• Publications
  • Influence
On Training Targets for Supervised Speech Separation
  • Yuxuan Wang, A. Narayanan, D. Wang
  • Computer Science, Medicine
  • IEEE/ACM Transactions on Audio, Speech, and…
  • 1 December 2014
TLDR
We evaluate and compare speech separation as a supervised learning problem by using different training targets, including the target binary mask, the ideal ratio mask (IRM), the short-time Fourier transform spectral magnitude and its corresponding mask (FFT-MASK), and the Gammatone frequency power spectrum. Expand
  • 661
  • 99
  • PDF
On Ideal Binary Mask As the Computational Goal of Auditory Scene Analysis
  • D. Wang
  • Computer Science
  • Speech Separation by Humans and Machines
  • 2005
TLDR
A computational-theory analysis of auditory scene analysis, where the main task is to understand the character of the CASA problem. Expand
  • 528
  • 59
  • PDF
Monaural speech segregation based on pitch tracking and amplitude modulation
  • Guoning Hu, D. Wang
  • Computer Science, Medicine
  • IEEE Transactions on Neural Networks
  • 1 September 2004
TLDR
We propose a novel system for voiced speech segregation that segregates resolved and unresolved harmonics differently. Expand
  • 426
  • 53
  • PDF
Image Segmentation Based on Oscillatory Correlation
TLDR
We study image segmentation on the basis of locally excitatory, globally inhibitory oscillator networks (LEGION), whereby the phases of oscillators encode the binding of pixels. Expand
  • 356
  • 36
  • PDF
Separation of speech from interfering sounds based on oscillatory correlation
  • D. Wang, G. Brown
  • Computer Science, Medicine
  • IEEE Trans. Neural Networks
  • 1 May 1999
TLDR
A multistage neural model is proposed for an auditory scene analysis task that performs stream segregation on the basis of oscillatory correlation. Expand
  • 320
  • 36
  • PDF
A multipitch tracking algorithm for noisy speech
TLDR
We present a robust algorithm for multipitch tracking of noisy speech that can reliably track single and double pitch tracks in noisy environment. Expand
  • 294
  • 36
Complex Ratio Masking for Monaural Speech Separation
TLDR
We present a supervised monaural speech separation approach that simultaneously enhances the magnitude and phase spectra by operating in the complex domain. Expand
  • 307
  • 34
  • PDF
Speech segregation based on sound localization
TLDR
We study the cocktail-party effect, which refers to the ability of a listener to attend to a single talker in the presence of adverse acoustical conditions. Expand
  • 352
  • 34
  • PDF
A two-stage algorithm for one-microphone reverberant speech enhancement
  • Mingyang Wu, D. Wang
  • Computer Science
  • IEEE Transactions on Audio, Speech, and Language…
  • 1 December 2006
TLDR
We propose a two-stage reverberant speech enhancement algorithm using one microphone. Expand
  • 208
  • 31
  • PDF
Role of mask pattern in intelligibility of ideal binary-masked noisy speech.
Intelligibility of ideal binary masked noisy speech was measured on a group of normal hearing individuals across mixture signal to noise ratio (SNR) levels, masker types, and local criteria forExpand
  • 161
  • 30
  • PDF
...
1
2
3
4
5
...