Andrew O. Hatch

Contact information:

The International Computer Science Institute
1947 Center Street, Suite 600
Berkeley, CA 94704

a o h a t c h AT_SYMBOL g m a i l PERIOD c o m

Until recently, I was a post-doctoral researcher at the International Computer Science Institute (ICSI) in Berkeley, California. My research at ICSI focused on machine learning techniques for speech and speaker recognition, with an emphasis on kernel methods and support vector machines (SVMs). In July of 2007, I took a position as a research scientist at the Lawrence Livermore National Lab (LLNL). My research at LLNL is currently focused on applying particle filters to road tracking problems.

• Resume

Publications

• A Generalized Support Vector Machine for Modeling Clustered Data. A. Hatch., technical report, June 2006.
  [.pdf ]
  
  
• Kernel Optimization for Support Vector Machines: Application to Speaker Verification. A. Hatch. Ph.D. Thesis, Department of Electrical Engineering and Computer Sciences (EECS), The University of California, Berkeley, December, 2006.
  [.pdf ]
  
  
• Within-Class Covariance Normalization for SVM-based Speaker Recognition. A. Hatch, S. Kajarekar, and A. Stolcke. proceedings of ICSLP, 2006.
  [.pdf ]
  
  
• Adaptive Linear Kernels for Binary Classification of Multiclass Data. A. Hatch and A. Stolcke. submitted to ICML, 2006.
  [.pdf ]
  
  
• Generalized Linear Kernels for One-Versus-All Classification: Application to Speaker Recognition. A. Hatch and A. Stolcke. proceedings of ICASSP, 2006.
  [.pdf ]
  
  
• Combining Feature Sets with Support Vector Machines: Application to Speaker Recognition. A. Hatch, A. Stolcke and B. Peskin. proceedings of ASRU, 2005.
  [.pdf ]
  
  
• ICSI's 2005 Speaker Recognition System. N. Mirghafori, A. Hatch, S. Stafford, K. Boakye, D. Gillick, and B. Peskin. proceedings of ASRU, 2005.
  [.pdf ]
  
  
• Improved Phonetic Speaker Recognition Using Lattice Decoding. A. Hatch, B. Peskin, and A. Stolcke. proceedings of ICASSP, 2005.
  [.pdf ]