Internal Language Model Estimation based Adaptive Language Model Fusion for Domain Adaptation

11/02/2022
by   Rao Ma, et al.
0

ASR model deployment environment is ever-changing, and the incoming speech can be switched across different domains during a session. This brings a challenge for effective domain adaptation when only target domain text data is available, and our objective is to obtain obviously improved performance on the target domain while the performance on the general domain is less undermined. In this paper, we propose an adaptive LM fusion approach called internal language model estimation based adaptive domain adaptation (ILME-ADA). To realize such an ILME-ADA, an interpolated log-likelihood score is calculated based on the maximum of the scores from the internal LM and the external LM (ELM) respectively. We demonstrate the efficacy of the proposed ILME-ADA method with both RNN-T and LAS modeling frameworks employing neural network and n-gram LMs as ELMs respectively on two domain specific (target) test sets. The proposed method can achieve significantly better performance on the target test sets while it gets minimal performance degradation on the general test set, compared with both shallow and ILME-based LM fusion methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/02/2021

Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition

The efficacy of external language model (LM) integration with existing e...
research
05/05/2023

Mask The Bias: Improving Domain-Adaptive Generalization of CTC-based ASR with Internal Language Model Estimation

End-to-end ASR models trained on large amount of data tend to be implici...
research
06/15/2022

Residual Language Model for End-to-end Speech Recognition

End-to-end automatic speech recognition suffers from adaptation to unkno...
research
06/04/2021

Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition

Integrating external language models (LMs) into end-to-end (E2E) models ...
research
06/23/2020

Domain Adaptation for Semantic Parsing

Recently, semantic parsing has attracted much attention in the community...
research
09/18/2023

Improved Factorized Neural Transducer Model For text-only Domain Adaptation

End-to-end models, such as the neural Transducer, have been successful i...
research
04/07/2021

Librispeech Transducer Model with Internal Language Model Prior Correction

We present our transducer model on Librispeech. We study variants to inc...

Please sign up or login with your details

Forgot password? Click here to reset