The network architecture of end-to-end (E2E) automatic speech recognition (ASR) can be classified into several models, including connectionist temporal classification (CTC), recurrent neural network transducer (RNN-T), attention mechanism, and non-autoregressive mask-predict models. Since each of these network architectures has pros and cons, a typical use case is to switch these separate models depending on the application requirement, resulting in the increased overhead of maintaining all models. Several methods for integrating two of these complementary models to mitigate the overhead issue have been proposed; however, if we integrate more models, we will further benefit from these complementary models and realize broader applications with a single system. This paper proposes four-decoder joint modeling (4D) of CTC, attention, RNN-T, and mask-predict, which has the following three advantages: 1) The four decoders are jointly trained so that they can be easily switched depending on the application scenarios. 2) Joint training may bring model regularization and improve the model robustness thanks to their complementary properties. 3) Novel one-pass joint decoding methods using CTC, attention, and RNN-T further improves the performance. The experimental results showed that the proposed model consistently reduced the WER.

一个由许多移动计算实体组成的自动移动机器人系统（称为机器人）吸引了研究人员的广泛关注，并阐明机器人的能力与问题的可溶性之间的关系是近几十年来的新兴问题。通常，只要没有任何机器人的数量，每个机器人都可以观察所有其他机器人。在本文中，我们提供了关于机器人观察的新观点。机器人不一定要观察所有其他机器人，而不管距离距离如何。我们称此新的计算模型瑕疵视图模型。在该模型下，在本文中，我们考虑了需要所有机器人在同一时刻收集的收集问题，并提出了两种算法来解决对抗性（$ n $，$ n-2 $）中的收集问题 - 违法模型对于$ n \ geq 5 $（每个机器人最多观察$ n-2 $机器人在对手身上选择）和基于距离的（4,2）的模型（每个机器人在最接近的机器人最接近的机器人中分别观察到）分别，其中$ n $是机器人的数量。此外，我们提出了一个不可能的结果，表明在对抗性或基于距离（3,1）的模型中没有（确定性的）收集算法。此外，我们在放松的（$ n $，$ n-2 $）中的聚会中表现出了不可能的结果。