Sciweavers

1243 search results - page 200 / 249
» Reduced-Rank Hidden Markov Models
Sort
View
158
Voted
ECCV
2010
Springer
15 years 8 months ago
Image Segmentation with Topic Random Field
Abstract. Recently, there has been increasing interests in applying aspect models (e.g., PLSA and LDA) in image segmentation. However, these models ignore spatial relationships amo...
NIPS
2007
15 years 7 months ago
HM-BiTAM: Bilingual Topic Exploration, Word Alignment, and Translation
We present a novel paradigm for statistical machine translation (SMT), based on a joint modeling of word alignment and the topical aspects underlying bilingual document-pairs, via...
Bing Zhao, Eric P. Xing
INFORMATICALT
2007
106views more  INFORMATICALT 2007»
15 years 5 months ago
Framework for Choosing a Set of Syllables and Phonemes for Lithuanian Speech Recognition
This paper describes a framework for making up a set of syllables and phonemes that subsequently is used in the creation of acoustic models for continuous speech recognition of Lit...
Sigita Laurinciukaite, Antanas Lipeika
TASLP
2002
84views more  TASLP 2002»
15 years 5 months ago
Substate tying with combined parameter training and reduction in tied-mixture HMM design
Two approaches are proposed for the design of tied-mixture hidden Markov models (TMHMM). One approach improves parameter sharing via partial tying of TMHMM states. To facilitate ty...
Liang Gu, Kenneth Rose
TASLP
2002
124views more  TASLP 2002»
15 years 5 months ago
A robust compensation strategy for extraneous acoustic variations in spontaneous speech recognition
In this paper, we propose a robust compensation strategy to deal effectively with extraneous acoustic variations for spontaneous speech recognition. This strategy extends speaker a...
Hui Jiang, Li Deng