Abstract. Conditional Random Fields (CRFs) provide a powerful instrument for labeling sequences. So far, however, CRFs have only been considered for labeling sequences over flat al...
Much previous work has investigated weak supervision with HMMs and tag dictionaries for part-of-speech tagging, but there have been no similar investigations for the harder proble...
Preparation, recording, segmentation and pitch labelling of Slovenian diphone inventories are described. A special user friendly intert'ace package was developed in order to ...
Jerneja Gros, Ivo Ipsic, Simon Dobrisek, France Mi...
We present a study on purely data-based recognition of animal sounds, performing evaluation on a real-world database obtained from the Humboldt-University Animal Sound Archive. As...
Modern monaural voice and accompaniment separation systems usually consist of two main modules: melody extraction and timefrequency masking. A main distinction between different s...