This paper presents a new approach to language model construction, learning a language model not from text, but directly from continuous speech. A phoneme lattice is created using...
Graham Neubig, Masato Mimura, Shinsuke Mori, Tatsu...
Software developers must modify their programs to keep up with changing requirements and designs. Often, a conceptually simple change can require numerous edits that are similar b...
Marat Boshernitsan, Susan L. Graham, Marti A. Hear...
—This paper describes a new approach to matching geometric structure in 2D point-sets. The novel feature is to unify the tasks of estimating transformation geometry and identifyi...
—During collaborative writing each author works on a copy of the shared document. These copies are then merged to produce the final document. This asynchronous work is supported...
Charbel Rahhal, Hala Skaf-Molli, Pascal Molli, Nis...
We present an approach to music identification based on weighted finite-state transducers and Gaussian mixture models, inspired by techniques used in large-vocabulary speech recogn...