2021/04/06 by Tinglong Zhu, Zhu, Tinglong, Xiaoyi Qin +3
Computer Science · Engineering · #Algorithm #Arithmetic #Artificial intelligence #Artificial neural network #Audio and Speech Processing (eess.AS) #Binary classification #Binary number #Computer science #Convolutional neural network #Deep learning #Deep neural networks #Domain (mathematical analysis) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Machine learning #Music and Audio Processing #Pruning #Quantization (signal processing) #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #Task (project management) #Time delay neural network #cs.LG #cs.SD #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2104.02306
published in arXiv (Cornell University) (Cornell University)
arxiv created 2021/04/06 · openalex publication_date 2021/04/06 · arxiv updated 2021/04/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.