Abstract. The prosodic specification of an utterance to be spoken by a Textto-Speech synthesis system can be devised in break indices, pitch accents and boundary tones. In particu...
Abstract. We consider the problem of estimating an unknown probability distribution from samples using the principle of maximum entropy (maxent). To alleviate overfitting with a v...
Abstract. The Gram matrix plays a central role in many kernel methods. Knowledge about the distribution of eigenvalues of the Gram matrix is useful for developing appropriate model...
Speaker indexing has recently emerged as an important task due to the rapidly growing volume of audio archives. Current filtration techniques still suffer from problems both in acc...
We describe the ICSI-SRI-UW team’s entry in the Spring 2004 NIST Meeting Recognition Evaluation. The system was derived from SRI’s 5xRT Conversational Telephone Speech (CTS) r...
Chuck Wooters, Nikki Mirghafori, Andreas Stolcke, ...