On Ideal Binary Mask as the Computational Goal of Auditory Scene Analysis (Preprint)
Abstract
This chapter intends to examine the goal of CASA. After analyzing the advantages and disadvantages of different computational objectives, I suggest ideal time-frequency (T-F) mask as the computational goal of auditory scene analysis. The remainder of the chapter is organized as follows. The next section reviews different CASA evaluation criteria. Section 3 is devoted to a general discussion of the CASA goal, including an analysis of several alternative CASA objectives. Section 4 introduces the ideal binary mask, analyzes its properties, and argues for its use as the CASA goal. Section 5 describes two models that explicitly estimate the ideal binary mask. Finally, Section 6 concludes the chapter.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 2014
- Accession Number
- AD1151363
Entities
People
- DeLiang Wang
Organizations
- Ohio State University