TC-BiMamba: 通过在BiMamba内双向处理Trans-Chunk实现统一的流式和非流式ASR
TC-BiMamba: Trans-Chunk bidirectionally within BiMamba for unified streaming and non-streaming ASR
AI总结：
TC-BiMamba通过动态分块大小训练实现双向上下文捕捉，提升训练效率并优化ASR性能。
摘要：
本工作研究了双向Mamba（BiMamba）在统一的流式和非流式自动语音识别（ASR）中的应用。动态分块大小训练使模型能够支持离线解码和流式解码，并具有各种延迟设置。相比之下，现有的基于BiMamba的流式方法仅限于固定分块大小解码。当应用动态分块大小训练时，训练开销显著增加。为了解决这个问题，我们提出了Trans-Chunk BiMamba（TC-BiMamba）用于动态分块大小训练。Trans-Chunk机制以离线方式训练双向序列，采用动态分块大小。一方面，与传统的分块式处理相比，TC-BiMamba实现了1.3倍的训练加速，减少了50%的训练内存，并由于能够捕捉双向上下文而提高了模型性能。另一方面，实验结果表明，TC-BiMamba在性能上优于U2++，并且在更小的模型大小下与LC-BiMmaba相匹配。
英文摘要：
This work investigates bidirectional Mamba (BiMamba) for unified streaming and non-streaming automatic speech recognition (ASR). Dynamic chunk size training enables a single model for offline decoding and streaming decoding with various latency settings. In contrast, existing BiMamba based streaming method is limited to fixed chunk size decoding. When dynamic chunk size training is applied, training overhead increases substantially. To tackle this issue, we propose the Trans-Chunk BiMamba (TC-BiMamba) for dynamic chunk size training. Trans-Chunk mechanism trains both bidirectional sequences in an offline style with dynamic chunk size. On the one hand, compared to traditional chunk-wise processing, TC-BiMamba simultaneously achieves 1.3 times training speedup, reduces training memory by 50%, and improves model performance since it can capture bidirectional context. On the other hand, experimental results show that TC-BiMamba outperforms U2++ and matches LC-BiMmaba with smaller model size.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
