We present an approach for the cross-lingual induction of speech recognition grammars that separates the task of translation from the task of grammar generation. The source speech...
A two-dimensional (2-D) convolution mask is proposed for detecting the location of irregularities and defects in a periodic two-dimensional signal or image. In this approach, defe...
We propose three new features for MT evaluation: source-sentence constrained n-gram precision, source-sentence reordering metrics, and discriminative unigram precision, as well as...
In text-dependent speaker verification the speech signals have to be time-aligned. For that purpose dynamic time warping (DTW) can be used which performs the alignment by minimizi...
This paper proposes the “Hierarchical Directed Acyclic Graph (HDAG) Kernel” for structured natural language data. The HDAG Kernel directly accepts several levels of both chunk...
Jun Suzuki, Tsutomu Hirao, Yutaka Sasaki, Eisaku M...