Downloadable Code from Perception and Neurodynamics Lab

• GCRN (Gated Convolutional Recurrent Network) with complex spectral mapping for speech enhancement: 2020 Tan-Wang paper & Description and Python code
  

• Deep CASA for talker-independent speaker separation: Description and Tensorflow code for both non-causal and causal versions
  
  • Related papers: 2019 Liu-Wang original paper (non-causal) and 2020 Liu-Wang paper for causal version
    

• CRN (Convolutional Recurrent Network) for real-time speech enhancement: 2018 Tan-Wang paper & Description and Python code
  

• DNN toolbox for speech separation/enhancement: Description and Matlab code
  

• Cochleagram analysis/synthesis toolbox (Including IBM processing): README & Matlab programs
  

• Factorization-based texture segmentation: 2015 Yuan et al. paper & Description and Matlab code
  

• Neural network based pitch tracking in background noise: 2014 Han-Wang paper, Matlab code, & README
  

• Multi-resolution cochleagram (MRCG) feature extraction: 2014 Chen et al. paper, Matlab code, & README
  

• Model-based cochannel speech separation: 2013 Hu-Wang paper & Matlab/C++ code including README
  

• Unsupervised cochannel speech separation: 2013 Hu-Wang paper, Matlab code, & README
  

• Robust speaker identification: 2012 Zhao et al. paper, Matlab code, & README
  

• SNR estimator: 2012 Narayanan-Wang paper, Matlab/C++ code, & README
  

• Regression-based image segmentation: 2012 Yuan et al. paper, Matlab code, & README
  

• Unvoiced speech segregation: 2011 Hu-Wang paper & Matlab code including README
  

• Segregation of reverberant voiced speech: 2011 Jin-Wang paper & Matlab/Java code including README
  

• Multipitch tracking for noisy and reverberant speech: 2011 Jin-Wang Paper, Java code and reference pitch, & README
  

• Tandem algorithm for pitch estimation and speech segregation: 2010 Hu-Wang paper & C++ code including README (both original 128-channel and simplified 64-channel versions)
  

• Monaural musical sound separation: 2009 Li et al. paper & Matlab code including README
  

• Two-microphone separation of speech mixture: 2008 Pedersen et al. paper & Program
  

• GFCC extraction for robust speaker recognition: 2007 Shao et al. paper & Matlab code including README
  

• Auditory segmentation: 2007 Hu-Wang paper & C++ code including README
  

• Singing voice separation: 2007 Li-Wang paper & C++ code including README
  

• One-microphone reverberant speech enhancement: 2006 Wu-Wang paper & Matlab code including README
  

• Voiced speech segregation: 2006 Hu-Wang book chapter/2004 Hu-Wang paper & C++ code including README for the book chapter (recommended)/C++ code for the earlier paper
  

• Localization-based speech segregation: 2003 Roman et al. paper & C++/Matlab code including README
  

• Multipitch tracking for noisy speech: 2003 Wu et al. paper & C++ code (Windows and Linux/Unix platforms) including README
  

• Feature-preserving smoothing and LEGION segmentation: 2000 Chen et al. paper, README, Program directory, & Test images
  

• Speech segregation based on oscillatory correlation: 1999 Wang-Brown paper, README, Program directory, & Test mixtures
  

• Singular limit method for integrating oscillator networks: 1998 Linsay-Wang paper, README, Program directory, & C routine for the 4th-order Runge-Kutta method
  

• Image Segmentation by LEGION Networks: 1997 Wang-Terman paper, README, Program directory, & Test images
  

• Selective gating mechanism for LEGION: 1995 Wang-Terman paper/1995 Terman-Wang paper, README, & Program directory