Contextual Adapters For Personalized Speech Recognition In Neural Transducers
2022 · Kanthashree Mysore Sathyendra, Thejaswi Muniyappa, Feng-Ju Chang, et al.
Abstract
Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR) models is a challenge due to the lack of training data. A standard way to address this issue is with shallow fusion methods at inference time. However, due to their dependence on external language models and the deterministic approach to weight boosting, their performance is limited. In this paper, we propose training neural contextual adapters for personalization in neural transducer based ASR models. Our approach can not only bias towards user-defined words, but also has the flexibility to work with pretrained ASR models. Using an in-house dataset, we demonstrate that contextual adapters can be applied to any general purpose pretrained ASR model to improve personalization. Our method outperforms shallow fusion, while retaining functionality of the pretrained models by not altering any of the model weights. We further show that the adapter style training is superior to full-fine-tuning of the ASR model
Authors
(none)
Tags
Stats
Related papers
- Fast Contextual Adaptation With Neural Associative Memory For On-device Personalized Speech Recognition (2021)9.76
- PROCTER: Pronunciation-aware Contextual Adapter For Personalized Speech Recognition In Neural Transducers (2023)8.60
- Towards Personalization Of CTC Speech Recognition Models With Contextual Adapters And Adaptive Boosting (2022)0.00
- Deep Shallow Fusion For RNN-T Personalization (2020)12.81
- Robust Acoustic And Semantic Contextual Biasing In Neural Transducers For Speech Recognition (2023)8.60
- The Universal Personalizer: Few-shot Dysarthric Speech Recognition Via Meta-learning (2025)0.00
- Multilingual Contextual Adapters To Improve Custom Word Recognition In Low-resource Languages (2023)4.52
- Residual Adapters For Parameter-efficient ASR Adaptation To Atypical And Accented Speech (2021)10.74