Publication Details
On-the-Fly Text Retrieval for end-to-end ASR Adaptation
retrieval, language model, domain adaptation, end-to-end ASR, RNN transducer,
contextual biasing
End-to-end speech recognition models are improved by incorporat- ing external
text sources, typically by fusion with an external lan- guage model. Such
language models have to be retrained whenever the corpus of interest changes.
Furthermore, since they store the entire corpus in their parameters, rare words
can be challenging to recall. In this work, we propose augmenting
a transducer-based ASR model with a retrieval language model, which directly
retrieves from an external text corpus plausible completions for a partial ASR
hy- pothesis. These completions are then integrated into subsequent pre- dictions
by an adapter, which is trained once, so that the corpus of interest can be
switched without incurring the computational over- head of retraining. Our
experiments show that the proposed model significantly improves the performance
of a transducer baseline on a pair of question-answering datasets. Further, it
outperforms shallow fusion on recognition of named entities by about 7% relative;
when the two are combined, the relative improvement increases to 13%
@inproceedings{BUT185196,
author="YUSUF, B. and GOURAV, A. and GANDHE, A. and BULYKO, I.",
title="On-the-Fly Text Retrieval for end-to-end ASR Adaptation",
booktitle="Proceedings of ICASSP 2023",
year="2023",
pages="1--5",
publisher="IEEE Signal Processing Society",
address="Rhodes Island",
doi="10.1109/ICASSP49357.2023.10095857",
isbn="978-1-7281-6327-7",
url="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10095857"
}