We propose an algorithm that enables joint Viterbi decoding of multiple independent audio recordings of a word to derive its pronunciation. Experiments show that this method resul...
Let M be a fixed finite monoid. We consider the problem of implementing a data type containing a vector x ϭ ( x1, x2, . . . , xn) ʦ Mn , initially (1, 1, . . . , 1), with two kin...
Gudmund Skovbjerg Frandsen, Peter Bro Miltersen, S...
We propose the first joint model for word segmentation, POS tagging, and dependency parsing for Chinese. Based on an extension of the incremental joint model for POS tagging and ...
Jun Hatori, Takuya Matsuzaki, Yusuke Miyao, Jun-ic...
This paper investigates the correlation between acoustic confidence scores as returned by speech recognizers with recognition quality. We report the results of two machine learni...
el Sequential Memory Abstraction for Model Checking Per Bjesse Advanced Technology Group Synopsys Inc. Many designs intermingle large memories with wide data paths and nontrivial c...