Nikki Mirghafori's publications and patents (file updated June 2012). Most of the PDFs can be found here.

Patents

  1. T. Zeppenfeld, N. Mirghafori, L. Guerra, R. Gutierrez, and A. Rajakumar, "Systems, methods, and media for generating hierarchical fused risk scoring," US Patent filed March 2012.

  2. L.P. Heck and N. Mirghafori,   "Method and system for online unsupervised adaptation in speaker verification," US Patent number 6,804,647. Filed March 2001; Granted October 2004.

  3. M. Cohen, L.P. Heck, J. Balogh, J. Riseman, and N. Mirghafori, "Detection of Characteristics of Human-Machine Interactions for Dialog Customization and Analysis," US Patent number 7,263,489. Filed January 2002; Granted August 2007.

Publications

    In Speech Meta-Data Extraction

  1. M. Knox, N. Mirghafori, G. Friedland, "Where did I go wrong?: Identifying troublesome segments for speaker diarization systems", Interspeech 2012, Portland, Oregon, USA.

  2. M. Knox, N. Morgan, and N. Mirghafori, "Getting the last laugh: Automatic laughter segmentation in meetings," Interspeech 2008, Brisbane, Australia.

  3. Y. Huang, G. Friedland, C. Mueller, N. Mirghafori, C. Wooters, "A Fast-Match Approach for Robust, Faster than Real-Time Speaker Diarization," ASRU 2007, Kyoto, Japan.

  4. H. Hung, D. Jayagopi, C. Yeo, G. Friedland, S. Ba, J.-M. Odobez, K. Ramchandran, N. Mirghafori, D. Gatica-Perez, "Using Audio and Video Features to Classify the Most Dominant Person in a Group Meeting," ACM Multimedia 2007.

  5. Y. Huang, G. Friedland, C. Mueller, and N. Mirghafori, "Speeding up speaker diarization by using prosodic features," ICSI TR-04-2007.

  6. M. Knox and N. Mirghafori, "Automatic Laughter Detection Using Neural Networks,"INTERSPEECH 2007, Antwerp, Belgium.

  7. J.G. Fung , D. Hakkani-Tur , M. Magimai , E. Shriberg , S. Cuendet , N. Mirghafori, "Prosodic Features and Feature Selection for Multi-Lingual Sentence Segmentation," INTERSPEECH 2007, Antwerp, Belgium.

  8. M. Magimai Doss, D. Hakkani-Tur, O. Cetin, E. Shriberg, J. Fung, N. Mirghafori, "Entropy based classifier combination for sentence segmentation," ICASSP 2007, Honolulu, Hawaii.

  9. M. Zimmerman, D. Hakkani-Tur, J. Fung, N. Mirghafori, L. Gottlieb, E. Shriberg, Y. Liu, "The ICSI+ Multilingual Sentence Segmentation System," ICSLP 2006, Pittsburg, PA. (pdf)

  10. N. Mirghafori and C. Wooters, "Nuts and Flakes: A Study of Data Characteristics in Speaker Diarization," ICASSP-2006, Toulouse, France. (pdf)

    11. In Speaker Recognition

  11. H. Lei, B. T. Meyer, and N. Mirghafori, "Spectro-Temporal Gabor Features for Speaker Recognition", ICASSP 2012, Kyoto, Japan.

  12. H. Lei and N. Mirghafori, "Data Selection with Kurtosis and Nasality features for Speaker Recognition,", Interspeech 2011, Florence, Italy.

  13. H. Lei and N. Mirghafori, "Comparisons of Recent Speaker Recognition Approaches based on Word-Conditioning," Proc. of Speaker Odyssey, Jan 2008, Stellenbosch, South Africa.

  14. H. Lei and N. Mirghafori, "Word-Conditioned HMM Supervectors for Speaker Recognition," INTERSPEECH 2007, Antwerp, Belgium.

  15. L. Stoll, J. Frankel, N. Mirghafori, "Speaker Recognition via Nonlinear Discriminant Features," Proc. of Non-Linear Speech Processing, May 2007, Paris, France.

  16. H. Lei, N. Mirghafori, "Word-conditioned phone N-grams for speaker recognition," ICASSP 2007, Honolulu, Hawaii.

  17. N. Mirghafori, A.O. Hatch, S. Stafford, K. Boakye, D. Gillick, and B. Peskin, "ICSI's 2005 Speaker Recognition System," ASRU 2005, Puerto Rico. (pdf)

  18. N. Mirghafori and M. Hebert, "Parameterization of the Score Threshold for a Text-Dependent Adaptive Speaker Verification System," ICASSP-2004, Montreal, Canada. (pdf)

  19. M. Hebert and N. Mirghafori, "Desperately Seeking Impostors: Data-Mining for Competitive Impostor Testing in a Text-Dependent Speaker Verification System," ICASSP-2004, Montreal, Canada. (pdf)

  20. N. Mirghafori and L.P. Heck, "An Adaptive Speaker Verification System With Speaker Dependent A Priori Decision Thresholds," Proc. International Conference on Spoken Language Processing, Denver, Colorado, 2002. (pdf)

  21. L.P. Heck and N. Mirghafori, "Unsupervised On-Line Adaptation in Speaker Verification: Confidence-Based Updates and Improved Parameter Estimation," Proc. Adaptation in Speech Recognition, Sophia Antipolis, France, August 2001. (pdf)

  22. L.P. Heck and N. Mirghafori, "Unsupervised On-Line Adaptation in Speaker Verification," Proc. International Conference on Spoken Language Processing, Beijing, China, Oct 2000. (pdf)

    23. In Speech Recognition

  23. C. Wooters, N. Mirghafori, A. Stolcke, T. Pirinen, I. Bulyko, D. Gelbart, M. Graciarena, S. Otterson, B. Peskin, M. Ostendorf, The 2004 ICSI-SRI-UW Meeting Recognition System. Lecture Notes in Computer Science, Volume 3361, Jan 2005, Pages 196 - 208. (pdf)

  24. N. Mirghafori,  A. Stolcke, C. Wooters, T. Pirinen, I. Bulyko, D. Gelbart, M. Graciarena, S. Otterson, B. Peskin, and M. Ostendorf, "From Switchboard to Meetings: Development of the 2004 ICSI-SRI-UW Meeting Recognition System".  ICSLP 2004.(pdf) 

  25. A. Stolcke, C. Wooters,  N. Mirghafori, T. Pirinen, I. Bulyko, D. Gelbart, M. Graciarena, S. Otterson, B. Peskin, M. Ostendorf "Progress in Meeting Recognition:   The ICSI-SRI-UW Spring 2004 Evaluation System". The Proceedings of NIST 2004 Spring Evaluation Workshop. (pdf)

  26. C. Wooters, N. Mirghafori, A. Stolcke, T. Pirinen, I. Bulyko, D. Gelbart, M. Graciarena, S. Otterson, B. Peskin, M. Ostendorf, "The 2004 ICSI-SRI-UW Meeting Recognition System".  Joint AMI/Pascal/IM2/M4 Workshop on Meeting Recognition.

  27. N. Mirghafori and N. Morgan, "Sooner or later: exploring asynchrony in multi-band speech recognition," Proceedings of the 6th European Conference on Speech Communication and Technology, Budapest, Hungary, Sep 1999. (pdf)

  28. N. Mirghafori, "A Multi-Band Approach to Automatic Speech Recognition," PhD Dissertation, University of California at Berkeley, Dec 1998. Reprinted as ICSI Technical Report, TR-99-04, Berkeley, CA, Jan 1999. (postscript)

  29. N. Mirghafori and N. Morgan, "Combining Connectionist Multi-Band and Full-Band Probability Streams for Speech Recognition of Natural Numbers," ICSLP-98, Vol 3, pp 743-747, Sydney, Australia, Nov 1998. (postscript)

  30. N. Mirghafori and N. Morgan, "Transmissions and Transitions: A Study of Two Common Assumptions in Multi-Band ASR," ICASSP-98, pp 713-716, Seattle, Washington, May 1998. (postscript)

  31. N. Mirghafori, "Multi-Band Speech Recognition: A Summary of Recent Work at ICSI," ICSI Technical Report, TR-97-051, Berkeley, California, Dec 1997. (postscript)

  32. N. Morgan, E. Fosler, and N. Mirghafori, "Speech Recognition using On-line Estimation of Speaking Rate," 5th European Conference on Speech Communication and Technology, Rhodes, Greece, Sep 1997, pp. 2079-2083. (postscript)

  33. N. Mirghafori, E. Fosler, and N. Morgan, "Towards Robustness to Fast Speech in ASR," ICASSP-96 , pp. I335-338, Atlanta, Georgia, May 1996. (postscript)

  34. N. Mirghafori, "On Robustness to Fast Speech in Automatic Speech Recognition" Masters Report , University of California at Berkeley, Dec 1995. (postscript)

  35. N. Mirghafori, E. Fosler, and N. Morgan, "Making Automatic Speech Recognition More Robust to Fast Speech," ICSI Technical Report, tr-95-067, Berkeley, California, Dec 1995. (postscript)

  36. N. Mirghafori, E. Fosler, and N. Morgan, "Why Is ASR Harder For Fast Speech And What Can We Do About It?," Proceedings of the IEEE Signal Processing Society Snowbird95 Workshop , pp. 179-180, Snowbird, Utah, Dec 1995. (Postscript)

  37. N. Mirghafori, E. Fosler, and N. Morgan, "Fast Speakers in Large Vocabulary Continuous Speech Recognition: Analysis & Antidotes," EUROSPEECH95 , pp. 491-494, Madrid, Spain, Sep 1995. (Postscript)

  38. N. Mirghafori, N. Morgan, and H. Bourlard, "Parallel Training of MLP Probability Estimators for Speech Recognition: A Gender-Based Approach," Proc. of IEEE Neural Networks for Signal Processing Workshop, Greece, Sep 1994. (Postscript)

  39. N. Morgan, G. Tajchman, N. Mirghafori, Y. Konig, and C. Wooters, "Scaling a Hybrid HMM/MLP System for Large Vocabulary CSR," Proceedings of ARPA's Spoken Language Systems Technology Workshop, Mar 1994.

    40. In Other Areas of Computer Science

  40. O. Vinyals, G. Friedland, and N. Mirghafori, "Revisiting a basic function on current CPUs: A fast logarithm implementation with adjustable accuracy," ICSI Technical Report, TR-07-002, June 2007.

  41. N. Mirghafori, M. Jacoby, and D. Patterson, "Truth in SPEC Benchmarks," Computer Architecture News, Vol. 23, No. 5, pp. 34 - 42, Dec 1995. (Postscript)

  42. N. Mirghafori and A. Fontaine, "A Design for File Access in a Mobile Environment," Proceedings of the Workshop on Mobile Computing Systems & Applications. Santa Cruz, CA, Dec 1994.(Postscript)