Sciweavers

ICASSP
2010
IEEE
13 years 7 months ago
Texas Hold 'Em algorithms for distributed compressive sensing
This paper develops a new class of algorithms for signal recovery in the distributed compressive sensing (DCS) framework. DCS exploits both intra-signal and inter-signal correlati...
Stephen R. Schnelle, Jason N. Laska, Chinmay Hegde...
ICASSP
2010
IEEE
13 years 7 months ago
An alternate approach to adaptive beamforming using SRP-PHAT
An important application for microphone arrays is to extract highquality output from a single wideband source in multi-source and adverse environments. Methods based on blind-sour...
Avram Levi, Harvey F. Silverman
ICASSP
2010
IEEE
13 years 7 months ago
Word confidence calibration using a maximum entropy model with constraints on confidence and word distributions
It is widely known that the quality of confidence measure is critical for speech applications. In this paper, we present our recent work on improving word confidence scores by cal...
Dong Yu, Shizhen Wang, Jinyu Li, Li Deng
ICASSP
2010
IEEE
13 years 7 months ago
Towards multi-speaker unsupervised speech pattern discovery
In this paper, we explore the use of a Gaussian posteriorgram based representation for unsupervised discovery of speech patterns. Compared with our previous work, the new approach...
Yaodong Zhang, James R. Glass
ICASSP
2010
IEEE
13 years 7 months ago
Hierarchical dictionary learning for invariant classification
Sparse representation theory has been increasingly used in the fields of signal processing and machine learning. The standard sparse models are not invariant to spatial transform...
Leah Bar, Guillermo Sapiro
ICASSP
2010
IEEE
13 years 7 months ago
Perceptual audio features for unsupervised key-phrase detection
We propose a new type of audio feature (HFCC-ENS) as well as an unsupervised method for detecting short sequences of spoken words (key-phrases) within long speech recordings. Our ...
Dirk von Zeddelmann, Frank Kurth, Meinard Mül...
ICASSP
2010
IEEE
13 years 7 months ago
Visual localization and segmentation based on foreground/background modeling
In this paper, we propose a novel method to localize (or track) a foreground object and segment the foreground object from the surrounding background with occlusions for a moving ...
Hanzi Wang, Tat-Jun Chin, David Suter
ICASSP
2010
IEEE
13 years 7 months ago
Fast structural similarity index algorithm
The development of real-time image quality assessment algorithms is an important direction on which little research has focused. This paper presents a design of real-time implemen...
Ming-Jun Chen, Alan Conrad Bovik
ICASSP
2010
IEEE
13 years 7 months ago
Large margin filtering for Signal Sequence Labeling
Signal Sequence Labeling consists in predicting a sequence of labels given an observed sequence of samples. A naive way is to filter the signal in order to reduce the noise and t...
Rémi Flamary, Benjamin Labbé, Alain ...