BERT Attends the Conversation: Improving Low-Resource Conversational ASR
This work addresses the challenge of accurate ASR for low-resource conversational domains like Norwegian parliament proceedings and customer service calls, though it is incremental as it builds on existing BERT and ASR methods.
The paper tackles the problem of improving automatic speech recognition (ASR) for conversational speech in low-resource settings by proposing data-efficient BERT training tasks that use past conversational context to rescore ASR candidates, achieving word error rate recoveries up to 37.2%.
We propose new, data-efficient training tasks for BERT models that improve performance of automatic speech recognition (ASR) systems on conversational speech. We include past conversational context and fine-tune BERT on transcript disambiguation without external data to rescore ASR candidates. Our results show word error rate recoveries up to 37.2%. We test our methods in low-resource data domains, both in language (Norwegian), tone (spontaneous, conversational), and topics (parliament proceedings and customer service phone calls). These techniques are applicable to any ASR system and do not require any additional data, provided a pre-trained BERT model. We also show how the performance of our context-augmented rescoring methods strongly depends on the degree of spontaneity and nature of the conversation.