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 2104.02306cs.SDcs.LGeess.AS
收藏

用于说话人确认的二进制神经网络

Binary Neural Network for Speaker Verification

Duke Kunshan University(昆山杜克大学);Wuhan University(武汉大学)

Tinglong Zhu, Xiaoyi Qin, Ming Li

摘要:

尽管深度神经网络在语音领域的许多任务上都取得了成功,但深度神经网络的高计算和内存成本使得难以在低资源嵌入式设备上直接部署高性能神经网络系统。有几种机制,以减少神经网络的大小,即参数修剪,参数量化等,本文重点讨论如何将二进制神经网络的说话人确认任务。所提出的训练参数的二值化可以在很大程度上保持性能,同时显着降低存储空间需求和计算成本。实验结果表明,在对卷积神经网络进行二值化后,基于ResNet34的网络在Voxceleb1测试数据集上的EER达到了5%左右,在文本依赖数据集Xiaole上的EER甚至超过了传统的实数网络,同时节省了32倍的内存。

英文摘要:

Although deep neural networks are successful for many tasks in the speech domain, the high computational and memory costs of deep neural networks make it difficult to directly deploy highperformance Neural Network systems on low-resource embedded devices. There are several mechanisms to reduce the size of the neural networks i.e. parameter pruning, parameter quantization, etc. This paper focuses on how to apply binary neural networks to the task of speaker verification. The proposed binarization of training parameters can largely maintain the performance while significantly reducing storage space requirements and computational costs. Experiment results show that, after binarizing the Convolutional Neural Network, the ResNet34-based network achieves an EER of around 5% on the Voxceleb1 testing dataset and even outperforms the traditional real number network on the text-dependent dataset: Xiaole while having a 32x memory saving.

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。

↑