一种优化 DIART 说话人日志流水线推理的方法
An approach to optimize inference of the DIART speaker diarization pipeline
AI总结：
本文针对 DIART 在线说话人日志流水线中嵌入模型导致的主要延迟，评估知识蒸馏、剪枝、量化和层融合，发现量化与层融合可在不损失准确率的情况下降低延迟。
摘要：
说话人日志用于回答音频文件中“谁在何时说话”的问题。在某些日志场景中，转写需要低延迟。具有低延迟的说话人日志被称为在线说话人日志。DIART 流水线是一个在线说话人日志系统，由分割模型和嵌入模型组成，其中嵌入模型在整体延迟中占比最大。本文旨在优化 DIART 流水线的推理延迟。研究将知识蒸馏、剪枝、量化和层融合等不同推理优化方法应用于该流水线的嵌入模型。结果表明，知识蒸馏可优化延迟，但会对准确率产生负面影响；量化和层融合同样对延迟具有积极影响，且不会降低准确率；另一方面，剪枝并不能改善延迟。
英文摘要：
Speaker diarization answers the question "who spoke when" for an audio file. In some diarization scenarios, low latency is required for transcription. Speaker diarization with low latency is referred to as online speaker diarization. The DIART pipeline is an online speaker diarization system. It consists of a segmentation and an embedding model. The embedding model has the largest share of the overall latency. The aim of this paper is to optimize the inference latency of the DIART pipeline. Different inference optimization methods such as knowledge distilation, pruning, quantization and layer fusion are applied to the embedding model of the pipeline. It turns out that knowledge distillation optimizes the latency, but has a negative effect on the accuracy. Quantization and layer fusion also have a positive influence on the latency without worsening the accuracy. Pruning, on the other hand, does not improve latency.
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。
