• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Song, Zhigang (Song, Zhigang.) | He, Dongzhi (He, Dongzhi.) | Jiang, Hongchen (Jiang, Hongchen.) | Chang, Jiacheng (Chang, Jiacheng.)

Indexed by:

EI Scopus

Abstract:

Aiming at the problem of insufficient feature learning of time-delay neural networks, which is widely used in the field of language identification, a new architecture called multi-scale and multi-dimensional convolution is proposed. The structure includes a global inter-frame correlation network, local and global multi-scale network, global channel correlation network, and multi-head attention statistics pooling layer. The global inter-frame correlation network models the global context at the initial frame layer to obtain the dependency characteristics of the global context, which makes up for the natural deficiency of time-delay neural network based on limited context; local and global multi-scale networks aggregate the information within and between layers to extract features on a finer and more complex scale; the global channel correlation network is explicitly modeled from the channel dimension to realize the adaptive correction of the channel dimension characteristics; The attention statistics pool layer is extended to multiple heads so that features can be distinguished from multiple aspects. Through the training of the AP17-OLR data set, it has been improved by 41% compared with the previous excellent model. © 2022 SPIE.

Keyword:

Multilayer neural networks Natural language processing systems Time delay Convolution Timing circuits

Author Community:

  • [ 1 ] [Song, Zhigang]Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 2 ] [He, Dongzhi]Faculty of Information Technology, Beijing University of Technology, Beijing, China
  • [ 3 ] [Jiang, Hongchen]Institute of Automation, Chinese Academy of Sciences, Beijing, China
  • [ 4 ] [Chang, Jiacheng]Faculty of Information Technology, Beijing University of Technology, Beijing, China

Reprint Author's Address:

Email:

Show more details

Related Keywords:

Related Article:

Source :

ISSN: 0277-786X

Year: 2022

Volume: 12331

Language: English

Cited Count:

WoS CC Cited Count:

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Affiliated Colleges:

Online/Total:644/5296407
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.