Optimization of DNN-based speaker verification model through efficient quantization technique
This work addresses the challenge of deploying speaker verification models on mobile systems, but it is incremental as it applies quantization to an existing model.
The research tackled the problem of high computational costs and memory consumption in DNN-based speaker verification models by proposing an efficient quantization technique, resulting in a 50% reduction in model size with only a 0.07% increase in EER.
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%.