Sciweavers

160 search results - page 9 / 32
» Exploiting contextual information for improved phoneme recog...
Sort
View
NIPS
2004
13 years 9 months ago
Contextual Models for Object Detection Using Boosted Random Fields
We seek to both detect and segment objects in images. To exploit both local image data as well as contextual information, we introduce Boosted Random Fields (BRFs), which use boos...
Antonio Torralba, Kevin P. Murphy, William T. Free...
ICASSP
2009
IEEE
14 years 2 months ago
Posterior features applied to speech recognition tasks with user-defined vocabulary
This paper presents a novel approach for those applications where vocabulary is defined by a set of acoustic samples. In this approach, the acoustic samples are used as reference...
Guillermo Aradilla, Hervé Bourlard, Mathew ...
ANLP
1994
80views more  ANLP 1994»
13 years 9 months ago
Improving Language Models by Clustering Training Sentences
Many of the kinds of language model used in speech understanding suffer from imperfect modeling of intra-sentential contextual influences. I argue that this problem can be address...
David M. Carter
ICASSP
2011
IEEE
12 years 11 months ago
Improving text-independent phonetic segmentation based on the Microcanonical Multiscale Formalism
In an earlier work, we proposed a novel phonetic segmentation method based on speech analysis under the Microcanonical Multiscale Formalism (MMF). The latter relies on the computa...
Vahid Khanagha, Khalid Daoudi, Oriol Pont, Hussein...
CAIP
2009
Springer
211views Image Analysis» more  CAIP 2009»
14 years 2 months ago
Contextual-Guided Bag-of-Visual-Words Model for Multi-class Object Categorization
Abstract. Bag-of-words model (BOW) is inspired by the text classification problem, where a document is represented by an unsorted set of contained words. Analogously, in the objec...
Mehdi Mirza-Mohammadi, Sergio Escalera, Petia Rade...