Unifying Streaming and Non-streaming Zipformer-based ASR

• URL: http://arxiv.org/abs/2506.14434v1
• Date: Tue, 17 Jun 2025 11:52:41 GMT
• Title: Unifying Streaming and Non-streaming Zipformer-based ASR
• Authors: Bidisha Sharma, Karthik Pandia Durai, Shankar Venkatesan, Jeena J Prakash, Shashi Kumar, Malolan Chetlur, Andreas Stolcke,
• Abstract summary: We present a unified framework that trains a single end-to-end ASR model for both streaming and non-streaming applications.<n>We propose to use dynamic right-context through the chunked attention masking in the training of zipformer-based ASR models.<n>We analyze the effect of varying the number of right-context frames on accuracy and latency of the streaming ASR models.
• Score: 14.226219579716629
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• StreamChat: Chatting with Streaming Video [85.02875830683637]
  StreamChat is a novel approach that enhances the interaction capabilities of Large Multimodal Models with streaming video content.<n>We introduce a flexible and efficient crossattention-based architecture to process dynamic streaming inputs.<n>We construct a new dense instruction dataset to facilitate the training of streaming interaction models.
  arXiv  Detail & Related papers  (2024-12-11T18:59:54Z)
• RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter [77.0205013713008]
  Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. To date, most state-of-the-art TVR methods learn image-to-video transfer learning based on large-scale pre-trained vision models. We propose a sparse-andcorrelated AdaPter (RAP) to fine-tune the pre-trained model with a few parameterized layers.
  arXiv  Detail & Related papers  (2024-05-29T19:23:53Z)
• Streaming Anchor Loss: Augmenting Supervision with Temporal Significance [5.7654216719335105]
  Streaming neural network models for fast frame-wise responses to various speech and sensory signals are widely adopted on resource-constrained platforms. We propose a new loss, Streaming Anchor Loss (SAL), to better utilize the given learning capacity by encouraging the model to learn more from essential frames.
  arXiv  Detail & Related papers  (2023-10-09T17:28:35Z)
• Semi-Autoregressive Streaming ASR With Label Context [70.76222767090638]
  We propose a streaming "semi-autoregressive" ASR model that incorporates the labels emitted in previous blocks as additional context. Experiments show that our method outperforms the existing streaming NAR model by 19% relative on Tedlium2, 16%/8% on Librispeech-100 clean/other test sets, and 19%/8% on the Switchboard(SWB)/Callhome(CH) test sets.
  arXiv  Detail & Related papers  (2023-09-19T20:55:58Z)
• DCTX-Conformer: Dynamic context carry-over for low latency unified streaming and non-streaming Conformer ASR [20.42366884075422]
  We propose the integration of a novel dynamic contextual carry-over mechanism in a state-of-the-art unified ASR system. Our proposed dynamic context Conformer (DCTX-Conformer) utilizes a non-overlapping contextual carry-over mechanism. We outperform the SOTA by a relative 25.0% word error rate, with a negligible latency impact due to the additional context embeddings.
  arXiv  Detail & Related papers  (2023-06-13T23:42:53Z)
• Learning a Dual-Mode Speech Recognition Model via Self-Pruning [18.248552732790852]
  This work aims to jointly learn a compact sparse on-device streaming ASR model, and a large dense server non-streaming model, in a single supernet. We present that, performing supernet training on both wav2vec 2.0 self-supervised learning and supervised ASR fine-tuning can not only substantially improve the large non-streaming model as shown in prior works, and also be able to improve the compact sparse streaming model.
  arXiv  Detail & Related papers  (2022-07-25T05:03:13Z)
• Streaming Align-Refine for Non-autoregressive Deliberation [42.748839817396046]
  We propose a streaming non-autoregressive (non-AR) decoding algorithm to deliberate the hypothesis alignment of a streaming RNN-T model. Our algorithm facilitates a simple greedy decoding procedure, and at the same time is capable of producing the decoding result at each frame with limited right context. Experiments on voice search datasets and Librispeech show that with reasonable right context, our streaming model performs as well as the offline counterpart.
  arXiv  Detail & Related papers  (2022-04-15T17:24:39Z)
• Real-time Object Detection for Streaming Perception [84.2559631820007]
  Streaming perception is proposed to jointly evaluate the latency and accuracy into a single metric for video online perception. We build a simple and effective framework for streaming perception. Our method achieves competitive performance on Argoverse-HD dataset and improves the AP by 4.9% compared to the strong baseline.
  arXiv  Detail & Related papers  (2022-03-23T11:33:27Z)
• Multi-mode Transformer Transducer with Stochastic Future Context [53.005638503544866]
  Multi-mode speech recognition models can process longer future context to achieve higher accuracy and when a latency budget is not flexible, the model can still achieve reliable accuracy. We show that a Multi-mode ASR model rivals, if not surpasses, a set of competitive streaming baselines trained with different latency budgets.
  arXiv  Detail & Related papers  (2021-06-17T18:42:11Z)
• Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling [76.43479696760996]
  We propose a unified framework, Dual-mode ASR, to train a single end-to-end ASR model with shared weights for both streaming and full-context speech recognition. We show that the latency and accuracy of streaming ASR significantly benefit from weight sharing and joint training of full-context ASR.
  arXiv  Detail & Related papers  (2020-10-12T21:12:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.