Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning
This addresses the challenge of adapting speech recognition to specific domains with limited audio-transcript data, offering a practical solution for applications in fields such as healthcare and finance.
The paper tackles the problem of domain-sensitive speech recognition by fine-tuning a pre-trained model to condition on textual prompts, achieving up to 33% WER reduction on unseen datasets like medical conversations and air traffic control.
In this work, we propose a method to create domain-sensitive speech recognition models that utilize textual domain information by conditioning its generation on a given text prompt. This is accomplished by fine-tuning a pre-trained, end-to-end model (Whisper) to learn from demonstrations with prompt examples. We show that this ability can be generalized to different domains and even various prompt contexts, with our model gaining a Word Error Rate (WER) reduction of up to 33% on unseen datasets from various domains, such as medical conversation, air traffic control communication, and financial meetings. Considering the limited availability of audio-transcript pair data, we further extend our method to text-only fine-tuning to achieve domain sensitivity as well as domain adaptation. We demonstrate that our text-only fine-tuned model can also attend to various prompt contexts, with the model reaching the most WER reduction of 29% on the medical conversation dataset.