- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Knowledge Graph Search feature is available on CiNii Labs
- 【Updated on June 30, 2025】Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
The comparative study on separation of sound sources in various cases
Description
This study focuses on the verification experiment of the blind source separation method about speech signal. In the field of speech and auditory signal processing, research on how to extract specified speech signal from various aliased speech signal is being conducted and compared. The proposal methods is improved based on independent component analysis algorithm. By changing the factors of sources, the reason why the separation was failed can be discovered and improved.
Journal
-
- TENCON 2017 - 2017 IEEE Region 10 Conference
-
TENCON 2017 - 2017 IEEE Region 10 Conference 912-917, 2017-11-01
IEEE