• Publications
  • Influence
MVA Processing of Speech Features
TLDR
In this paper, we investigate a technique consisting of mean subtraction, variance normalization and time sequence filtering. Expand
  • 230
  • 41
  • PDF
Frontend post-processing and backend model enhancement on the Aurora 2.0/3.0 databases
TLDR
We investigate a highly effective and extremely simple noiserobust front end based on novel post-processing of standard MFCC features on the Aurora databases. Expand
  • 47
  • 4
  • PDF
Lighting normalization with generic intrinsic illumination subspace for face recognition
TLDR
We propose a lighting normalization method based on the generic intrinsic illumination subspace, which is used as a bootstrap subspace for novel images. Expand
  • 34
  • 3
  • PDF
Effective Attention Mechanism in Dynamic Models for Speech Emotion Recognition
TLDR
We propose to integrate the attention mechanism into deep recurrent neural network models for speech emotion recognition. Expand
  • 20
  • 3
  • PDF
Feature space dimension reduction in speech emotion recognition using support vector machine
TLDR
We report implementations of automatic speech emotion recognition systems based on support vector machines in this paper. Expand
  • 20
  • 3
  • PDF
Low-resource noise-robust feature post-processing on Aurora 2.0
TLDR
We present a highly effective and extremely simple noiserobust front end based on novel post-processing of standard MFC C features. Expand
  • 56
  • 2
  • PDF
Image set compression through minimal-cost prediction structure
TLDR
We propose a new scheme for compressing on image set by building its minimal-cost prediction structure. Expand
  • 31
  • 2
MOMI-Cosegmentation: Simultaneous Segmentation of Multiple Objects among Multiple Images
TLDR
We present a new approach, MOMI-cosegmentation, to segment multiple objects that repeatedly appear among multiple images. Expand
  • 22
  • 2
  • PDF
Improved spoken term detection using support vector machines based on lattice context consistency
TLDR
We propose an improved spoken term detection approach that uses support vector machines trained with lattice context consistency to refine the relevance score of the spoken segments. Expand
  • 13
  • 2
  • PDF
Speech feature smoothing for robust ASR
TLDR
We evaluate smoothing within the context of the MVA (mean subtraction, variance normalization, and ARMA filtering) post-processing scheme for noise-robust automatic speech recognition. Expand
  • 29
  • 1
  • PDF
...
1
2
3
4
5
...