58 search results - page 2 / 12 » Using Gradient Descent Optimization for Acoustics Training f... |
EMNLP
2009
13 years 3 months ago
2009
Many statistical translation models can be regarded as weighted logical deduction. Under this paradigm, we use weights from the expectation semiring (Eisner, 2002), to compute fir...
NAACL
2010
13 years 3 months ago
2010
The goal of this work is to integrate query similarity metrics as features into a dense model that can be trained on large amounts of query log data, in order to rank query rewrit...
TASLP
2008
13 years 5 months ago
2008
We describe an acoustic chord transcription system that uses symbolic data to train hidden Markov models and gives best-of-class frame-level recognition results. We avoid the extre...
JMLR
2012
11 years 7 months ago
2012
“Energy” models for continuous domains can be applied to many problems, but often suffer from high computational expense in training, due to the need to repeatedly minimize t...
CVPR
2000
IEEE
14 years 7 months ago
2000
IEEE
In this work, we approach the classic Mumford-Shah problem from a curve evolution perspective. In particular, we let a given family of curves define the boundaries between regions...