PromptASR for contextualized ASR with controllable style

TL;DR

PromptASR introduces a novel framework that incorporates prompts into end-to-end speech recognition systems, enabling contextualized and style-controllable transcriptions with improved accuracy and flexibility.

Contribution

This work presents the first integration of prompt-based conditioning in E2E ASR systems for style control and biasing, enhancing recognition performance and adaptability.

Findings

Achieves 21.9% and 6.8% relative WER reductions on datasets.

Effectively uses text prompts for rare word biasing.

Enables style-guided transcriptions through prompts.

Abstract

Prompts are crucial to large language models as they provide context information such as topic or logical relationships. Inspired by this, we propose PromptASR, a framework that integrates prompts in end-to-end automatic speech recognition (E2E ASR) systems to achieve contextualized ASR with controllable style of transcriptions. Specifically, a dedicated text encoder encodes the text prompts and the encodings are injected into the speech encoder by cross-attending the features from two modalities. When using the ground truth text from preceding utterances as content prompt, the proposed system achieves 21.9% and 6.8% relative word error rate reductions on a book reading dataset and an in-house dataset compared to a baseline ASR system. The system can also take word-level biasing lists as prompt to improve recognition accuracy on rare words. An additional style prompt can be given to the text encoder and guide the ASR system to output different styles of transcriptions. The code is available at icefall.