arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.08991eess.AScs.AIcs.CC
收藏

通过高效量化技术优化基于DNN的说话人验证模型

Optimization of DNN-based speaker verification model through efficient quantization technique

Yonsei University(延世大学)

Yeona Hong, Woo-Jin Chung, Hong-Goo Kang

AI总结:

针对DNN说话人验证模型计算与内存开销高、难部署于移动系统的问题,提出量化优化框架,通过分析预训练模型各层性能变化与体积缩减,首次在保持ECAPATDNN性能的同时将模型体积减半,EER仅上升0.07%。

摘要:

随着深度神经网络(DNNs)在包括说话人验证在内的各领域快速发展,它们通常存在计算成本高、内存消耗大的问题,在移动系统上难以部署。深度模型量化为降低计算和内存开销提供了一种途径。本研究提出了一种说话人验证模型量化优化框架。通过分析预训练说话人验证模型各层的性能变化与模型体积缩减情况,我们在显著减小模型体积的同时,有效降低了性能下降幅度。我们的量化算法是首个在保持当前最优预训练说话人验证模型ECAPATDNN性能的同时,大幅压缩其模型体积的尝试。总体而言,我们的量化方法将模型体积缩减了一半,等错误率(EER)的上升幅度控制在0.07%以内。

英文摘要:

As Deep Neural Networks (DNNs) rapidly advance in various fields, including speech verification, they typically involve high computational costs and substantial memory consumption, which can be challenging to manage on mobile systems. Quantization of deep models offers a means to reduce both computational and memory expenses. Our research proposes an optimization framework for the quantization of the speaker verification model. By analyzing performance changes and model size reductions in each layer of a pre-trained speaker verification model, we have effectively minimized performance degradation while significantly reducing the model size. Our quantization algorithm is the first attempt to maintain the performance of the state-of-the-art pre-trained speaker verification model, ECAPATDNN, while significantly compressing its model size. Overall, our quantization approach resulted in reducing the model size by half, with an increase in EER limited to 0.07%.

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。

↑