.com/paper/2401.13146/) (2024)
- [An Effective Context-Balanced Adaptation Approach for Long-Tailed Speech Recognition](https://mlsanity.com/paper/2409.06468/) (2024)
- [Transducers with Pronunciation-aware Embeddings for Automatic Speech Recognition](https://mlsanity.com/paper/2404.04295/) (2024)
- [PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation](https://mlsanity.com/paper/2509.04357/) (2025)

## Abstract (arXiv)

End-to-End (E2E) automatic speech recognition (ASR) systems used in voice assistants often have difficulties recognizing infrequent words personalized to the user, such as names and places. Rare words often have non-trivial pronunciations, and in such cases, human knowledge in the form of a pronunciation lexicon can be useful. We propose a PROnunCiation-aware conTextual adaptER (PROCTER) that dynamically injects lexicon knowledge into an RNN-T model by adding a phonemic embedding along with a textual embedding. The experimental results show that the proposed PROCTER architecture outperforms the baseline RNN-T model by improving the word error rate (WER) by 44% and 57% when measured on personalized entities and personalized rare entities, respectively, while increasing the model size (number of trainable parameters) by only 1%. Furthermore, when evaluated in a zero-shot setting to recognize personalized device names, we observe 7% WER improvement with PROCTER, as compared to only 1% WER improvement with text-only contextual attention