Domain-aware Neural Language Models for Speech Recognition

01/05/2021
by   Linda Liu, et al.
0

As voice assistants become more ubiquitous, they are increasingly expected to support and perform well on a wide variety of use-cases across different domains. We present a domain-aware rescoring framework suitable for achieving domain-adaptation during second-pass rescoring in production settings. In our framework, we fine-tune a domain-general neural language model on several domains, and use an LSTM-based domain classification model to select the appropriate domain-adapted model to use for second-pass rescoring. This domain-aware rescoring improves the word error rate by up to 2.4 error rate by up to 4.1 and music – compared to domain general rescoring. These improvements are obtained while maintaining accuracy for the general use case.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset