Sciweavers

ICASSP
2011
IEEE
12 years 11 months ago
A data-driven residual gain approach for two-stage speech enhancement
In this paper, we propose a novel speech enhancement algorithm based on data-driven residual gain estimation. The system consists of two stages. A noisy input signal is processed ...
Yu Gwang Jin, Chul Min Lee, Kiho Cho, Nam Soo Kim
ICASSP
2011
IEEE
12 years 11 months ago
Time-frequency segmentation of bird song in noisy acoustic environments
Recent work in machine learning considers the problem of identifying bird species from an audio recording. Most methods require segmentation to isolate each syllable of bird call ...
Lawrence Neal, Forrest Briggs, Raviv Raich, Xiaoli...
ICASSP
2011
IEEE
12 years 11 months ago
Detection of targets embedded in multipath clutter with Time Reversal
—Detection of targets in complex environments is of importance in both radar and sonar applications. Recent work has shown that the use of Time Reversal (TR) techniques improves ...
Nicholas O'Donoughue, Joel Harley, José M. ...
ICASSP
2011
IEEE
12 years 11 months ago
An ALPS view of sparse recovery
We provide two compressive sensing (CS) recovery algorithms based on iterative hard-thresholding. The algorithms, collectively dubbed as algebraic pursuits (ALPS), exploit the res...
Volkan Cevher
ICASSP
2011
IEEE
12 years 11 months ago
Estimating pressure and volume velocity in the ear canal for insert headphones
It is difficult to measure or estimate accurately the pressure or the volume velocity at the eardrums of human subjects. A method that enables us to determine both the pressure a...
Marko Hiipakka
ICASSP
2011
IEEE
12 years 11 months ago
Using clustering comparison measures for speaker recognition
Recent results seem to cast some doubt over the assumption that improvements in fused recognition accuracy for speaker recognition systems based on different acoustic features are...
Jia Min Karen Kua, Julien Epps, Mohaddeseh Nosrati...
ICASSP
2011
IEEE
12 years 11 months ago
An effective foreground/background segmentation approach for bootstrapping video sequences
In this study, an effective foreground/background segmentation approach for bootstrapping video sequences is proposed. First, a modified block representation approach is used to c...
Han-Hui Hsiao, Jin-Jang Leou
ICASSP
2011
IEEE
12 years 11 months ago
Deep belief nets for natural language call-routing
This paper considers application of Deep Belief Nets (DBNs) to natural language call routing. DBNs have been successfully applied to a number of tasks, including image, audio and ...
Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabha...
ICASSP
2011
IEEE
12 years 11 months ago
Characterization of three-dimensional data with multidimensional deformable models based on B-splines in the fourier domain
This paper presents the formulation and implementation of multidimensional deformable models in the frequency domain. The models are defined by finite element discretization, us...
Rafael Berenguer-Vidal, Rafael Verdú Monede...
ICASSP
2011
IEEE
12 years 11 months ago
Noise power gain as a measure of errors in discrete-time transversal estimators
The noise power gain (NPG) is addressed and the error bound (EB) is specified via NPG for a general p-shift linear timevariant finite impulse response (FIR) transversal estimato...
Yuriy S. Shmaliy, Oscar Gerardo Ibarra-Manzano