CPPF: A contextual and post-processing-free model for automatic speech recognition
This addresses the need for streamlined and error-resistant ASR pipelines for users of speech recognition technology, though it appears incremental as it builds on existing LLM and Whisper capabilities.
The paper tackles the problem of ASR systems requiring post-processing by integrating multiple text processing tasks directly into the model, resulting in direct generation of post-processed text without significant performance loss.
ASR systems have become increasingly widespread in recent years. However, their textual outputs often require post-processing tasks before they can be practically utilized. To address this issue, we draw inspiration from the multifaceted capabilities of LLMs and Whisper, and focus on integrating multiple ASR text processing tasks related to speech recognition into the ASR model. This integration not only shortens the multi-stage pipeline, but also prevents the propagation of cascading errors, resulting in direct generation of post-processed text. In this study, we focus on ASR-related processing tasks, including Contextual ASR and multiple ASR post processing tasks. To achieve this objective, we introduce the CPPF model, which offers a versatile and highly effective alternative to ASR processing. CPPF seamlessly integrates these tasks without any significant loss in recognition performance.