Abstract. The use of high level information in source separation algorithms can greatly constrain the problem and lead to improved results by limiting the solution space to semanti...
In this paper we present a novel scheme for unstructured audio scene classification that possesses three highly desirable and powerful features: autonomy, scalability, and robust...
Julian Ramos, Sajid M. Siddiqi, Artur Dubrawski, G...
This paper presents a discriminative training (DT) approach to irrelevant variability normalization (IVN) based training of feature transforms and hidden Markov models for large v...
Speech synthesis by unit selection requires the segmentation of a large single speaker high quality recording. Automatic speech recognition techniques, e.g. Hidden Markov Models (...
Pierre Lanchantin, Andrew C. Morris, Xavier Rodet,...
Accurate unsupervised learning of phonemes of a language directly from speech is demonstrated via an algorithm for joint unsupervised learning of the topology and parameters of a ...