This paper addresses the training of classification trees for weakly labelled data. We call ”weakly labelled data”, a training set such as the prior labelling information pro...
Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approa...
Lukas Burget, Petr Schwarz, Mohit Agarwal, Pinar A...
Vast segments of the frequency spectrum are licensed to specific users for particular applications. These legacy users, however, often under-utilize their designated spectrum seg...
We investigate whether Amazon’s Mechanical Turk (MTurk) service can be used as a reliable method for transcription of spoken language data. Utterances with varying speaker demog...
Matthew Marge, Satanjeev Banerjee, Alexander I. Ru...
Algorithms such as Least Median of Squares (LMedS) and Random Sample Consensus (RANSAC) have been very successful for low-dimensional robust regression problems. However, the comb...