tion Abstract ChengXiang Zhai (Advisor: John Lafferty) Language Technologies Institute School of Computer Science Carnegie Mellon University With the dramatic increase in online in...
We measure the effects of a weak language model, estimated from as little as 100k words of text, on unsupervised acoustic model training and then explore the best method of using ...
The optimal settings of retrieval parameters often depend on both the document collection and the query, and are usually found through empirical tuning. In this paper, we propose ...
Background: Natural antisense transcripts (NATs) are endogenous RNA molecules that exhibit partial or complete complementarity to other RNAs, and that may contribute to the regula...
Yifei Yin, Yi Zhao, Jie Wang, Changning Liu, Shugu...
This paper focuses on confidence scores for use in acoustic model adaptation. Frame-based confidence estimates are used in linear transform (CMLLR and MLLR) and MAP adaptation. ...