arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.02868cs.SDeess.AS
收藏

Darts-Conformer:面向端到端ASR的高效基于代理的神经架构搜索

Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASR

Sogou(搜狗)

Xian Shi, Pan Zhou, Wei Chen, Lei Xie

摘要:

神经结构搜索(NAS)已成功应用于图像分类和语言建模等任务,以找到高效的高性能网络架构。在自动语音识别领域,尤其是端到端自动语音识别方面,相关的研究还处于起步阶段。在这项工作中,我们专注于将NAS应用于最流行的手动设计的模型:Conformer,然后提出一种有效的ASR模型搜索方法,该方法受益于可微结构搜索(Darts)在减少计算开销方面的天然优势。我们融合Darts mutator和Conformer块形成一个完整的搜索空间,在这个空间中自动找到一个被称为Darts-Conformer单元的改进结构。AISHELL-1数据集上的整个搜索过程仅需0.7 GPU天。通过堆叠搜索单元来替换Conformer编码器,我们得到了一个端到端的ASR模型(命名为Darts-Conformner),在开源AISHELL-1数据集上的性能超过Conformer基线4.7%。此外,我们还验证了在小数据集上搜索到的架构到更大的2k-hour数据集的可移植性。据我们所知,这是第一次成功地尝试应用基于梯度的架构搜索在基于注意力的编码器-解码器ASR模型。

英文摘要:

Neural architecture search (NAS) has been successfully applied to tasks like image classification and language modeling for finding efficient high-performance network architectures. In ASR field especially end-to-end ASR, the related research is still in its infancy. In this work, we focus on applying NAS on the most popular manually designed model: Conformer, and then propose an efficient ASR model searching method that benefits from the natural advantage of differentiable architecture search (Darts) in reducing computational overheads. We fuse Darts mutator and Conformer blocks to form a complete search space, within which a modified architecture called Darts-Conformer cell is found automatically. The entire searching process on AISHELL-1 dataset costs only 0.7 GPU days. Replacing the Conformer encoder by stacking searched cell, we get an end-to-end ASR model (named as Darts-Conformner) that outperforms the Conformer baseline by 4.7\% on the open-source AISHELL-1 dataset. Besides, we verify the transferability of the architecture searched on a small dataset to a larger 2k-hour dataset. To the best of our knowledge, this is the first successful attempt to apply gradient-based architecture search in the attention-based encoder-decoder ASR model.

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。

↑