面向神经说话人日志的预训练多说话人识别
Pretraining Multi-Speaker Identification for Neural Speaker Diarization
AI总结：
本文提出预训练多说话人识别模型作为替代方案，利用大规模说话人识别数据集，无需模拟对话数据即可实现高精度轻量级的局部说话人日志模型。
摘要：
端到端说话人日志通过并行联合估计多个说话人的语音活动，实现了准确的感知重叠的日志。该方法对数据需求量大，需要大量带标签的对话数据，仅靠真实数据集无法完全满足。为解决此问题，通常使用大规模模拟数据进行预训练，但这需要庞大的存储和I/O能力，且模拟与真实对话高度相似的数据仍具挑战性。本文提出预训练一个模型，从输入的完全重叠混合语音中识别多个说话人，作为预训练日志模型的替代方案。该方法无需准备大规模模拟数据集，同时利用大规模说话人识别数据集进行训练。通过综合实验，我们证明所提方法无需模拟对话数据，即可实现高精度且轻量级的局部日志模型。
英文摘要：
End-to-end speaker diarization enables accurate overlap-aware diarization by jointly estimating multiple speakers' speech activities in parallel. This approach is data-hungry, requiring a large amount of labeled conversational data, which cannot be fully obtained from real datasets alone. To address this issue, large-scale simulated data is often used for pretraining, but it requires enormous storage and I/O capacity, and simulating data that closely resembles real conversations remains challenging. In this paper, we propose pretraining a model to identify multiple speakers from an input fully overlapped mixture as an alternative to pretraining a diarization model. This method eliminates the need to prepare a large-scale simulated dataset while leveraging large-scale speaker recognition datasets for training. Through comprehensive experiments, we demonstrate that the proposed method enables a highly accurate yet lightweight local diarization model without simulated conversational data.
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。
