arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.04578cs.SDcs.NEeess.AS
收藏

通过量化感知训练和二值激活图的资源高效语音质量预测

Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps

Friedrich Miescher Institute for Biomedical Research(弗里德里希·米舍尔生物医学研究所);GN Audio(GN音频公司);Technical University of Denmark(丹麦技术大学);University of Basel(巴塞尔大学)

Mattias Nilsson, Riccardo Miccini, Clément Laroche, Tobias Piechowiak, Friedemann Zenke

AI总结:

本文提出基于DNSMOS的卷积架构结合二值激活图(BAMs)与量化感知训练,在匹配基线预测性能的同时结合8位权重量化实现25倍内存减少,为资源受限设备上的语音质量预测提供高效方案。

摘要:

随着移动和边缘设备中的语音处理系统变得更加普遍,对无干扰语音质量监控的需求增加。深度学习方法提供了对客观和主观语音质量指标的高质量估计。然而,其巨大的计算需求在资源受限设备上通常是不可行的。为解决此问题,我们在基于DNSMOS的卷积架构上研究了用于语音质量预测的二值激活图(BAMs)。我们展示了采用量化感知训练的二值激活模型匹配了基线模型的预测性能。它还进一步允许使用其他压缩技术。结合8位权重量化,我们的方法在推理期间实现了25倍的内存减少,同时用求和替换了几乎所有的点积。我们的发现通过在硬件和软件中支持混合精度二值乘法,展示了实现大量资源节省的途径。

英文摘要:

As speech processing systems in mobile and edge devices become more commonplace, the demand for unintrusive speech quality monitoring increases. Deep learning methods provide high-quality estimates of objective and subjective speech quality metrics. However, their significant computational requirements are often prohibitive on resource-constrained devices. To address this issue, we investigated binary activation maps (BAMs) for speech quality prediction on a convolutional architecture based on DNSMOS. We show that the binary activation model with quantization aware training matches the predictive performance of the baseline model. It further allows using other compression techniques. Combined with 8-bit weight quantization, our approach results in a 25-fold memory reduction during inference, while replacing almost all dot products with summations. Our findings show a path toward substantial resource savings by supporting mixed-precision binary multiplication in hard- and software.

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。

↑