Recently there has been interest in structured discriminative models for speech recognition. In these models sentence posteriors are directly modelled, given a set of features ext...
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...
Features generated by Non-Negative Matrix Factorization (NMF) have successfully been introduced into robust speech processing, including noise-robust speech recognition and detect...
Defining suitable features for environmental sounds is an important problem in an automatic acoustic scene recognition system. As with most pattern recognition problems, extracti...
Abstract. Opposing the pre-dominant turn-wise statistics of acoustic LowLevel-Descriptors followed by static classification we re-investigate dynamic modeling directly on the frame...