CLSP Homepage : Workshop Homepage
Workshop 2004
Workshop 2004 Monday, November 23, 2009

Landmark-Based Speech Recognition: References

Data and Tools

  1. ICSI Switchboard phoneme transcriptions (http://www.icsi.berkeley.edu/real/stp/index.html)
  2. HTK: http://www.hkt.eng.cam.ac.uk
  3. SRILM: http://www-speech.sri.com/projects/srilm/download.html
  4. SVM Tools: http://www.kernel-machines.org/
  5. SVMlight: http://svmlight.joachims.org/
  6. LibSVM: http://www.csie.ntu.edu.tw/~cjlin/libsvm/

Phonetic Background

  1. G. A. Miller and P. E. Nicely, "Analysis of Perceptual Confusions Among Some English Consonants," JASA 27:338-352, 1955.
  2. K. N. Stevens, S. Y. Manuel, S. Shattuck-Hufnagel, and S. Liu, "Implementation of a Model for Lexical Access Based on Features," ICSLP 1992.

Neural Networks, Nonparametric Methods, and Support Vector Machines for Distinctive Feature Extraction and Classification

  1. Kirchhoff, 1998: http://ssli.ee.washington.edu/people/katrin/Papers/ICSLP98.ps
  2. Shastri, Chang and Greenberg, 1999: http://www.icsi.berkeley.edu/%7Esteveng/PDF/Shastri.pdf
  3. Chang, Shastri and Greenberg, 2000: http://www.icsi.berkeley.edu/~steveng/2000/PDF/ICSLP2000.pdf
  4. Hasegawa-Johnson, 2000: http://www.ifp.uiuc.edu/speech/pubs/2000/icslp00.pdf
  5. Chang and Greenberg, 2001(a): http://www.icsi.berkeley.edu/%7Esteveng/PDF/Elitist.pdf
  6. Chang and Greenberg, 2001(b): http://www.icsi.berkeley.edu/%7Esteveng/PDF/CRAC.pdf
  7. Chang and Greenberg, 2001(c): http://www.icsi.berkeley.edu/%7Esteveng/PDF/Elitist_SpeCom.pdf
  8. Wester, Greenberg and Chang, 2001: http://www.icsi.berkeley.edu/%7Esteveng/PDF/Dutch.pdf
  9. Niyogi and Ramesh, 2002: http://www.cs.uchicago.edu/research/publications/techreports/TR-2002-02
  10. Juneja, 2003: http://www.glue.umd.edu/~juneja/paper_ijcnn.pdf
  11. Juneja, 2003: http://www.glue.umd.edu/~juneja/proposal.pdf
  12. Hasegawa-Johnson, 2003: http://www.ifp.uiuc.edu/speech/pubs/2003/hasegawa_ssp.pdf
  13. Borys, 2003: http://www.ifp.uiuc.edu/speech/pubs/2003/borys_thesis.pdf

HMMs using Landmarks and/or Distinctive Features

  1. Kirchhoff, 2000: http://ssli.ee.washington.edu/people/katrin/Papers/ICASSP00.ps
  2. Omar and Hasegawa-Johnson, 2001: http://www.ifp.uiuc.edu/speech/pubs/2001/wasru01.pdf
  3. K. Kirchhoff, G.A. Fink and G. Sagerer. ``Combining acoustic and articulatory feature information for robust speech recognition.'' Speech Communication, May, 2002.

Pronunciation Modeling

  1. Fosler-Lussier: http://www.cis.ohio-state.edu/~fosler/publications.html
  2. Greenberg, 1999: http://www.icsi.berkeley.edu/~steveng/PDF/SpeakingInShorthandMIME.pdf
  3. Fosler-Lussier, Greenberg, and Morgan, 1999: http://www.icsi.berkeley.edu/%7Esteveng/PDF/ICPhS99-invited.pdf
  4. Greenberg, Harvey and Hitchcock, 2002: http://www.icsi.berkeley.edu/%7Esteveng/PDF/Pronunciation_StressAccent.pdf
  5. Greenberg, Harvey, Hitchcock and Chang 2002: http://www.icsi.berkeley.edu/%7Esteveng/PDF/Beyond_the_Phoneme.pdf
  6. Greenberg, Harvey, Hitchcock and Chang 2003: http://www.icsi.berkeley.edu/%7Esteveng/PDF/Phonetic_Patterning.pdf
  7. Livescu, Glass, and Bilmes, Eurospeech 2003: http://www.sls.csail.mit.edu/klivescu/livescu_eurospeech2003.pdf (Aurora recognition experiments with very limited pronunciation model)
  8. Livescu and Glass, HLT/NAACL-2004: http://www.sls.csail.mit.edu/klivescu/papers/livescu_HLT04.pdf (Switchboard isolated-word "recognition" from ICSI transcriptions using more complex pronunciation model)

The Center for Language and Speech Processing
The Johns Hopkins University
3400 North Charles Street, Barton Hall
Baltimore, MD 21218
*Telephone: (410) 516-4237 *Fax: (410) 516-5050 *E-mail: clsp@clsp.jhu.edu