• Publications
  • Influence
A Maximum Likelihood Approach to Single-channel Source Separation
TLDR
This paper presents a new technique for achieving blind signal separation when given only a single channel recording. Expand
  • 186
  • 8
  • PDF
Semi-Local Structure Patterns for Robust Face Detection
TLDR
We propose semi-local structure patterns (SLSP), a novel feature extraction method based on local region-based differences. Expand
  • 34
  • 5
Independent Vector Analysis using Non-Spherical Joint Densities for the Separation of Speech Signals
TLDR
We propose a new blind source separation approach that models the inherent signal dependencies such as those observed in speech signals in order to solve the problem of separating convolved sources. Expand
  • 11
  • 3
  • PDF
Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection
TLDR
We use a CNN for image enhancement and the detection of driving lanes on motorways using an extreme learning machine. Expand
  • 89
  • 2
Single-channel signal separation using time-domain basis functions
TLDR
We present a new technique for achieving blind source separation when given only a single-channel recording by learning a priori sets of time-domain basis functions that encode the sources in a statistically efficient manner. Expand
  • 62
  • 2
  • PDF
A Genetic Algorithm-Based Moving Object Detection for Real-time Traffic Surveillance
TLDR
We present a moving object detection method for real-time traffic surveillance applications using genetic dynamic saliency map and background subtraction. Expand
  • 25
  • 2
Learning statistically efficient features for speaker recognition
TLDR
We apply independent component analysis for extracting an optimal basis to the problem of finding efficient features for a speaker, which is calculated so that each component should be independent upon others on the given training data. Expand
  • 29
  • 2
Acoustic interference cancellation for a voice-driven interface in smart TVs
TLDR
A novel method is proposed to improve the voice recognition performance by suppressing acoustic interferences that add nonlinear distortion to a target recording signal when received by the recognition device. Expand
  • 31
  • 2
The statistical structures of male and female speech signals
TLDR
We use a flexible independent component analysis (ICA) algorithm to adapt the basis functions as well as the source coefficients for male and female speakers respectively. Expand
  • 32
  • 1
A subspace approach to single channel signal separation using maximum likelihood weighting filters
TLDR
We propose a new signal separation algorithm based on a subspace decomposition to extract multiple source signals when only a single observation channel is available. Expand
  • 17
  • 1
  • PDF
...
1
2
3
4
5
...