@inproceedings{sharma-etal-2025-unifying,
    title = "Unifying Streaming and Non-streaming Zipformer-based {ASR}",
    author = "Sharma, Bidisha  and
      S, Karthik Pandia D  and
      Venkatesan, Shankar  and
      Prakash, Jeena J  and
      Kumar, Shashi  and
      Chetlur, Malolan  and
      Stolcke, Andreas",
    editor = "Rehm, Georg  and
      Li, Yunyao",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.acl-industry.87/",
    pages = "1254--1262",
    ISBN = "979-8-89176-288-6",
    abstract = "There has been increasing interest in unifying streaming and non-streaming automatic speech recognition (ASR) models to reduce development, training, and deployment costs. We present a unified framework that trains a single end-to-end ASR model for both streaming and non-streaming applications, leveraging future context information. We propose to use dynamic right-context through the chunked attention masking in the training of zipformer-based ASR models. We demonstrate that using right-context is more effective in zipformer models compared to other conformer models due to its multi-scale nature. We analyze the effect of varying the number of right-context frames on accuracy and latency of the streaming ASR models. We use Librispeech and large in-house conversational datasets to train different versions of streaming and non-streaming models and evaluate them in a production grade server-client setup across diverse testsets of different domains. The proposed strategy reduces word error by relative 7.9{\%} with a small degradation in user-perceived latency. By adding more right-context frames, we are able to achieve streaming performance close to that of non-streaming models. Our approach also allows flexible control of the latency-accuracy tradeoff according to customers requirements."
}