论文标题
实时语音中断分析：从云到客户部署
Real-time Speech Interruption Analysis: From Cloud to Client Deployment
论文作者
论文摘要
会议是所有类型组织的一种基本沟通形式，自COVID-19大流行以来，远程协作系统被广泛使用。远程会议的一个主要问题是，远程参与者打扰和讲话是一个挑战。我们最近开发了第一个语音中断分析模型，该模型检测到失败的语音中断，显示出非常有前途的性能，并且正在云中部署。为了以更具成本效益和环境友好的方式交付此功能，我们降低了模型的复杂性和尺寸，以在客户端设备中运送WAVLM_SI模型。在本文中，我们首先描述了如何通过在较大的数据集中训练和微调训练的语音中断检测模型，以1％的误报率（FPR）成功提高了真正的正率（TPR）从50.9％到68.3％。然后，我们将模型大小从222.7 MB缩小到9.3 MB，准确性损失可接受，并将复杂性从31.2 GMAC（GIGA Multiply-Accymulate Altions）降低到4.3 GMAC。我们还估计了降低复杂性的环境影响，该降低可以用作大型基于变压器模型的一般指南，从而使这些模型更容易在较少的计算开销中访问。
Meetings are an essential form of communication for all types of organizations, and remote collaboration systems have been much more widely used since the COVID-19 pandemic. One major issue with remote meetings is that it is challenging for remote participants to interrupt and speak. We have recently developed the first speech interruption analysis model, which detects failed speech interruptions, shows very promising performance, and is being deployed in the cloud. To deliver this feature in a more cost-efficient and environment-friendly way, we reduced the model complexity and size to ship the WavLM_SI model in client devices. In this paper, we first describe how we successfully improved the True Positive Rate (TPR) at a 1% False Positive Rate (FPR) from 50.9% to 68.3% for the failed speech interruption detection model by training on a larger dataset and fine-tuning. We then shrank the model size from 222.7 MB to 9.3 MB with an acceptable loss in accuracy and reduced the complexity from 31.2 GMACS (Giga Multiply-Accumulate Operations per Second) to 4.3 GMACS. We also estimated the environmental impact of the complexity reduction, which can be used as a general guideline for large Transformer-based models, and thus make those models more accessible with less computation overhead.
