Abstract
This paper proposes a Gaussian mixture model (GMM)-based music discrimination system for mobile broadcasting receivers. The objective of the system is automatically archiving music signals from audio broadcasting programs that are normally mixed with human voices, acoustic noises, commercial advertisements, and so on. To enhance the robustness of the system performance and to sharply cut the starting/ending-point of the recording, we also introduce a post-processing module whose features consist of signal duration, energy dynamics, and local variation of feature statistics. Experimental results to various input signals verify the superiority of the proposed system.
| Original language | English |
|---|---|
| Publication status | Published - 2008 Oct 13 |
| Event | AES 34th International Conference: New Trends in Audio for Mobile and Handheld Devices - Jeju Island, Korea, Republic of Duration: 2008 Aug 28 → 2008 Aug 30 |
Other
| Other | AES 34th International Conference: New Trends in Audio for Mobile and Handheld Devices |
|---|---|
| Country | Korea, Republic of |
| City | Jeju Island |
| Period | 08/8/28 → 08/8/30 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering
- Acoustics and Ultrasonics
Cite this
}
Discrimination of music signals for mobile broadcasting receivers. / Song, Myung Suk; Kang, Hyun Woo; Kang, Hong Goo.
2008. Paper presented at AES 34th International Conference: New Trends in Audio for Mobile and Handheld Devices, Jeju Island, Korea, Republic of.Research output: Contribution to conference › Paper
TY - CONF
T1 - Discrimination of music signals for mobile broadcasting receivers
AU - Song, Myung Suk
AU - Kang, Hyun Woo
AU - Kang, Hong Goo
PY - 2008/10/13
Y1 - 2008/10/13
N2 - This paper proposes a Gaussian mixture model (GMM)-based music discrimination system for mobile broadcasting receivers. The objective of the system is automatically archiving music signals from audio broadcasting programs that are normally mixed with human voices, acoustic noises, commercial advertisements, and so on. To enhance the robustness of the system performance and to sharply cut the starting/ending-point of the recording, we also introduce a post-processing module whose features consist of signal duration, energy dynamics, and local variation of feature statistics. Experimental results to various input signals verify the superiority of the proposed system.
AB - This paper proposes a Gaussian mixture model (GMM)-based music discrimination system for mobile broadcasting receivers. The objective of the system is automatically archiving music signals from audio broadcasting programs that are normally mixed with human voices, acoustic noises, commercial advertisements, and so on. To enhance the robustness of the system performance and to sharply cut the starting/ending-point of the recording, we also introduce a post-processing module whose features consist of signal duration, energy dynamics, and local variation of feature statistics. Experimental results to various input signals verify the superiority of the proposed system.
UR - http://www.scopus.com/inward/record.url?scp=53349156848&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=53349156848&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:53349156848
ER -