Publications

Found 11 results
Author Title Type [ Year(Desc)]
Filters: Author is Steven Wegmann  [Clear All Filters]
1996
Fosler-Lussier, E., Weintraub M., Wegmann S., Kao Y-H., Khudanpur S., Galles C., et al. (1996).  Automatic Learning of Word Pronunciation from Data. Proceedings of the Fourth International Conference on Spoken Language Processing (CSLP-96).
2010
Wegmann, S., & Gillick L. (2010).  Why Has (Reasonably Accurate) Automatic Speech Recognition Been So Hard to Achieve?.
2011
Gillick, D., Gillick L., & Wegmann S. (2011).  Don't Multiply Lightly: Quantifying Problems with the Acoustic Model Assumptions in Speech Recognition.
2012
Gillick, D., Wegmann S., & Gillick L. (2012).  Discriminative Training for Speech Recognition is Compensating for Statistical Dependence on the HMM Framework. 4745-4748.
2013
Parthasarathi, S. Hari Krish, Chang S-Y., Cohen J., Morgan N., & Wegmann S. (2013).  The Blame Game in Meeting Room ASR: An Analysis of Feature versus Model Errors in Noisy and Mismatched Conditions.
Morgan, N., Cohen J., Parthasarathi S. Hari Krish, Chang S-Y., & Wegmann S. (2013).  Final Report: OUCH Project (Outing Unfortunate Characteristics of HMMs).
Wegmann, S., Faria A., Janin A., Riedhammer K., & Morgan N. (2013).  The Tao of ATWV: Probing the Mysteries of Keyword Search Performance.
2014
van Hout, J., Ferrer L., Vergyri D., Scheffer N., Lei Y., Mitra V., et al. (2014).  Calibration and Multiple System Fusion for Spoken Term Detection Using Linear Logistic Regression.
Vinyals, O., & Wegmann S. (2014).  Chasing the Metric: Smoothing Learning Algorithms for Keyword Detection.
2016
Su, H., & Wegmann S. (2016).  Factor analysis based speaker verification using ASR. Proceedings of Interspeech 2016.
Ravuri, S., & Wegmann S. (2016).  How neural network depth compensates for HMM conditional independence assumptions in DNN-HMM acoustic models. Proceedings of Interspeech 2016.