Follow
Steven Wegmann
Steven Wegmann
Verified email at microsoft.com
Title
Cited by
Cited by
Year
Speech and Audio Signal Processing: Processing and Perception of Speech and Music.
B Gold, N Morgan, D Ellis
Chapter 28 Acoustic Model Training: Further Topics, 394-413, 2011
13702011
Training and using pronunciation guessers in speech recognition
LS Gillick, SA Wegmann, JP Yamron
US Patent 7,467,087, 2008
3812008
Inquery and TREC-7
J Allan, J Callan, M Sanderson, J Xu, S Wegmann
NIST Special Publication 500-242: The Seventh Text REtrieval Conference …, 1998
2811998
Speaker normalization on conversational telephone speech
S Wegmann, D McAllaster, J Orloff, B Peskin
1996 IEEE International Conference on Acoustics, Speech, and Signal …, 1996
2791996
Multilingual speech recognition
LS Gillick, TE Lynch, MJ Newman, DL Roth, SA Wegmann, JP Yamron
US Patent 7,716,050, 2010
632010
Dragon systems' 1998 broadcast news transcription system.
S Wegmann, P Zhan, I Carp, M Newman, J Yamron, L Gillick
EUROSPEECH, 1999
591999
The TAO of ATWV: Probing the mysteries of keyword search performance
S Wegmann, A Faria, A Janin, K Riedhammer, N Morgan
2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 192-197, 2013
562013
Progress in broadcast news transcription at dragon systems
S Wegmann, P Zhan, L Gillick
1999 IEEE International Conference on Acoustics, Speech, and Signal …, 1999
521999
Automated assistant for user interaction via speech
JD Andreas, TD Berg-Kirkpatrick, P Chen, JR Cohen, LS Gillick, DLW Hall, ...
US Patent 10,276,160, 2019
432019
Automatic learning of word pronunciation from data
E Fosler, M Weintraub, S Wegmann, YH Kao, S Khudanpur, C Galles, ...
Proceedings of the International Conference on Spoken Language Processing …, 1996
431996
Improvements in recognition of conversational telephone speech
B Peskin, M Newman, D McAllaster, V Nagesha, H Richards, S Wegmann, ...
1999 IEEE International Conference on Acoustics, Speech, and Signal …, 1999
421999
Don't multiply lightly: Quantifying problems with the acoustic model assumptions in speech recognition
D Gillick, L Gillick, S Wegmann
2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 71-76, 2011
412011
Speech recognition using nonparametric speech models
SA Wegmann, LS Gillick
US Patent 6,224,636, 2001
282001
Discriminative training for speech recognition is compensating for statistical dependence in the HMM framework
D Gillick, S Wegmann, L Gillick
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
252012
Sequence to sequence transformations for speech synthesis via recurrent neural networks
DLW Hall, D Klein, D Roth, L Gillick, A Maas, S Wegmann
US Patent App. 15/792,236, 2018
242018
Progress in recognizing conversational telephone speech
B Peskin, L Gillick, N Liberman, M Newman, P van Mulbregt, S Wegmann
1997 IEEE International Conference on Acoustics, Speech, and Signal …, 1997
241997
Automatic learning of word pronunciation from data
M Weintraub
JHU Workshop-96 Project Report, 1996
241996
Dragon Systems’ 1998 broadcast news transcription system for Mandarin
P Zhan, S Wegmann, L Gillick
Proc. 1999 DARPA Broadcast News Workshop, 183-186, 1999
221999
The blame game in meeting room ASR: An analysis of feature versus model errors in noisy and mismatched conditions
SHK Parthasarathi, SY Chang, J Cohen, N Morgan, S Wegmann
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
202013
WS96 project report: Automatic learning of word pronunciation from data
M Weintraub, E Fosler, C Galles, YH Kao, S Khudanpur, M Saraclar, ...
1996 LVCSR Summer Research Workshop Technical Reports, 753-756, 1997
171997
The system can't perform the operation now. Try again later.
Articles 1–20