EUVIMEDEUVIMED entdecken
Crossref

BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance

Haotong Qin, Xudong Ma, Yifu Ding, Xiaoyang Li, Yang Zhang, Zejun Ma, Jiakai Wang, Jie Luo, Xianglong Liu

IEEE Transactions on Neural Networks and Learning Systems · 2024-08 · 35 (8) · 10674-10686

DOI: 10.1109/tnnls.2023.3243259 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Neural Networks and Learning Systems, 2024-08. Verfasst von Haotong Qin und 8 weiteren Autor:innen. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: National Key Research and Development Plan of China, National Natural Science Foundation of China, Fund of State Key Laboratory of Software Development Environment.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep neural networks, such as the deep-FSMN, have been widely studied for keyword spotting (KWS) applications while suffering expensive computation and storage. Therefore, network compression technologies such as binarization are studied to deploy KWS models on edge. In this article, we present a strong yet efficient binary neural network for KWS, namely, BiFSMNv2, pushing it to the real-network accuracy performance. First, we present a dual-scale thinnable 1-bit-architecture (DTA) to recover the representation capability of the binarized computation units by dual-scale activation binarization and liberate the speedup potential from an overall architecture perspective. Second, we also construct a frequency-independent distillation (FID) scheme for KWS binarization-aware training, which distills the high- and low-frequency components independently to mitigate the information mismatch between full-precision and binarized representations. Moreover, we propose the learning propagation binarizer (LPB), a general and efficient binarizer that enables the forward and backward propagation of binary KWS networks to be continuously improved through learning. We implement and deploy BiFSMNv2 on ARMv8 real-world hardware with a novel fast bitwise computation kernel (FBCK), which is proposed to fully use registers and increase instruction throughput. Comprehensive experiments show our BiFSMNv2 outperforms the existing binary networks for KWS by convincing margins across different datasets and achieves comparable accuracy with the full-precision networks (only a tiny 1.51% drop on Speech Commands V1-12). We highlight that benefiting from the compact architecture and optimized hardware kernel, BiFSMNv2 can achieve an impressive 25.1× speedup and 20.2× storage-saving on edge hardware.

Förderung

  • National Key Research and Development Plan of China
  • National Natural Science Foundation of China
  • Fund of State Key Laboratory of Software Development Environment
  • Academic Excellence Foundation of Beihang University (BUAA) for Ph.D. Students

Zitieren

APA

Qin, H., Ma, X., Ding, Y., Li, X., Zhang, Y., Ma, Z., Wang, J., Luo, J., & Liu, X. (2024). BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance. IEEE Transactions on Neural Networks and Learning Systems, 35(8), 10674-10686. https://doi.org/10.1109/tnnls.2023.3243259

Vancouver

Qin H, Ma X, Ding Y, Li X, Zhang Y, Ma Z, et al. BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance. IEEE Transactions on Neural Networks and Learning Systems. 2024;35(8):10674-10686. doi:10.1109/tnnls.2023.3243259

BibTeX
@article{Qin2024,
  author = {Qin, Haotong and Ma, Xudong and Ding, Yifu and Li, Xiaoyang and Zhang, Yang and Ma, Zejun and Wang, Jiakai and Luo, Jie and Liu, Xianglong},
  title = {BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  year = {2024},
  volume = {35},
  number = {8},
  pages = {10674--10686},
  doi = {10.1109/tnnls.2023.3243259}
}
Kostenlos starten →