1291 search results - page 161 / 259 » Learning a language model from continuous speech |
195
click to vote
CIVR
2007
Springer
16 years 15 days ago
2007
Springer
Near-duplicate keyframes (NDK) play a unique role in large-scale video search, news topic detection and tracking. In this paper, we propose a novel NDK retrieval approach by explo...
138
click to vote
IJCNLP
2005
Springer
15 years 11 months ago
2005
Springer
Abstract. This paper presents our recent work on period disambiguation, the kernel problem in sentence boundary identification, with the maximum entropy (Maxent) model. A number o...
173
click to vote
ICASSP
2011
IEEE
14 years 10 months ago
2011
IEEE
This paper describes a text normalization system for deletion-based abbreviations in informal text. We propose using statistical classifiers to learn the probability of deleting ...
176
click to vote
CIKM
2008
Springer
15 years 8 months ago
2008
Springer
We propose a novel probabilistic method based on the Hidden Markov Model (HMM) to learn the structure of a Latent Variable Model (LVM) for query language modeling. In the proposed...
148
click to vote
NIPS
2003
15 years 7 months ago
2003
We present a novel connectionist model for acquiring the semantics of a simple language through the behavioral experiences of a real robot. We focus on the “compositionality” ...