Sciweavers

1230 search results - page 167 / 246
» Information retrieval methods for automatic speech recogniti...
Sort
View
EMNLP
2009
14 years 7 months ago
Domain adaptive bootstrapping for named entity recognition
Bootstrapping is the process of improving the performance of a trained classifier by iteratively adding data that is labeled by the classifier itself to the training set, and retr...
Dan Wu, Wee Sun Lee, Nan Ye, Hai Leong Chieu
DSMML
2004
Springer
15 years 3 months ago
Multi Channel Sequence Processing
Abstract. This paper summarizes some of the current research challenges arising from multi-channel sequence processing. Indeed, multiple real life applications involve simultaneous...
Samy Bengio, Hervé Bourlard
ICMI
2009
Springer
129views Biometrics» more  ICMI 2009»
15 years 2 months ago
Cache-based language model adaptation using visual attention for ASR in meeting scenarios
In a typical group meeting involving discussion and collaboration, people look at one another, at shared information resources such as presentation material, and also at nothing i...
Neil Cooke, Martin J. Russell
ACII
2011
Springer
13 years 10 months ago
A Psychologically-Inspired Match-Score Fusion Model for Video-Based Facial Expression Recognition
Communication between humans is rich in complexity and is not limited to verbal signals; emotions are conveyed with gesture, pose and facial expression. Facial Emotion Recognition ...
Albert Cruz, Bir Bhanu, Songfan Yang
CIVR
2007
Springer
160views Image Analysis» more  CIVR 2007»
15 years 4 months ago
Automatic image annotation by an iterative approach: incorporating keyword correlations and region matching
Automatic image annotation automatically labels image content with semantic keywords. For instance, the Relevance Model estimates the joint probability of the keyword and the imag...
Xiangdong Zhou, Mei Wang, Qi Zhang, Junqi Zhang, B...