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

Author:

Yang, Xue (Yang, Xue.) | Bao, Changchun (Bao, Changchun.)

Indexed by:

CPCI-S EI Scopus

Abstract:

Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent neural network (RNN) to advanced transformer, have been designed sophistically to improve separation performance. However, the state-of-the-art models usually suffer from several flaws related to the computation, such as large model size, huge memory consumption and computational complexity. To find the balance between the performance and computational efficiency and to further explore the modeling ability of traditional network structure, we combine RNN and a newly proposed variant of convolutional network to cope with speech separation problem. By embedding two RNNs into basic block of this variant with the help of dual-path strategy, the proposed network can effectively learn the local information and global dependency. Besides, a four-staged structure enables the separation procedure to be performed gradually at finer and finer scales as the feature dimension increases. The experimental results on various datasets have proven the effectiveness of the proposed method and shown that a trade-off between the separation performance and computational efficiency is well achieved.

Keyword:

computational complexity dual-path strategy memory consumption speech separation deep neural network

Author Community:

  • [ 1 ] [Yang, Xue]Beijing Univ Technol, Fac Informat Technol, Speech & Audio Signal Proc Lab, Beijing, Peoples R China
  • [ 2 ] [Bao, Changchun]Beijing Univ Technol, Fac Informat Technol, Speech & Audio Signal Proc Lab, Beijing, Peoples R China

Reprint Author's Address:

Show more details

Related Keywords:

Related Article:

Source :

INTERSPEECH 2022

ISSN: 2308-457X

Year: 2022

Page: 5338-5342

Cited Count:

WoS CC Cited Count:

SCOPUS Cited Count: 1

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Affiliated Colleges:

Online/Total:560/5287507
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.