This paper investigates a method for simulating natural conversation in the
model training of end-to-end neural diarization (EEND). Due to the lack of any
annotated real conversational dataset, EEND is usually pretrained on a
large-scale simulated conversational dataset first and then adapted to the
target real dataset. Simulated datasets play an essential role in the training
of EEND, but as yet there has been insufficient investigation into an optimal
simulation method. We thus propose a method to simulate natural conversational
speech. In contrast to conventional methods, which simply combine the speech of
multiple speakers, our method takes turn-taking into account. We define four
types of speaker transition and sequentially arrange them to simulate natural
conversations. The dataset simulated using our method was found to be
statistically similar to the real dataset in terms of the silence and overlap
ratios. The experimental results on two-speaker diarization using the CALLHOME
and CSJ datasets showed that the simulated dataset contributes to improving the
performance of EEND.

研究了一种用于模拟自然对话的方法，用于训练端到端神经音频分离技术（EEND），并提出了一种考虑交替对话方式的模拟方法，用于在缺乏真实语音数据的情况下，优化 EEND 模型的训练。通过对 CALLHOME 和 CSJ 数据集的实验结果表明，使用这种方法模拟数据有助于提高 EEND 的性能表现。

提高端到端神经分离模型模拟对话自然度

Improving the Naturalness of Simulated Conversations for End-to-End Neural Diarization

We review the history of the parallel tempering simulation method. From its
origins in data analysis, the parallel tempering method has become a standard
workhorse of physiochemical simulations. We discuss the theory behind the
method and its various generalizations. We mention a selected set of the many
applications that have become possible with the introduction of parallel
tempering and we suggest several promising avenues for future research.

本文回顾了并行淬火模拟方法的历史，并介绍了其理论及应用，包括物理化学模拟和未来研究的前景。