arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.11571eess.AS
收藏

BAT:面向内存高效且低延迟ASR的边界感知转换器

BAT: Boundary aware transducer for memory-efficient and low-latency ASR

Keyu An, Xian Shi, Shiliang Zhang

AI总结:

本文提出边界感知转换器(BAT),通过利用连续整合与发放(CIF)对齐缩减RNN-T损失计算网格,显著降低了流式ASR训练的内存与时间消耗,并实现了良好的CER-延迟权衡。

摘要:

近期,循环神经网络转换器(RNN-T)因其天然的流式处理能力及卓越性能而日益受到关注。然而,RNN-T训练需要大量时间和计算资源,因为RNN-T损失计算缓慢且消耗大量内存。RNN-T的另一局限在于,它倾向于访问更多上下文以提升性能,从而导致流式ASR中的发射延迟更高。本文提出边界感知转换器(BAT),以实现内存高效且低延迟的ASR。在BAT中,用于RNN-T损失计算的网格被缩减为由连续整合与发放(CIF)对齐所选定的受限区域,该CIF与RNN-T模型联合优化。大量实验表明,与RNN-T相比,BAT在训练中显著降低了时间和内存消耗,并在流式ASR推理中实现了良好的CER-延迟权衡。

英文摘要:

Recently, recurrent neural network transducer (RNN-T) gains increasing popularity due to its natural streaming capability as well as superior performance. Nevertheless, RNN-T training requires large time and computation resources as RNN-T loss calculation is slow and consumes a lot of memory. Another limitation of RNN-T is that it tends to access more contexts for better performance, thus leading to higher emission latency in streaming ASR. In this paper we propose boundary-aware transducer (BAT) for memory-efficient and low-latency ASR. In BAT, the lattice for RNN-T loss computation is reduced to a restricted region selected by the alignment from continuous integrate-and-fire (CIF), which is jointly optimized with the RNN-T model. Extensive experiments demonstrate that compared to RNN-T, BAT reduces time and memory consumption significantly in training, and achieves good CER-latency trade-offs in inference for streaming ASR.

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。

↑