Commit 42392732 authored by Dan Povey's avatar Dan Povey
Browse files

Adding ASRU'11 toolkit paper to repository; making dir for poster

git-svn-id: https://svn.code.sf.net/p/kaldi/code/trunk@641 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8
parent 89dfb281
This diff is collapsed.
This diff is collapsed.
PAPER=kaldi_asru
all: $(PAPER).pdf
cp $(PAPER).pdf ~/desktop/2011_asru_kaldi.pdf
ifeq ($(shell uname), Darwin)
$(PAPER).pdf: $(PAPER).tex $(PAPER).bbl
pdflatex $(PAPER)
open $(PAPER).pdf
else
$(PAPER).pdf: $(PAPER).tex $(PAPER).bbl
pdflatex $(PAPER)
endif
$(PAPER).bbl: $(PAPER).tex refs.bib
pdflatex $(PAPER)
bibtex $(PAPER)
pdflatex $(PAPER)
clean:
-rm $(PAPER).aux $(PAPER).blg $(PAPER).bbl $(PAPER).log *~
.PHONY: clean
This diff is collapsed.
@conference{rwth,
Author = {David Rybach and Christian Gollan and Georg Heigold and Bj\"{o}rn Hoffmeister and Jonas L\"{o}\"{o}f and Ralf Schl\"{u}ter and Hermann Ney},
Booktitle = {INTERSPEECH},
Pages = {2111-2114},
Title = "{The RWTH Aachen University Open Source Speech Recognition System}",
Year = {2009}}
@book{htkbook,
author = {S. Young and G. Evermann and M. Gales and T. Hain and D. Kershaw and X. Liu and G. Moore and J. Odell and D. Ollason and D. Povey and V. Valtchev and P. Woodland},
title = "The HTK Book (for version 3.4)",
publisher = {Cambridge University Engineering Department},
year = {2009}}
@conference{julius,
Author = {Akinobu Lee and Tatsuya Kawahara and Kiyohiro Shikano},
Booktitle = {EUROSPEECH},
Pages = {1691-1694},
Title = {Julius -- an Open Source Real-Time Large Vocabulary Recognition Engine},
Year = {2001}}
@conference{attila,
Author = {Hagen Soltau and George Saon and Brian Kingsbury},
Booktitle = {IEEE Workshop on Spoken Language Technology (SLT)},
Pages = {97-102},
Title = "{The IBM Attila speech recognition toolkit}",
Year = {2010}}
@techreport{sphinx,
Author = {Willie Walker and Paul Lamere and Philip Kwok and Bhiksha Raj and Rita Singh and Evandro Gouvea and Peter Wolf and Joe Woelfel},
Institution = {Sun Microsystems Inc.},
Number = {SML1 TR2004-0811},
Title = {Sphinx-4: {A} Flexible Open Source Framework for Speech Recognition},
Type = {Technical Report},
Year = {2004}}
@article{sgmm_csl,
Author = {D. Povey and L. Burget and others},
Journal = {Computer Speech \& Language},
Title = {{The subspace Gaussian mixture model---A structured model for speech recognition}},
Volume = {25},
Number = {2},
Pages = {404-439},
Month = {April},
Year = {2011}}
@conference{goel_lex,
Author = {Nagendra Goel and Samuel Thomas and others},
Booktitle = {Proc. IEEE ICASSP},
Pages = {5094-5097},
Title = {Approaches to automatic lexicon learning with limited training examples},
Year = {2010}}
@conference{asru_et,
Author = {Daniel Povey and Geoffrey Zweig and Alex Acero},
Booktitle = {IEEE ASRU},
Title = {{The Exponential Transform as a generic substitute for VTLN}},
Year = {2011}}
@INPROCEEDINGS {openfst,
author = {C. Allauzen and M. Riley and J. Schalkwyk and W. Skut and M. Mohri },
title = "{OpenFst}: a general and efficient weighted finite-state transducer library",
booktitle = "Proc. CIAA",
year = 2007
}
@Book {golub,
author = "G. H. Golub and C. F. {Van Loan}",
title = "{Matrix Computations}",
edition = 3,
publisher = "{The Johns Hopkins University Press}",
year = 1996
}
@article {blas,
author = "L. S. Blackford and J. Demmel and J. Dongarra and I. Duff and S. Hammarling and G. Henry and M. Heroux and L. Kaufman and A. Lumsdaine and A. Petitet and R. Pozo and K. Remington and R. C. Whaley",
title = {An updated set of basic linear algebra subprograms ({BLAS})},
journal = {ACM Trans. Math. Softw.},
volume = {28},
issue = {2},
month = {June},
year = {2002},
pages = {135--151},
publisher = {ACM},
}
@UNPUBLISHED{atlas,
AUTHOR = "{ATLAS homepage}",
NOTE = "{http://math-atlas.sourceforge.net/}"
}
@ARTICLE{atlas2,
AUTHOR = "R. Clint Whaley and Antoine Petitet and Jack J. Dongarra",
TITLE = "Automated Empirical Optimization of Software and the
{ATLAS} Project",
JOURNAL = "Parallel Computing",
VOLUME = "27",
NUMBER = "1--2",
PAGES = "3--35",
YEAR = 2001}
@BOOK{lapack,
AUTHOR = {Anderson, E. and Bai, Z. and Bischof, C. and
Blackford, S. and Demmel, J. and Dongarra, J. and
Du Croz, J. and Greenbaum, A. and Hammarling, S. and
McKenney, A. and Sorensen, D.},
TITLE = {{LAPACK} Users' Guide},
EDITION = {Third},
PUBLISHER = {Society for Industrial and Applied Mathematics},
YEAR = {1999}}
@UNPUBLISHED{jama,
AUTHOR = "{JAMA homepage}",
NOTE = "{http://math.nist.gov/javanumerics/jama/}"
}
@TECHREPORT{ubmdoc,
author = {D. Povey},
title = "{A Tutorial-style Introduction to Subspace Gaussian Mixture Models for Speech Recognition}",
institution = "{Microsoft Research}",
year = 2009,
number = "MSR-TR-2009-111"
}
@inproceedings{stolcke2002srilm,
title={SRILM-an extensible language modeling toolkit},
author={Stolcke, A.},
booktitle={Proceedings of the international conference on spoken language processing},
volume={2},
pages={901--904},
year={2002},
}
@conference{irstlm,
Author = {Marcello Federico and Nicola Bertoldi and Mauro Cettolo},
Booktitle = {INTERSPEECH},
Pages = {1618-1621},
Title = "{IRSTLM}: An Open Source Toolkit for Handling Large Scale Language Models",
Year = {2008}}
@conference{Ghoshal:ICASSP10,
Author = {A. Ghoshal and D. Povey and others},
Booktitle = {Proc. IEEE ICASSP},
Pages = {4310-4313},
Title = {{A Novel Estimation of Feature-space MLLR for Full-covarinace Models}},
Year = {2010}}
@article{Gales:CSL98,
Author = {M. J. F. Gales},
Journal = {Computer Speech and Language},
Month = {April},
Number = {2},
Pages = {75-98},
Title = {Maximum likelihood linear transformations for {HMM}-based speech recognition},
Volume = {12},
Year = {1998}}
@conference{Price:ICASSP88,
Author = {P. Price and W. M. Fisher and J. Bernstein and D. S. Pallett},
Booktitle = {Proc. IEEE ICASSP},
Pages = {651-654},
Title = {The DARPA 1000-word resource management database for continuous speech recognition},
Volume = {1},
Year = {1988}}
@conference{Povey:ICASSP99,
Author = {D. Povey and P. C. Woodland},
Booktitle = {Proc. IEEE ICASSP},
Pages = {333-336},
Title = {Frame discrimination training for {HMMs} for large vocabulary speech recognition},
Volume = {1},
Year = {1999}}
@article{stc,
Author = {Mark J. F. Gales},
Journal = {IEEE Trans. Speech and Audio Proc.},
Month = {May},
Number = {3},
Pages = {272-281},
Title = {Semi-Tied Covariance Matrices for Hidden {Markov} Models},
Volume = {7},
Year = {1999}}
@conference{mllt,
Author = {Ramesh Gopinath},
Booktitle = {Proc. IEEE ICASSP},
Pages = {661-664},
Title = {Maximum likelihood modeling with {Gaussian} distributions for classification},
Volume = {2},
Year = {1998}}
@article{gales_linxform,
Author = {Mark J. F. Gales},
Journal = {Computer Speech and Language},
Month = {April},
Number = {2},
Pages = {75-98},
Title = {Maximum likelihood linear transformations for {HMM}-based speech recognition},
Volume = {12},
Year = {1998}}
@techreport{regtree,
Author = {Mark J. F. Gales},
Institution = {Cambridge University Engineering Department},
Month = {August},
Number = {CUED/F-INFENG/TR.263},
Title = {The Generation and Use of Regression Class Trees for {MLLR} Adaptation},
Type = {Technical Report},
Year = {1996}}
@article{hlda,
Author = {Nagendra Kumar and Andreas G. Andreou},
Journal = {Speech Communication},
Month = {December},
Number = {4},
Pages = {283-297},
Title = {Heteroscedastic discriminant analysis and reduced rank {HMMs} for improved speech recognition},
Volume = {26},
Year = {1998}}
@Article{wfst,
author = {Mehryar Mohri and Fernando Pereira and Michael Riley},
title = "Weighted Finite-State Transducers in Speech Recognition",
journal = "Computer Speech and Language",
year = {2002},
pages = {69--88},
volume = {20},
number = {1}
}
@INPROCEEDINGS {clustering,
author = "S. J. Young and J. J. Odell and P. C. Woodland",
title = {Tree-Based State Tying for High Accuracy Acoustic Modelling},
booktitle = "{Proc. 1994 ARPA Human Language Technology Workshop}",
year = 1994,
pages = "304--312"
}
@article{Reichl:ITSAP00,
Author = {Wolfgang Reichl and Wu Chou},
Journal = {IEEE Transactions on Speech and Audio Processing},
Month = {September},
Number = {5},
Pages = {555-566},
Title = {Robust decision tree state tying for continuous speech recognition},
Volume = {8},
Year = {2000}}
@conference{Woodland:ICASSP94,
Author = {P. C. Woodland and J. J. Odell and V. Valtchev and S. J. Young},
Booktitle = {Proc. IEEE ICASSP},
Pages = {II/125-II/128},
Title = {Large vocabulary continuous speech recognition using {HTK}},
Volume = {2},
Year = {1994}}
@Book {rico_book,
author = "Henrique S. Malvar",
title = "{Signal Processing with Lapped Transforms}",
publisher = {Artech House, Inc.},
year = 1992
}
@article{mllr,
Author = {C. J. Leggetter and P. C. Woodland},
Journal = {Computer Speech and Language},
Number = {2},
Pages = {171-185},
Title = {Maximum likelihood linear regression for speaker adaptation of continuous density hidden {Markov} models},
Volume = {9},
Year = {1995}}
@conference{lvtln,
Author = {D. Y. Kim and S. Umesh and M. J. F. Gales and T. Hain and P. C. Woodland},
Booktitle = {Proc. ICSLP},
Pages = {1953-1956},
Title = {Using {VTLN} for Broadcast News Transcription},
Year = {2004}}
% Note: the original submission was rev. 530...
% Note: the original submission was rev. 530...
% submitted again at 539 before review..
% Template for SLT-2006 paper; to be used with:
% spconf.sty - ICASSP/ICIP LaTeX style file, and
% IEEEbib.bst - IEEE bibliography style file.
......@@ -87,7 +88,7 @@
\name{ \em Daniel Povey$^1$, Mirko Hannemann$^{1,2}$, \\
\em {Gilles Boulianne}$^3$, {Luk\'{a}\v{s} Burget}$^{2,4}$, {Arnab Ghoshal}$^5$, {Milo\v{s} Janda}$^2$, {Martin Karafi\'{a}t}$^2$, {Stefan Kombrink}$^2$, \\
\em {Petr Motl\'{i}\v{c}ek}$^6$, {Yanmin Qian}$^7$, {Ngoc Thang Vu}$^8$, {Korbinian Riedhammer}$^9$, {Karel Vesel\'{y}}$^2$
\em {Petr Motl\'{i}\v{c}ek}$^6$, {Yanmin Qian}$^7$, {Korbinian Riedhammer}$^9$, {Karel Vesel\'{y}}$^2$, {Ngoc Thang Vu}$^8$
\thanks{Thanks to Honza \v{C}ernock\'{y}, Renata Kohlov\'{a}, and Tom\'{a}\v{s} Ka\v{s}p\'{a}rek for their help relating to the Kaldi'11 workshop at BUT, and to Sanjeev Khudanpur for his help in preparing the paper. Researchers at BUT were partly supported by Technology Agency of the Czech Republic grant No. TA01011328, Czech Ministry of Education project No. MSM0021630528, and Grant Agency of the Czech Republic project No. 102/08/0707.}}
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment