In this paper, we explore the use of a Gaussian posteriorgram based representation for unsupervised discovery of speech patterns. Compared with our previous work, the new approach...
Detecting the time of occurrence of an acoustic event (for instance, a cheer) embedded in a longer soundtrack is useful and important for applications such as search and retrieval...
Keansub Lee, Daniel P. W. Ellis, Alexander C. Loui
Abstract--Recently Kutin and Niyogi investigated several notions of algorithmic stability--a property of a learning map conceptually similar to continuity--showing that training-st...
We have developed a Ch Mechanism Toolkit for analysis and design of mechanisms. The toolkit was developed using Ch, an embeddable C/C++ interpreter with high-level extensions. The ...
: This paper presents a feature selection technique based on distributional differences for efficient machine learning. Initial training data consists of data including many featur...