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

TL;DR

This paper presents a resource-efficient speech quality prediction model using binary activation maps and quantization aware training, achieving significant memory reduction while maintaining performance, suitable for mobile and edge devices.

Contribution

The study introduces a novel binary activation map approach combined with quantization aware training for speech quality prediction, enabling substantial resource savings.

Findings

Achieves 25-fold memory reduction during inference.

Maintains predictive performance comparable to baseline models.

Supports mixed-precision binary multiplication for resource-efficient deployment.

Abstract

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.