The optimal ratio time-frequency mask for speech separation in terms of the signal-to-noise ratio | Zendy

Shan Liang | Zendy; Wenju Liu | Zendy; Wei Jiang | Zendy; Wei Xue | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

The optimal ratio time-frequency mask for speech separation in terms of the signal-to-noise ratio

Author(s) -

Shan Liang,

Wenju Liu,

Wei Jiang,

Wei Xue

Publication year - 2013

Publication title -

the journal of the acoustical society of america

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.619

H-Index - 187

eISSN - 1520-8524

pISSN - 0001-4966

DOI - 10.1121/1.4824632

Subject(s) - orthogonality , computer science , signal to noise ratio (imaging) , disjoint sets , monaural , correctness , separation (statistics) , signal to interference ratio , speech recognition , noise (video) , interference (communication) , algorithm , acoustics , mathematics , artificial intelligence , telecommunications , physics , power (physics) , channel (broadcasting) , geometry , combinatorics , quantum mechanics , machine learning , image (mathematics)

In this paper, a computational goal for a monaural speech separation system is proposed. Since this goal is derived by maximizing the signal-to-noise ratio (SNR), it is called the optimal ratio mask (ORM). Under the approximate W-Disjoint Orthogonality assumption which almost always holds due to the sparse nature of speech, theoretical analysis shows that the ORM can improve the SNR about 10log(10)2 dB over the ideal ratio mask. With three kinds of real-world interference, the speech separation results of SNR gain and objective quality evaluation demonstrate the correctness of the theoretical analysis, and imply that the ORM achieves a better separation performance.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research