Word discovery is the task of discovering and collecting occurrences of repeating words in the absence of prior acoustic and linguistic knowledge, or training material. The capabi...
Massive amounts of raw data are currently being generated by biologists while sequencing organisms. Outside of the largest, high-pro le projects such as the Human Genome Project, ...
The rising popularity of Web 2.0, such as blogs, forums, online calendars/diaries, etc., makes users more interested in keeping their data on the Web. Sharing of such data could m...
In this paper, we describe methods to exploit search queries mined from search engine query logs to improve domain detection in spoken language understanding. We propose extending...
Information-theoretic clustering aims to exploit information theoretic measures as the clustering criteria. A common practice on this topic is so-called INFO-K-means, which perfor...