Automatic recognition of sound events can be valuable for efficient analysis of audio scenes. For example, detecting human activities like trespassing and hunting in natural environments can play an important role in their preservation by alerting authorities to take action. In the proposed system, each sound class is represented by a hidden Markov model created from descriptors in the time, frequency, and wavelet domains. The system has the ability to automatically adapt to acoustic conditions of different scenes via the feedback loop that refines an unsupervised model. A reliable testing process was adopted for assessing the performance of the system under adverse conditions characterized by highly nonstationary environmental noise.

Authors: Ntalampiras, Stavros; Potamitis, Ilyas; Fakotakis, Nikos
Affiliations: Politecnico di Milano, Milan, Italy; Technological Educational Institute of Crete, Rethymno, Greece; University of Patras, Patras, Greece(See document for exact affiliation information.)
JAES Volume 60 Issue 9 pp. 686-695; September 2012
Publication Date: October 9, 2012

Click to purchase paper as a non-member or you can login as an AES member to see more options.

No AES members have commented on this paper yet.

Subscribe to this discussion

To be notified of new comments on this paper you can subscribe to this RSS feed. Forum users should login to see additional options.

Start a discussion!

If you would like to start a discussion about this paper and are an AES member then you can login here:
Username:
Password:

If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.