Steven Wegmann

发表

Don't multiply lightly: Quantifying problems with the acoustic model assumptions in speech recognition

Larry Gillick, Daniel Gillick, Steven Wegmann, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

Syllable based keyword search: Transducing syllable lattices to word lattices

Hang Su, Eric Fosler-Lussier, Steven Wegmann, 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

The TAO of ATWV: Probing the mysteries of keyword search performance

Nelson Morgan, Korbinian Riedhammer, Adam Janin, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Approximations to the MMI criterion and their effect on lattice-based MMI pdf

Steven Wegmann, 2010, ArXiv.

INQUERY and TREC-8

James Allan, Mark Sanderson, James P. Callan, 1998, TREC.

WS96 project report: Automatic learning of word pronunciation from data

Mitch Weintraub, Sanjeev Khudanpur, Murat Saraclar, 1997 .

The blame game in meeting room ASR: An analysis of feature versus model errors in noisy and mismatched conditions

Sree Hari Krishnan Parthasarathi, Nelson Morgan, Steven Wegmann, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Progress in Broadcast News transcription at Dragon Systems

Puming Zhan, Larry Gillick, Steven Wegmann, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

Why has (reasonably accurate) Automatic Speech Recognition been so hard to achieve? pdf

Larry Gillick, Steven Wegmann, L. Gillick, 2010, ArXiv.

Automatic Learning of Word Pronunciation from Data

Mitch Weintraub, Sanjeev Khudanpur, Murat Saraclar, 1996 .

Dragon systems' 1998 broadcast news transcription system

Puming Zhan, Larry Gillick, Michael Newman, 1999, EUROSPEECH.

How neural network features and depth modify statistical properties of HMM acoustic models

Suman V. Ravuri, Steven Wegmann, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Factor Analysis Based Speaker Verification Using ASR

Hang Su, Steven Wegmann, 2016, INTERSPEECH.

Semi-Automated Speech Transcription System Study

Steven Wegmann, Janet Baker, 1994 .

Improvements in recognition of conversational telephone speech

Don McAllaster, Larry Gillick, Venkatesh Nagesha, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

Chasing the metric: Smoothing learning algorithms for keyword detection

Oriol Vinyals, Steven Wegmann, Oriol Vinyals, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

How Neural Network Depth Compensates for HMM Conditional Independence Assumptions in DNN-HMM Acoustic Models

Suman V. Ravuri, Steven Wegmann, 2016, INTERSPEECH.

On the importance of modeling and robustness for deep neural network feature

Steven Wegmann, Shuo-Yiin Chang, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

WHAT'S WRONG WITH AUTOMATIC SPEECH RECOGNITION (ASR) AND HOW CAN WE FIX IT?

Nelson Morgan, Steven Wegmann, Jordan Cohen, 2013 .

Progress in recognizing conversational telephone speech

Larry Gillick, Natalie Liberman, Barbara Peskin, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Calibration and multiple system fusion for spoken term detection using linear logistic regression

Yun Lei, Dimitra Vergyri, Julien van Hout, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

DRAGON SYSTEMS' AUTOMATIC TRANSCRIPTION OF NEW TDT CORPUS

Puming Zhan, Jonathan Yamron, Larry Gillick, 1998 .

Discriminative training for speech recognition is compensating for statistical dependence in the HMM framework

Larry Gillick, Daniel Gillick, Steven Wegmann, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).