State-of-the-art speaker diarization systems for meetings are now at a point where overlapped speech contributes significantly to the errors made by the system. However, little i...
Kofi Boakye, B. Trueba-Hornero, Oriol Vinyals, Ger...
This paper presents a new probabilistic framework of Mandarin speech recognition by incorporating a sophisticated hierarchical prosody model into the conventional HMM-based system...
A method for stochastically modeling bidirectionality in chart parsing is presented. A bidirectional parser, which starts analysis from certain dynamically determined positions of ...
With the rise of community-generated web content, the need for automatic assessment of resource quality has grown, particularly in the realm of educational digital libraries. We d...
Philipp G. Wetzler, Steven Bethard, Kirsten R. But...
We illustrate that Web searches can often be utilized to generate background text for use with text classification. This is the case because there are frequently many pages on the...