In this paper, we propose a Unified pre-training Framework for Online and Offline (UFO2) Automatic Speech Recognition (ASR), which 1) simplifies the two separate training workflows for online and offline modes into one process, and 2) improves the Word Error Rate (WER) performance with limited utterance annotating. Specifically, we extend the conventional offline-mode Self-Supervised Learning (SSL)-based ASR approach to a unified manner, where the model training is conditioned on both the full-context and dynamic-chunked inputs. To enhance the pre-trained representation model, stop-gradient operation is applied to decouple the online-mode objectives to the quantizer. Moreover, in both the pre-training and the downstream fine-tuning stages, joint losses are proposed to train the unified model with full-weight sharing for the two modes. Experimental results on the LibriSpeech dataset show that UFO2 outperforms the SSL-based baseline method by 29.7% and 18.2% relative WER reduction in offline and online modes, respectively.
翻译:在本文中,我们提出了一个在线和离线(UFO2)自动语音识别统一培训前框架(UFO2),其中1个将在线和离线模式的两种单独培训工作流程简化为一个过程,2个改进了Word错误率(WER)的绩效,并作了有限的发文说明。具体地说,我们将传统的离线模式自协调学习基于ASR(SSL)的方法推广到一个统一的方式,即示范培训以全文和动态组合输入为条件。为了加强预先培训的代表模式,对在线和离线模式目标进行截断操作。此外,在培训前阶段和下游微调阶段,都提议联合损失来对统一模式进行培训,对两种模式进行全称共享。LibriSpeech数据集的实验结果表明,UFO2在离线和在线模式中分别比SLS基准方法高出29.7%和18.2%。