Detail publikačního výsledku

On-the-Fly Text Retrieval for end-to-end ASR Adaptation

YUSUF, B.; GOURAV, A.; GANDHE, A.; BULYKO, I.

Originální název

On-the-Fly Text Retrieval for end-to-end ASR Adaptation

Anglický název

On-the-Fly Text Retrieval for end-to-end ASR Adaptation

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

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%

Anglický abstrakt

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%

Klíčová slova

retrieval, language model, domain adaptation, end-to-end ASR, RNN transducer, contextual biasing

Klíčová slova v angličtině

retrieval, language model, domain adaptation, end-to-end ASR, RNN transducer, contextual biasing

Autoři

YUSUF, B.; GOURAV, A.; GANDHE, A.; BULYKO, I.

Rok RIV

2024

Vydáno

04.10.2023

Nakladatel

IEEE Signal Processing Society

Místo

Rhodes Island

ISBN

978-1-7281-6327-7

Kniha

Proceedings of ICASSP 2023

Strany od

1

Strany do

5

Strany počet

5

URL

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10095857

BibTex

@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"
}

Dokumenty

yusuf_icassp2023_amazon paper