Streaming Automatic Speech Recognition (ASR), also known as online or real-time ASR, transcribes speech incrementally while audio is being spoken and is critical for many industry applications. Despite the strong performance of modern offline ASR models, streaming deployment remains challenging because limited future context can cause early recognition errors to propagate across later chunks. We define the task of streaming ASR error correction and propose StreamCorrect, a modular framework that fine-tunes a lightweight error corrector from self-generated streaming ASR errors and integrates it with existing streaming ASR systems. To enable training without human annotation, StreamCorrect introduces a timestamp-free boundary recovery procedure based on Prefix-to-Reference Alignment for generating chunk-level correction data. Across multiple languages and ASR backbones, StreamCorrect achieves up to 39% relative character error rate (CER) reduction with minimal latency overhead. Error propagation analysis further shows increasing benefits over time, with up to 7.2% absolute CER reduction in later audio chunks. StreamCorrect bridges offline ASR models and streaming deployment through a lightweight correction plug-in while preserving the pretrained ASR component without additional tuning or distillation.

Language model is a vital component in modern automatic speech recognition (ASR) systems. Since “one-size-fits-all” language model works suboptimally for conversational speeches, language model adaptation (LMA) is considered as a promising solution for solving this problem. In order to compare the state-of-the-art LMA techniques and systematically demonstrate their effect in conversational speech recognition, we develop a novel toolkit named Chameleon, which includes the state-of-the-art cache-based and topic-based LMA techniques. This demonstration does not only vividly visualize underlying working mechanisms of a variety of the state-of-the-art LMA models but also provide an interface for the user to customize the hyperparameters of them. With this demonstration, the audience can experience the effect of LMA in an interactive and real-time fashion. We wish this demonstration would inspire more research on better language model techniques for ASR.