Single-channel speech enhancement method for high-level background noise mixture

https://tapchi.humg.edu.vn/en/archives?article=1129
  • Affiliations:

    1 Khoa Công nghệ Thông tin, Trường Đại học Mỏ - Địa chất, Việt Nam;
    2 Trường Đại học Công nghiệp Hà Nội, Việt Nam

  • *Corresponding:
    This email address is being protected from spambots. You need JavaScript enabled to view it.
  • Received: 15th-July-2017
  • Revised: 20th-Aug-2017
  • Accepted: 30th-Oct-2017
  • Online: 30th-Oct-2017
Views: 1888
Downloads: 729
Rating: 1.0, Total rating: 72
Yours rating

Abstract:

This paper focuses on using the single-channel source separation techniques to improve the quality of the desired speech in the real-world environment where the speech signal is corrupted by high-level background noise, and especially when there is no source-specific training data. We propose a solution combining the Nonnegative Matrix Factorization model (NMF) with mixed group sparsity constraints to separate the speech signal from the single - channel audio signal with high ambient noise. Experiment result over mixtures containing different real-world noises confirms the effectiveness of the proposed algorithm.

How to Cite
Duong, T.Hien Thi, Tran, H.Thanh, Nguyen, H.Thu, Pham, H.Quang and Vu, L.Kim Thi 2017. Single-channel speech enhancement method for high-level background noise mixture (in Vietnamese). Journal of Mining and Earth Sciences. 58, 5 (Oct, 2017).

Other articles