CONSISTENCY MODELING

Publications

• A. Sankar, V. R. Rao Gadde, A. Stolcke, and F. Weng, "Improved Modeling and Efficiency for Automatic Transcription of Broadcast News", Speech Communication 37(1-2), 133-158, 2002. (PDF)

• A. Sankar,F. Weng, Z. Rivlin, A. Stolcke and R. Gadde, "Development of SRI's 1997 Broadcast News Transcription System," Proceedings of the 1997 DARPA Broadcast News Transcription and Understanding Workshop , pp. 91--96, February, 1998.

• A. Sankar, "Experiments with a Gaussian Merging-Splitting Algorithm for HMM Training for Speech Recognition," Proceedings of the 1997 DARPA Broadcast News Transcription and Understanding Workshop , pp. 99--104, February, 1998.

• F. Weng, A. Stolcke and A. Sankar, "New Developments in Lattice-Based Search Strategies in SRI's Hub4 System," Proceedings of the 1997 DARPA Broadcast News Transcription and Understanding Workshop , pp. 138--143, February, 1998.

• A. Stolcke, "Entropy-Based Pruning of Backoff Language Models," Proceedings of the 1997 DARPA Broadcast News Transcription and Understanding Workshop , pp. 270--274", February, 1998.

• Z. Rivlin, A. Sankar and H. Bratt, "HMM state clustering across allophone class boundaries," Proceedings of the European Conference on Speech Communication and Technology , pp. 127--130, September, 1997.

• L. Heck and A. Sankar, "Acoustic Clustering and Adaptation for Robust Speech Recognition," Proceedings of the European Conference on Speech Communication and Technology , pp. 1867--1870, September, 1997.

• A. Sankar, L. Heck and A. Stolcke, "Acoustic Modeling for the SRI Hub4 Partitioned Evaluation Continuous Speech Recognition System," Proceedings of the DARPA Speech Recognition Workshop, Chantilly, VA , pp 127--132, 1997.

• F. Weng, A. Stolcke and A. Sankar, "Hub-4 Language Modeling using Domain Interpolation and Data Clustering," Proceedings of the DARPA Speech Recognition Workshop, Chantilly, VA , pp 147--151, 1997.

• A. Sankar, L. Neumeyer, and M. Weintraub, ``An Experimental Study of Acoustic Adaptation Algorithms,'' to appear in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing , 1996.

• A. Sankar, A. Stolcke, T. Chung, L. Neumeyer, M. Weintraub, H. Franco and F. Beaufays, ``Noise-resistant Feature Extraction and Model Training for Robust Speech Recognition,'' in Proceedings of the 1996 DARPA CSR Workshop, Ardenhouse, NY

• V. Digalakis, M. Weintraub, A. Sankar, H. Franco, L. Neumeyer, and H. Murveit, ``Continuous Speech Dictation on ARPA's North American Business News Domain,'' Proceedings of the Spoken Language Systems Technology Workshop , pp. 88--93, January, 1995.

• A. Sankar, F. Beaufays, and V. Digalakis, ``Training Data Clustering for Improved Speech Recognition,'' Proceedings of the European Conference on Speech Communication and Technology, Madrid, Spain, September, 1995.

• L. Neumeyer, A. Sankar, and V. Digalakis, ``Comparison of Supervised and Unsupervised Adaptation Techniques'', Proceedings of the European Conference on Speech Communication and Technology, Madrid, Spain, September, 1995.

• V. Digalakis and L. Neumeyer, ``Speaker Adaptation Using Combined Transformation and Bayesian Methods,'' Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing , 1995.

• V. Digalakis, D. Rtischev and L. Neumeyer, ``Speaker Adaptation Using Constrained Reestimation of Gaussian Mixtures,'' IEEE Transactions on Speech and Audio Processing , vol. 3, no. 5, pp 357--366, 1995.

• V. Digalakis, D. Rtischev and L. Neumeyer, ``Speaker Adaptation Using Combined Transformation and Bayesian Methods,'' 1994, accepted for publication in IEEE Transactions on Speech and Audio Processing .

• V. Digalakis, P. Monaco and H. Murveit, ``Genones: Generalized Mixture Tying in Continuous Hidden Markov Model-Based Speech Recognizers,'' 1994, accepted for publication in IEEE Transactions on Speech and Audio Processing.