Publications

Books    Book Chapters    Journal Articles    Conference Papers    Technical Reports    Patents    Awards    Invited Talks     Random Musings   
PUBLICATIONS - Books and Theses

  1. R. A. Gopinath. The Wavelet Transforms and Time-Scale Analysis. Master's Thesis, Rice University, January 1990.
  2. R. A. Gopinath. Wavelets and filter banks - New Results and Applications. Phd Thesis, Rice University, August 1992. gopinath-phd.ps.Z
  3. C. S. Burrus, R. A. Gopinath, and H. Guo. Introduction to Wavelets and Wavelet Transforms - A Primer. Prentice Hall, 1997. 

 

PUBLICATIONS - Book Chapter

  1. R. A. Gopinath and C. S. Burrus. Wavelets and filter banks. In Charles K. Chui, editor, Wavelets: A Tutorial in Theory and Applications , pages 603--654. Academic Press, San Diego, CA, 1992.

PUBLICATIONS - Journal Articles

1.      C. S. Burrus, A. W. Soewito, and R. A. Gopinath. Least squared error fir filter design with transition bands. IEEE Trans. ASSP,ASSP-40(6):1327--1340, June 1992.  burrus-spline.ps ,burrus-spline.pdf

2.      P. Steffen, P. Heller, R. A. Gopinath, and C. S. Burrus. Theory of regular M-band wavelet bases. IEEE Trans. SP, 41(12), December 1993. steffen-regular-trans-sp1993.ps ,steffen-regular-trans-sp1993.pdf

3.      R. A. Gopinath and C. S. Burrus. On upsampling, downsampling and rational sampling rate filter banks. IEEE Trans. SP, April 1994. gopinath-updown-trans-sp1994.ps ,gopinath-updown-trans-sp1994.pdf

4.      R. A. Gopinath and C. S. Burrus. On cosine-modulated wavelet orthonormal bases. IEEE Trans. on Image Processing, 4(2), February 1994. gopinath-cmwlet-trans-ip1994.ps ,gopinath-cmwlet-trans-ip1994.pdf

5.      R. A. Gopinath, J. E. Odegard, and C. S. Burrus. Optimal wavelet representation of signals and the wavelet sampling theorem. IEEE Trans. on CAS II, 41(4):262-277, April 1994. gopinath-optimal-trans-casII1994.ps ,gopinath-optimal-trans-casII1994.pdf

6.      R. A. Gopinath and C. S. Burrus. Unitary FIR filter banks and symmetry. IEEE Trans. on CAS II, 41(10):695-700, October 1994. gopinath-symlets-trans-casII1994.ps ,gopinath-symlets-trans-casII1994.pdf

7.      R. A. Gopinath and C. S. Burrus. Some Results in the theory of modulated filter banks and modulated wavelet tight frames. Applied and Computational Harmonic Analysis 2, 303-326, October, 1995. gopinath-mfb-acha1995.ps ,gopinath-mfb-acha1995.pdf

8.      R. A. Gopinath and C. S. Burrus. Factorization approach to unitary time-varying filter banks. IEEE Trans. SP, 43(3), March 1995. gopinath-tvw-trans-sp1995.ps ,gopinath-tvw-trans-sp1995.pdf

9.      R. A. Gopinath Some thoughts on least-squared-error optimal windows. IEEE Trans. SP, April, 1996. gopinath-thoughts.ps ,gopinath-windows-trans-sp1996.pdf

10.  S. S. Chen, E. M. Eide, M. J. F. Gales, R. A. Gopinath, D. Kanevsky, P. Olsen. Automatic Transcription of Broadcast News Speech Communication, 37 (1-2) (2002) pp. 69-87. chen-bn-spcom2001.ps ,chen-bn-spcom2001.pdf, chen-bn-spcom2001-final.pdf

11.  S. S. Chen and R. A. Gopinath Gaussianization Submitted to Neural Comp, 2000. chen-gaussianization-neuralcomputation2000.ps ,chen-gaussianization-neuralcomputation2000.pdf

12.  S. Deligne and R. A. Gopinath. An EM Algorithm for Convolutive Independent Component Analysis. Neurocomputing - Special issue on BSS/ICA, 2001. deligne-cica-neurocomputing2001.ps ,deligne-cica-neurocomputing2001.pdf

13.  P. Olsen and R. A. Gopinath. Extended MLLT for Gaussian Mixture Models or Modeling Inverse Covariances by Basis Expansion. IEEE Trans. Speech and Audio Processing, January 2004. olsen-emllt-trans-sap2001.ps ,olsen-emllt-trans-sap2001.pdf . Here is the revised version of the same paper olsen-emllt-trans-sap2001-updated.ps ,olsen-emllt-trans-sap2001-updated.pdf

14.  S. Deligne, S. Dharanipragada, R. Gopinath, P. Olsen and H. Printz. A Robust High Accuracy Speech Recognition System for Mobile Applications. IEEE Trans. Speech and Audio Processing, November 2002. deligne-ese-trans-sap2001.ps ,deligne-ese-trans-sap2001.pdf

15.  R. A. Gopinath. The Phaselet Transform - An Integral Redundancy Nearly Shift-Invariant Wavelet Transform. IEEE Trans. Signal Processing, July 2003. gopinath-phaselet-trans-sp2001.ps ,gopinath-phaselet-trans-sp2001.pdf

16.  R. A. Gopinath. Least Squared Error FIR Filters with Flat Amplitude or Group Delay Constraints. IEEE Signal Processing Letters, September 2003. gopinath-fir-splet2001.ps ,gopinath-fir-splet2001.pdf

17.  R.A. Gopinath. Lowpass Delay Filters with Flat Magnitude and Group Delay Constraints. IEEE Trans. Signal Processing, January 2003. gopinath-baher-trans-sp2002.ps ,gopinath-baher-trans-sp2002.pdf

18.  R. A. Gopinath. Phaselets of Framelets. IEEE Trans. Signal Processing, to appear. gopinath-fp-trans-sp2002.ps ,gopinath-fp-trans-sp2002.pdf

19.  S. Axelrod, V. Goel, R. A. Gopinath, P. A. Olsen & K. Visweswariah. Subspace Constrained Gaussian Mixture Models for Speech Recognition. Submitted to IEEE Trans. Speech & Audio Processing, September 2003. axelrod-scgmms-trans-sap2003.ps, axelrod-scgmms-trans-sap2003.pdf

20.  S. Axelrod, V. Goel, R. A. Gopinath, P. A. Olsen & K. Visweswariah. Discriminative Training of Subspace Constrained Gaussian Mixture Models for Speech Recognition. Submitted to IEEE Trans. Speech & Audio Processing, March 2004. axelrod-scgmms-mmi-trans-sap2004.pdf , axelrod-scgmms-mmi-trans-sap2004.ps

PUBLICATIONS - Conferences

1.      R. A. Gopinath and C. S. Burrus. Efficient computation of the wavelet transforms. In Proc. Int. Conf. Acoust., Speech, Signal Processing, pages 1599--1602, Albuquerque, NM, April 1990. gopinath-icassp90.ps ,gopinath-icassp90.pdf

2.      C. S. Burrus, A. W. Soewito, and R. A. Gopinath. Least squared error fir filter design with spline transition functions. In Proc. Int. Conf. Acoust., Speech, Signal Processing, pages 1305--1308, Albuquerque, NM, April 1990. burrus-icassp90.ps ,burrus-icassp90.pdf

3.      R. A. Gopinath, W. M. Lawton, and C. S. Burrus. Wavelet-Galerkin approximation of linear translation invariant operators. In Proc. Int. Conf. Acoust., Speech, Signal Processing, volume 3, pages 2021--2024, Toronto, Canada, May 1991. IEEE. Also Tech. Report CML-TR91-01. gopinath-icassp91.ps ,gopinath-icassp91.pdf

4.      R. A. Gopinath and C. S. Burrus. Wavelet-based lowpass/bandpass interpolation. In Proc. Int. Conf. Acoust., Speech, Signal Processing , volume 4, pages IV385--IV388, San Francisco, CA, March 1992. IEEE. Also Tech. Report CML-TR91-06. gopinath-icassp92.ps ,gopinath-icassp92.pdf

5.      J. E. Odegard, R. A. Gopinath, and C. S. Burrus. Optimal wavelets for signal decomposition and the existence of scale limited signals. In Proc. Int. Conf. Acoust., Speech, Signal Processing, volume 4, pages IV 597--600, San Francisco, CA, March 1992. IEEE. odegard-icassp92.ps ,odegard-icassp92.pdf

6.      R. A. Gopinath, J. E. Odegard, and C. S. Burrus. On the correlation structure of multiplicity M scaling functions and wavelets. In Proc. of the ISCAS, volume 2, pages 959--962, San Diego, CA, May 1992. IEEE. Also Tech. Report CML-TR91-19. gopinath-iscas92-corr.ps ,gopinath-iscas92-corr.pdf

7.      R. A. Gopinath and C. S. Burrus. On the moments of the scaling function y0. In Proc. of the IEEE ISCS, volume 2, pages 963--966, San Diego, CA, May 1992. Also Tech. Report CML-TR91-05. gopinath-iscas92-mom.ps ,gopinath-iscas92-mom.pdf

8.      R. A. Gopinath and C. S. Burrus. On oversampling invariance of wavelet frames. In Proceedings of IEEE-SP Intl. Symposium on Time-Frequency and Time-Scale Analysis, pages 375--378, Victoria, BC, Canada, October 1992. IEEE. gopinath-istfts-92.ps ,gopinath-istfts-92.pdf

9.      R. A. Gopinath and C. S. Burrus. On cosine-modulated orthonormal wavelet bases. In Paper Summaries for the IEEE Signal Processing Society's Fifth DSP Workshop, page 1.10.1, Starved Rock Lodge, Utica, IL, September 1992. IEEE. gopinath-cml-cmwlet1.ps ,gopinath-cml-cmwlet1.pdf

10.  R. A. Gopinath and C. S. Burrus. Theory of modulated filter banks and modulated wavelet tight frames. In Proc. Int. Conf. Acoust., Speech, Signal Processing, Minneapolis, MN, 1993. IEEE. gopinath-icassp93.ps ,gopinath-icassp93.pdf

11.  R. A. Gopinath and C. S. Burrus. A tutorial overview of wavelets, filterbanks and interrelations. In Proc. of the ISCAS, Chicago, IL, May 1993. IEEE.  gopinath-iscas93.ps ,gopinath-iscas93.pdf

12.  R. A. Gopinath. Factorization approach to time-varying filter banks and wavelets. In Proc. Int. Conf. Acoust., Speech, Signal Processing , Adelaide, Australia, 1994. IEEE. gopinath-icassp94.ps ,gopinath-icassp94.pdf

13.  R. A. Gopinath. Some thoughts on least squares optimal windows. In Proc. of the ISCAS, London, May 1994. IEEE. gopinath-iscas94.ps ,gopinath-iscas94.pdf

14.  R. A. Gopinath. Introduction to time-varying filter banks and wavelets. In Proc. of the IFAC Symposium on Modeling and Control in Biomedical Systems, Galveston, TX, 1994. IEEE. gopinath-ifac94.ps ,gopinath-ifac94.pdf

15.  R. A. Gopinath, M. Lang, H. Guo, J. E. Odegard. Wavelet Based Post-Processing of Low Bitrate Transform Coded Images. In Proc. of Intl. Conf. in Image Processing, Austin, TX, November 1994. gopinath-icip94.ps ,gopinath-icip94.pdf

16.  R. A. Gopinath, M. Lang, H. Guo, J. E. Odegard. Enhancement of decompressed images at low bitrates In Proc. of SPIE, Mathematical Imaging: Wavelet Appications in Signal Processing and Image Processing II , July 1994. gopinath-spie94.ps ,gopinath-spie94.pdf

17.  H. Guo, J. E. Odegard, M. Lang, R. A. Gopinath, I. Selesnick, C. S. Burrus. Wavelet Based Speckle-reduction with with Applications to SAR based ATD/R. In Proc. of SPIE, Mathematical Imaging: Wavelet Appications in Signal Processing and Image Processing II, July 1994. guo-icip94.ps ,guo-icip94.pdf

18.  H. Guo, J. E. Odegard, M. Lang, R. A. Gopinath, I. Selesnick, C. S. Burrus. Wavelet Based Speckle-reduction with with Applications to SAR based ATD/R. In Proc. of Intl. Conf. in Image Processing, Austin, TX, November 1994. guo-spie94.ps ,guo-spie94.pdf

19.  R. A. Gopinath, M. Gales, P. S. Gopalakrishnan, S. Balakrishnan-Aiyer and M. A. Picheny Robust speech recognition in noise - performance of the IBM continuous speech recognizer on the ARPA noise task. In Proc. of Spoken Language Systems Tech. Workshop, Austin, TX, January 1995. gopinath-arpa95.ps ,gopinath-arpa95.pdf

20.  R. A. Gopinath Nonlinear recovery of sparse signals from narrowband data. In Proc. Int. Conf. Acoust., Speech, Signal Processing , Detroit, Michigan, May 1995. gopinath-icassp95.ps ,gopinath-icassp95.pdf

21.  R. A. Gopinath. Modulated Filter Banks and Wavelets - A General Unified Theory. Proc. of Int. Conf. Acoust., Speech, Signal Processing , Atlanta, Georgia, May 1996. gopinath-icassp96.ps ,gopinath-icassp96.pdf

22.  C. J. Chen, R. A. Gopinath, M. D. Monkowski, and M. A. Picheny A Continuous Speaker-Independent Putonghua Dictation System Proc. Int. Conf. Signal Processing, Oct. 1996, Beijing, pp. 821-824. chen-icsp96.ps ,chen-icsp96.pdf

23.  R. Bakis, S. Chen, P. S. Gopalakrishnan, R. A. Gopinath, S. Maes and L. Polymenakos. Transcription of Radio Broadcast News with the IBM Large Vocabulary Speech Recognition System. Proc. of ARPA Workshop on Human Language Understanding , Arden House, New York, February 18-22 1996. gopalakrishnan-hlt96.ps ,gopalakrishnan-hlt96.pdf

24.  P. S. Gopalakrishnan, R. A. Gopinath, S. Maes, M. Padmanabhan, L. Polymenakos, H. Printz and M. Franz. Transcription of Broadcast News - System Robustness Issues and Adaptation Techniques. Proc. ICASSP 1997 , Munich, Germany, April, 1997. gopalakrishnan-icassp97.ps ,gopalakrishnan-icassp97.pdf

25.  R. Bakis, S. Chen, P. S. Gopalakrishnan, R. A. Gopinath, S. Maes and L. Polymenakos. Transcription of Radio Broadcast News with the IBM Large Vocabulary Speech Recognition System. Proc. of ARPA Workshop on Human Language Understanding, Chantilly, VA, February 2-5 1997. bakis-slt97.ps ,bakis-slt97.pdf

26.  J. Chen, R. A. Gopinath, M. Monkowski, M. Picheny, and K. Shen New Methods in continuous Mandarin Speech Recognition Proc. EUROSPEECH '97, Vol. 3, pp. 1547-1550. chen-eurospeech97.ps ,chen-eurospeech97.pdf

27.  L. Polymenakos, P. Olsen, D. Kanvesky, R. A. Gopinath, P. S. Gopalakrishnan, S. Chen and H. Printz Transcription of Broadcast News Using IBM's LVCSR System Proc. of ARPA Workshop on Human Language Understanding, January, 1998. polymenakos-slt98.ps ,polymenakos-slt98.pdf

28.  R. A. Gopinath Constrained Maxmimum Likelihood Modeling with Gaussian Distributions. Proc. of ARPA Workshop on Human Language Understanding, January, 1998. gopinath-slt98.ps ,gopinath-slt98.pdf

29.  R. A. Gopinath Maxmimum Likelihood Modeling with Gaussian Distributions for Classification ICASSP '98, Seattle, USA. gopinath-icassp98.ps ,gopinath-icassp98.pdf

30.  L. Polymenakos, P. Olsen, D. Kanvesky, R. A. Gopinath, P. S. Gopalakrishnan and S. Chen Transcription of Broadcast News - Some Recent Improvements to IBM's LVCSR System ICASSP '98, Seattle, USA.  polymenakos-icassp98.ps ,polymenakos-icassp98.pdf

31.  R. A. Gopinath, B. Ramabhadran and S. Dharanipragada. Factor Analysis Invariant to Linear Transformations of Data Proc. Intl. Conf. on Spoken Language Processing, ICSLP '98, Sydney, Australia. gopinath-icslp98.ps ,gopinath-icslp98.pdf

32.  S. Dharanipragada and R. A. Gopinath Smoothed Cepstral Trajectories for Speech Recognition. Proc. Intl. Conf. on Spoken Language Processing, ICSLP '98, Sydney, Australia. dharanipragada-icslp98.ps ,dharanipragada-icslp98.pdf

33.  S. S. Chen, E. M. Eide, M. J. F. Gales, R. A. Gopinath, D. Kanevsky and P. Olsen. Recent Improvements to IBM's Speech Recognition System for Automatic Transcription of Broadcast News, Proceedings of 1999 ARPA Workshop on HLT, Washingon-DC, USA. chen-slt99.ps ,chen-slt99.pdf

34.  S. S. Chen, E. M. Eide, M. J. F. Gales, R. A. Gopinath, D. Kanevsky, P. Olsen. Recent Improvements to IBM's Speech Recognition System for Automatic Transcription of Broadcast News, ICASSP 99, Phoenix, AZ, March 1999. chen-icassp99.ps ,chen-icassp99.pdf

35.  S. S. Chen and R. A. Gopinath Model Selection in Acoustic Modeling. Proc. Eurospeech 99, Budapest, Hungary, September 1999. chen-eurospeech99.ps ,chen-eurospeech99.pdf

36.  A. Tritschler and R. A. Gopinath Improved Segmentation and Segment Clustering using the Bayesian Information Criterion. Eurospeech 1999, Budapest, Hungary, September, 1999. tritschler-eurospeech99.ps ,tritschler-eurospeech99.pdf

37.  G. Saon, M. Padmanabhan, R. A. Gopinath and S. Chen. Maximum Likelihood Discriminant Feature Spaces, ICASSP 2000, Istanbul, Turkey, June 2000. saon-icassp2000.ps ,saon-icassp2000.pdf

38.  U. Chaudhari, R. A. Gopinath and S. Maes. Pattern-Specific ML Transformations for Speaker Recognition, ICSLP 2000. chaudhari-icslp2000.ps ,chaudhari-icslp2000.pdf

39.  E. Eide, B. Maison, S. Chen, P. Olsen, D. Kanevsky and R. A. Gopinath. IBM's 10xRT system in the 1999 ARPA Broadcast News Evaluation. Proc. ICSLP 2000. eide-icslp2000.ps ,eide-icslp2000.pdf

40.  S. Chen and R. A. Gopinath. Gaussianization Proc. NIPS 2000, Denver Colorado. chen-nips2000.ps ,chen-nips2000.pdf

41.  N. K. Goel and R. A. Gopinath. Multiple Linear Transforms, Proc. ICASSP 2001. goel-icassp2001.ps ,goel-icassp2001.pdf

42.  B. Maison and R. A. Gopinath. Robust Confidence Annotation and Rejection for Continuous Speech Recognition, Proc. ICASSP 2001. maison-icassp2001.ps ,maison-icassp2001.pdf

43.  S. Deligne, B. Maison and R. A. Gopinath. Automatic Generation and Selection of Baseforms for Dynamic Vocabularies, Proc. ICASSP 2001. deligne-icassp2001.ps ,deligne-icassp2001.pdf

44.  S. Fine, J. Navratil and R. A. Gopinath. Hybrid GMM/SVM Approach to Speaker Identification, Proc. ICASSP 2001. fine-icassp2001.ps ,fine-icassp2001.pdf

45.  L. Comerford, D. Frank. P. S. Gopalakrishnan, R. A. Gopinath and J. Sedivy. The IBM Personal Speech Assistant, Proc. ICASSP 2001. comerford-icassp2001.ps ,comerford-icassp2001.pdf

46.  S. Deligne, E. Eide, R. A. Gopinath, D. Kanevksy, B. Maison, P. Olsen, H. Printz and J. Sedivy. Low-Resource Speech Recognition of 500-word Vocabularies, Proc. Eurospeech 2001. deligne-eurospeech2001.ps ,deligne-eurospeech2001.pdf

47.  S. Fine, J. Navratil and R. A. Gopinath. Enhancing GMM Scores Using SVM Hints, Proc. Eurospeech 2001. fine-eurospeech2001.ps ,fine-eurospeech2001.pdf

48.  P. A. Olsen and R. A. Gopinath. Modeling the Structure of the Inverse Covariance Matrix in Gaussian Mixture Models Submitted to NIPS 2001 (paper was rejected). olsen-nips2001.ps ,olsen-nips2001.pdf

49.  S. Deligne and R. A. Gopinath. Robust Speech Recognition Using Mutlichannel Codebook Dependent Cepstral Normalization (MCDCN). ASRU 2001. deligne-asru2001.ps ,deligne-asru2001.pdf

50.  G. Saon, M. Padmanabhan, and R. A. Gopinath. Eliminating Inter-Speaker Variability Prior to Linear Discriminant Transforms. ASRU 2001. saon-asru2001.ps ,saon-asru2001.pdf

51.  R. A. Gopinath, V. Goel, K. Visweswariah and P. Olsen. Adaptation Experiments on the Spine Database using the Extended Maximum Likelihood Linear Transformation (EMLLT) Model. ICASSP 2002 gopinath-icassp2002.ps ,gopinath-icassp2002.pdf

52.  P. Olsen and R. A. Gopinath. Modeling Inverse Covariances in Gaussian Mixture Models. ICASSP 2002 olsen-icassp2002.ps ,olsen-icassp2002.pdf

53.  M. Novak, R. A. Gopinath and J. Sedivy. Efficient Hierarchical Labeler Algorithm for Gaussian Likelihoods Computation in Resource Constrained Speech Recognition Systems. submitted to ICASSP 2002 (paper was rejected) novak-icassp2002.ps ,novak-icassp2002.pdf

54.  V. Goel, K. Visweswariah and R. A. Gopinath. Rapid Adaptation with Linear Combinations of Rank One Matrices. ICASSP 2002 goel-icassp2002.ps ,goel-icassp2002.pdf

55.  K. Visweswariah, V. Goel, and R. A. Gopinath. Structuring Linear Transformations For Adaptation Using Training Time Information. ICASSP 2002 visweswariah-icassp2002.ps ,visweswariah-icassp2002.pdf

56.  B. Xiang, U. Chaudhari, J. Navratil, G. Ramaswamy and R. Gopinath Short-Time Gaussianization for Robust Speaker Verification. ICASSP 2002 xiang-icassp2002.ps ,xiang-icassp2002.pdf

57.  S. Fine, G. Saon and R. A. Gopinath. Digits Recognition in a Noisy Environment via a Sequential GMM/SVM System. ICASSP 2002 fine-icassp2002.ps ,fine-icassp2002.pdf

58.  S. Axelrod, R. Gopinath and P. Olsen. Modeling with a Subspace Constraint on Inverse Covariances. ICSLP 2002 axelrod-icslp2002.ps ,axelrod-icslp2002.pdf

59.  K. Visweswariah, V. Goel, and R. A. Gopinath. Maximum Likelihood Training of Bases for Rapid Adaptation. Submitted to ICSLP 2002 (paper was rejected) visweswariah-icslp2002.ps ,visweswariah-icslp2002.pdf

60.  J. Huang, V. Goel, R. A. Gopinath, B. Kingsbury, P. Olsen and K. Visweswariah. Large Vocabulary Conversational Speech Recognition with the Extended Maximum Likelihood Linear Transformation (EMLLT) Model. ICSLP 2002 huang-icslp2002.ps ,huang-icslp2002.pdf

61.  S. Deligne and R. A. Gopinath. An EM Algorithm for Convolutive Independent Component Analysis. SAM 2002. deligne-sam2002.ps ,deligne-sam2002.pdf

62.  S. Axelrod, R. A. Gopinath, P. Olsen and K. Visweswariah. Dimensional Reduction, Covariance Modeling and Computational Complexity in ASR Systems. ICASSP 2003. axelrod-icassp2003.ps ,axelrod-icassp2003.pdf

63.  K. Visweswariah, P. Olsen, R. A. Gopinath and S. Axelrod. Maximum Likelihood Training of Subspaces for Inverse Covariance Modeling. ICASSP 2003. visweswariah-icassp2003.ps ,visweswariah-icassp2003.pdf

64.  K. Visweswariah, S. Axelrod and R. A. Gopinath. Acoustic Modeling with Mixtures of Subspace Constrained Exponential Models, Eurospeech 2003. visweswariah-eurospeech2003.ps, visweswariah-eurospeech2003.pdf

65.  V. Goel, S. Axelrod, R. A. Gopinath, P. Olsen and K. Visweswariah. Discriminative Estimation of Subspace Precision & Mean (SPAM) Models, Eurospeech 2003. goel-eurospeech2003.ps, goel-eurospeech2003.pdf

66.  S. Axelrod, V. Goel, B. Kingsbury, K. Visweswariah and R. A. Gopinath. Large Vocabulary Conversational Speech Recognition with a Subspace Constraint on Inverse Covariance Matrices, Eurospeech 2003. axelrod-eurospeech2003.ps, axelrod-eurospeech2003.pdf

67.  P. Olsen, S. Axelrod, K. Visweswariah and R. A. Gopinath. Gaussian Mixture Modeling with Volume Preserving Non-linear Feature Space Transforms. ASRU 2003. olsen-asru2003.ps, olsen-asru2003.pdf

68.  K. Visweswariah, R. A. Gopinath and V. Goel. Task Adaptation of Acoustic and Language Models Based on Large Quantities of Data. ICSLP 2004. visweswariah-icslp2004a.ps, visweswariah-icslp2004a.pdf

69.  K. Visweswariah, and R. A. Gopinath. Adaptation of front end parameters in a speech recognizer. ICSLP 2004. visweswariah-icslp2004b.ps, visweswariah-icslp2004b.pdf

70.  P. Olsen, K. Visweswariah, and R. A. Gopinath. Initializing Subspace Constrained Gaussian Mixture Models. ICASSP2005. olsen-icassp2005.ps, olsen-icassp2005.pdf

71.  T. Kristjansson and R. A. Gopinath. Cepstral Domain Laplace Denoising Algorithm. Submitted to ICASSP2005 (paper was rejected). kristjansson-icassp2005.ps, kristjansson-icassp2005.pdf

72.  S. S. Kozat, K. Visweswariah and R. A. Gopinath, " Efficient, low latency adaptation for speech recognition," Submitted to ICASSP 2006. kozat-icassp2006a.pdf

73.  S. S. Kozat, K. Visweswariah and R. A. Gopinath, "Feature adaptation based on Gaussian posteriors," Submitted to ICASSP 2006. kozat-icassp2006b.pdf

74.  V. Goel and R. Gopinath, "Using EM Clustering to Build Optimal Trees for Dialog Context Sensitive Language Models," Submitted to ICASSP 2006. goel-icassp2006.pdf

75.  S. Rennie, T. Kristjansson, P. Olsen and R. Gopinath, "Dynamic Noise Adaptation," ICASSP 2006. rennie-icassp2006.pdf

76.  T. Kristjansson, J. Hershey , P. Olsen , S. Rennie and R. A. Gopinath, "Super-human multi-talker speech recognition: The IBM 2006 speech separation challenge system," ICSLP 2006. kristjansson-icslp2006.pdf

PUBLICATIONS - Technical Reports

  1. R. A. Gopinath. On the Moments of the Scaling Function. Tech. Report, Sept. 1989, Aware Inc., Cambridge, MA-02138.
  2. R. A. Gopinath. Lattice Structure for VLSI Fixed Point Implementation of CQFs. Tech. Report, Oct. 1989, Aware Inc., Cambridge, MA-02138. 
  3. R. A. Gopinath. Efficient Computation of The Continuous Wavelet Transform. Tech. Report, Sept. 1989, Aware Inc., Cambridge, MA-02138.
  4. R. A. Gopinath. Moment Theorem for the Wavelet-Galerkin Method. Tech. Report, March 1990, Aware Inc., Cambridge, MA-02138.
  5. R. A. Gopinath. Uniform vs. Max-Lloyd Quantization for Wavelet-based Image Coding. Tech. Report, July 1990, Aware Inc., Cambridge, MA-02138. 

INVITED TALKS AND PANEL DISCUSSIONS

1.      IMA Workshop: Mathamatical Foundations of Speech Processing and Recognition, University of Minn., September 22 2000. Gaussianziation ima-workshop-2000.ps , ima-workshop-2000.pdf

2.       Johns Hopkins University CLSP Summer Workshop, July 18 2001 . Part I: Multiple Linear Transformations for Classification. Part II: Enhancing GMM Scores Using SVM Hints. jhu-workshop-2001.ps ,jhu-workshop-2001.pdf

3.      Symbol Technologies Seminar at Polytechnic University, Brooklyn, March 21 2002. Gaussian Mixture Modeling with the EMLLT Model. poly-seminar-2002.ps ,poly-seminar-2002.pdf

4.      Dimacs Workshop on Source Coding and Harmonic Analysis, Rutgers University, May 9, 2002 . The Phaselet Transform - An Integral Redundancy Nearly Shift-Invariant Wavelet Transform. dimacs-workshop-2002.ps,dimacs-workshop-2002.pdf

5.      California Institute for Telecommunications & Information Technology Seminar, University of San Diego, CA, March 4, 2003. Conversational Interface Technologies.

6.      Rice University Electrical & Computer Engineering Seminar, Rice University, TX, September 25, 2003. Subspace Constrained Gaussian Mixture Models for Speech Recognition. rice-seminar-2003.ps, rice-seminar-2003.pdf

7.      Automatic Speech Recognition and Understanding Workshop 2003, St. Thomas, Virgin Islands, December 3, 2003. Panel Discussion.

8.      International Conference on Acoustics, Speech and Signal Processing 2004, Montreal, Canada, May 17, 2004. Panel Discussion on Robust Speech Recognition in the Real World. icassp2004-robustness-panel-discussion.pdf

9.      University of Washington Seminar, Seattle, November 7th 2005. Some Recent Advances in Gaussian Mixture Modeling for Speech Recognition. uwash-seminar-2005.pdf

1.      Microsoft Research Seminar, Redmond, November 8th 2005. Some Recent Advances in Gaussian Mixture Modeling for Speech Recognition, msr-seminar-2005.pdf

RANDOM MUSINGS

This section is a few (some incomplete) manuscripts that are random musings on some technical topic or other. Over the years I’ve realized that there are several threads of research that I’ve plodded along, but not sufficiently enough to encode into a paper as a finished piece of work. However, after a few years I’ve revisited the topic (e.g., SVMs below) and found it useful to go back on my notes from that topic. More often that not I would have to re-learn everything thanks to my feeble recollection and lack of notes. These are the lucky cases when I do have some notes….

1.      R. A. Gopinath. Kernel PCA and LDA, April 2000. gopinath-kernelpcalda.ps , gopinath-kernelpcalda.pdf

2.      R. A. Gopinath. A Suite of Simple Algorithms for Support Vector Machine Optimization. March 2001. gopinath-svm-simple-algorithms.pdf

3.      R. A. Gopinath. Large-Scale Support Vector Machine Training Using Low Dimensional Approximations of the Kernel Matrix. March 2001. gopinath-svm-kernelapprox.pdf

PATENTS

1.      H. L. Resknikoff, W. M. Lawton, D. Pollen and R. A. Gopinath, Novel Spread Spectrum CODEC apparatus and Method , U.S. Patent #5081645, Issued 1/14/1992 .

2.      J.Chen, R.A.Gopinath, M. Monkowski and M. A. Picheny, Statistical Acoustic Processing Method and Apparatus for Speech Recognition Using a Phoneme System , U.S. Patent #5751901, Issued 5/121998 .

3.      P. S. Gopalakrishnan, R. A. Gopinath, M. Padmanabhan, L. Polymenakos and S. Maes, Transcription of speech data with segments from acoustically dissimilar environments , US Patent #6067517, Issued 5/23/2000.

4.      U. Chaudhari, R. A. Gopinath and S. Maes, Method and Apparatus for Performing Pattern Specific Maximum Likelihood Linear Transformations for Speaker Recognition, US Patent #6751590, issued 6/15/2004.

5.      E.Eide, R. A. Gopinath, D. Kanevsky and P. Olsen, Methods and Apparatus for Improving Automatic Digitization Techniques Using Decoding Metrics, U.S. Patent Filed October 29, 1999. 

6.      S. Chen and R. A. Gopinath, High Dimensional Acoustic Modeling Via Mixtures of Compound Gaussians with Linear Transforms, U.S. Patent #6539351, Issued 3/25/2003.

7.      S. Chen and R. A. Gopinath, High Dimensional Data Mining and Visualization via Gaussianization, U.S. Patent #6591235, Issued 7/8/2003.

8.       G. Saon, M. Padmanabhan and R. A. Gopinath, Methods and Apparatus for Performing heteroscedastic discriminant analysis in pattern recognition systems, U.S. Patent #6609093, Issued 8/19/2003.

9.       S. Deligne, B. Maison and R. A. Gopinath, Automatic Generation of Multiple Pronunciations from Acoustic Data, U.S. Patent Filed, September 2000. 

10.  N. K. Goel and R. A. Gopinath, System and Method for Enhancing Speech and Pattern Recognition Using Multiple Linear Transforms, U.S. Patent Filed November 2000. 

11.  S. Deligne, and R. A. Gopinath, Multi-Channel Codebook Dependent Compensation , U.S. Patent Filed March 14, 2001.

12.  S. Deligne and R. A. Gopinath, An EM algorithm for Convolutive Independent Component Analysis (CICA), U.S. Patent #6622117, Issued 9/16/2003. 

13.  B. Maison, R. Gopinath and B. Wu. Natural error correction for speech recognition using phrase repetitions, confidence scores and template matching. U.S. Patent Filed July 31, 2002.  

AWARDS

1.      IBM Research Division Award: in appreciation for Contributions to the real-time Mandarin Continuous Speech Recognition System. February 1995.

2.      IBM Research Division Award: in appreciation for Contributions to the successful launch of IBM Voicetype 3.0 Speech Recognition Product. July 1996.

3.      IBM Outstanding Innovation Award: in appreciation for Broadcast News Transcription Technologies. July 1999.

4.      IBM Outstanding Technical Achievement Award: in appreciation for ViaVoice for Embedded Multiplatforms. September 2000.