Sciweavers

120 search results - page 15 / 24
» Maximum entropy models for speech confidence estimation
Sort
View
ICASSP
2009
IEEE
14 years 2 months ago
Using collective information in semi-supervised learning for speech recognition
Training accurate acoustic models typically requires a large amount of transcribed data, which can be expensive to obtain. In this paper, we describe a novel semi-supervised learn...
Balakrishnan Varadarajan, Dong Yu, Li Deng, Alex A...
ICIP
2000
IEEE
14 years 9 months ago
Normalized Training for HMM-Based Visual Speech Recognition
This paper presents an approach to estimating the parameters of continuous density HMMs for visual speech recognition. One of the key issues of image-based visual speech recogniti...
Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamur...
SDM
2003
SIAM
110views Data Mining» more  SDM 2003»
13 years 9 months ago
Mixture Models and Frequent Sets: Combining Global and Local Methods for 0-1 Data
We study the interaction between global and local techniques in data mining. Specifically, we study the collections of frequent sets in clusters produced by a probabilistic clust...
Jaakko Hollmén, Jouni K. Seppänen, Hei...
ICASSP
2009
IEEE
14 years 2 months ago
Unsupervised equalization of Lombard effect for speech recognition in noisy adverse environment
When exposed to environmental noise, speakers adjust their speech production to maintain intelligible communication. This phenomenon, called Lombard effect (LE), is known to consi...
Hynek Boril, John H. L. Hansen
ICASSP
2010
IEEE
13 years 8 months ago
Noisy speech enhancement based on prior knowledge about spectral envelope and harmonic structure
This paper considers the enhancement of noisy speech. Earlier studies have revealed that an approach that enhances spectral envelopes by using prior knowledge about the all-pole (...
Takuya Yoshioka, Tomohiro Nakatani, Hiroshi G. Oku...