BLR-MoE:用于领域鲁棒多语言端到端自动语音识别的增强语言路由混合专家模型
BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASR
AI总结:
本文提出BLR-MoE架构,通过将语言混淆解耦为自注意力和路由器混淆,并在自注意力中应用MoE及专家剪枝和路由器增强方法,提升了多语言端到端语音识别在领域不匹配场景下的鲁棒性,并在万小时数据集上验证了有效性。
摘要:
近年来,混合专家(MoE)架构(如LR-MoE)常被用于缓解语言混淆对多语言自动语音识别(MASR)任务的影响。然而,该架构仍面临语言混淆问题,尤其是在领域不匹配的场景中。本文中,我们将LR-MoE中的语言混淆解耦为自注意力中的混淆和路由器中的混淆。为缓解自注意力中的语言混淆,我们基于LR-MoE提出在MASR中应用注意力-MoE架构。在新架构中,MoE不仅用于前馈网络(FFN),还用于自注意力。此外,为提高基于语言识别(LID)的路由器对语言混淆的鲁棒性,我们提出了专家剪枝和路由器增强方法。综合上述改进,我们得到了增强语言路由MoE(BLR-MoE)架构。我们在一个10,000小时的多语言自动语音识别数据集上验证了所提出的BLR-MoE的有效性。
英文摘要:
Recently, the Mixture of Expert (MoE) architecture, such as LR-MoE, is often used to alleviate the impact of language confusion on the multilingual ASR (MASR) task. However, it still faces language confusion issues, especially in mismatched domain scenarios. In this paper, we decouple language confusion in LR-MoE into confusion in self-attention and router. To alleviate the language confusion in self-attention, based on LR-MoE, we propose to apply attention-MoE architecture for MASR. In our new architecture, MoE is utilized not only on feed-forward network (FFN) but also on self-attention. In addition, to improve the robustness of the LID-based router on language confusion, we propose expert pruning and router augmentation methods. Combining the above, we get the boosted language-routing MoE (BLR-MoE) architecture. We verify the effectiveness of the proposed BLR-MoE in a 10,000-hour MASR dataset.
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。