Nguyen Bach
Graduate Student
Home | Experience | Miscellaneous | Personal Info

CONTACT INFORMATION

Johns Hopkins University Department of Computer Science 3400 N. Charles Street 224 NEB Baltimore, MD 21218 Phone gif-uks-pihu Email x@y where x=nguyen; y=cs.jhu.edu News: I graduated !!! I moved to Carnegie Mellon University - LTI, School of Computer Science and am doing my PhD. My new email address is x@y where x=nbach, y=andrew.cmu.edu, and homepage is www.cs.cmu.edu/~nbach. More information about my new home will be updated soon.

RESEARCH INTERESTS

• Information retrieval
• Natural language processing
• Speech recognition and synthesis
• Machine learning
• Computational linguistics

I also have interests in applied speech & language technologies to solve issues of speech disorders and hearing impaired persons.

PUBLICATIONS

• H. Mixdorff, N. Bach, et al.: 'Quantitative Analysis and Synthesis of Syllabic Tones in Vietnamese,' Proceeding of The Eighth European Conference on Speech Communication and Technology 2003, Sep 2003, pp 177 - 180. [PDF]
• N. Bach, M. Luong: 'Application of Dynamic Time Warping Algorithm for the recognition of Vietnamese isolated words,' Proceeding of National Scientific Conference in Hanoi, Vietnam, Dec 2001, pp 465 - 473. [PDF in Vietnamese]
  
  

TECHNICAL REPORTS – IMPLEMENTATIONS

• N. Bach, ' MetaShopper - a preliminary study and implementation ', May 2004, Johns Hopkins University
  You can try the implementation here VeryNaiveBookCrawler
• N. Bach, S. Reddy, 'A preliminary quantitative study on the characteristics of Vietnamese vowels and English vowels', May 2004, Johns Hopkins University
• A random sentence generator. Each time you run the generator; it reads the context-free grammar from a file and prints one or more random sentences. This small program was done in September 2003 and updated June 2004. You can try it here: 10 English sentences or 10 Vietnamese sentences with Nguyen_Binh's style
• A text classifier. The program uses 2 training corpora. They can be spam and not-spam or English and Spanish. Given an email the program classifies it to a training group. So for spam detector, the email is determined whether it is spam or not-spam. For language identification, the email is determined whether it is written in English or Spanish. By using smoothing techniques the error rate sharply decreases. I tried uniform, add-lambda, add-lambda backoff, and Witten-Bell backoff.

---

Nguyen Bach

Last modified: Friday, June 09, 2005