%%http://research.microsoft.com/apps/pubs/?id=139955 @INPROCEEDINGS { efficient_general, author = {A. Ljolje and F. Pereira and M. Riley}, title = "{Efficient General Lattice Generation and Rescoring}", booktitle = "{Proc. Eurospeech}", year = 1999 } @Article { ney_word_graph, author = {S. Ortmanns and H. Ney}, title = "{A Word Graph Algorithm for Large Vocabulary Continuous Speech Recognition}", journal = "{Computer Speech and Language}", volume = 11, pages = {43--72}, year = 1997 } @phdthesis{ odell_thesis, title={The use of context in large vocabulary speech recognition}, author={Odell, J.J.}, year={1995}, school={Cambridge University Engineering Dept.} } @inproceedings{sak2010fly, title={On-the-Fly Lattice Rescoring for Real-Time Automatic Speech Recognition}, author={Sak, H. and Sara{\c{c}}lar, M. and G{\"u}ng{\"o}r, T.}, booktitle={Proc. Interspeech}, year={2010} } @inproceedings{saon2005anatomy, title={{Anatomy of an extremely fast LVCSR decoder}}, author={Saon, G. and Povey, D. and Zweig, G.}, booktitle={Proc. Interspeech}, year={2005} } @Article{ ubmpaper, author = {D. Povey and Luk\'{a}\v{s} Burget and others}, title = "{The Subspace Gaussian Mixture Model -- a Structured Model for Speech Recognition}", journal = "{Computer Speech and Language}", volume = 25, number = 2, pages = {404--439}, year = 2011 } @INPROCEEDINGS{ ubmconf, author = {D. Povey and Luk\'{a}\v{s} Burget and others}, title = "{Subspace Gaussian Mixture Models for Speech Recognition}", booktitle = "{ICASSP}", year = 2010 } @TECHREPORT{ symmetric_tr, author = "{D. Povey}", title = "{The Symmetric Subspace Gaussian Mixture Model}", institution = "{Microsoft Research}", year = 2010, number = "MSR-TR-2010-138" } @TECHREPORT{ ubmdoc, author = "{D. Povey}", title = "{Subspace Gaussian Mixture Models for Speech Recognition}", institution = "{Microsoft Research}", year = 2009, number = "MSR-TR-2009-64" } @INPROCEEDINGS{ poveyfullcov, author = { D. Povey and G.Saon }, title = "{Feature and model space speaker adaptation with full covariance Gaussians}", booktitle = "Interspeech/ICSLP", year = 2006 } @INPROCEEDINGS{ poveyboostmmi, author = "{ D. Povey and D. Kanevsky and B. Kingsbury and B. Ramabhadran and G. Saon and K. Visweswariah}", title = "{Boosted MMI for Feature and Model Space Discriminative Training}", booktitle = "ICASSP", year = 2008 } @INPROCEEDINGS{ karthikbasesml, author = {K. Visweswariah and V. Goel and R. Gopinath}, title = "{Maximum Likelihood Training Of Bases For Rapid Adaptation}", booktitle = "ICSLP", year = 2002 } @TECHREPORT{ ubmtutorial, author = {D. Povey}, title = "{A Tutorial Introduction to Subspace Gaussian Mixture Models for Speech Recognition}", institution = "{Microsoft Research}", year = 2009, number = "MSR-TR-2009-111" } @Article{ nagendrapaper, author = {N. Goel and others}, title = "{Approaches to automatic lexicon learning with limited training examples}", note = "Submitted to: ICASSP", year = 2010 } @Article{ icassp10_ubm, author = {D. Povey and L. Burget and others}, title = "{Subspace Gaussian Mixture Models for Speech Recognition}", note = "Submitted to: ICASSP", year = 2010 } @Article{ multilingual, author = {Lukas Burget and Petr Schwartz and others}, title = "{Multilingual Acoustic Modeling for Speech Recognition based on Subspace Gaussian Mixture Models}", note = "Submitted to: ICASSP", year = 2010 } @Article{ adaptation, author = {Arnab Ghoshal and D. Povey and others}, title = "{A Novel Estimation of Feature-space MLLR for Full Covariance Models}", note = "Submitted to: ICASSP", year = 2010 } @MISC{ ubmchap, title = "{Approaches to Speech Recognition based on Speaker Recognition Techniques}", author = "D. Povey and S. M. Chu and J. Pelecanos", howpublished = "Book chapter in forthcoming book on GALE project", year = 2009 } @INPROCEEDINGS{ karthikbases, author = {K. Visweswariah and V. Goel and R. Gopinath}, title = "{Structuring Linear Transforms for Adaptation Using Training Time Information}", booktitle = "ICASSP", year = 2002 } @INPROCEEDINGS { nagendratransforms, author = {N. K. Goel and P.Gopinath}, title = "{Multiple Linear Transforms}", booktitle = "ICASSP", year = 2001 } @INPROCEEDINGS{ nap, title={Advances In Channel Compensation For SVM Speaker Recognition}, author={ A. Solomonoff and W. M. Campbell and I. Boardman}, booktitle={ICASSP}, year={2005}, volume={1}, pages={629--632} } @INPROCEEDINGS { gsvsvm, title = "{A Covariance Kernel for SVM Language Recognition}", author = "{W. M. Campbell}", booktitle = {ICASSP}, year = 2008, pages = "4141--4144" } %% Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on In Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on (2008), pp. 4141-4144. @Article{ ubmmap, author = "{ A. D. Reynolds and T. F. Quatieri and R. Dunn}", title = "{Speaker verification using adapted Gaussian mixture models}", journal = "Digital Signal Processing", volume = "10", number = "1-3", pages = "19--41", year = 2000 } @INPROCEEDINGS { sim05, author = {K. C. Sim and M. J. F. Gales}, title = "{Adaptation of Precision Matrix Models on Large Vocabulary Continuous Speech Recognition}", booktitle = "ICASSP", year = 2005 } %SP-L5.1: ADAPTATION OF PRECISION MATRIX MODELS ON LARGE VOCABULARY ..................................... I - 97 %CONTINUOUS SPEECH RECOGNITION %Khe Chai Sim, Mark J. F. Gales, @Book { golub, author = "Golub and {van Loan}", title = "{Matrix computations}", edition = 3, publisher = "{Johns Hopkins University Press}", year = 1983 } @INPROCEEDINGS{ cat, author = {M. J. F. Gales}, title = "{Multiple-cluster adaptive training schemes}", booktitle = "ICASSP", year = 2001 } @INPROCEEDINGS{ sat, author = {T. Anastasakos and J. McDonough and R. Schwartz and J. Makhoul}, title = "{A Compact Model for Speaker-Adaptive Training}", booktitle = "{ICSLP}", year = 1996 } @Article{ eigenvoices, author = "R. Kuhn and J.-C. Junqua and P. Nguyen and N. Niedzielski", title = "{Rapid Speaker Adaptation in Eigenvoice Space}", journal = "IEEE Transactions on Speech and Audio Processing", volume = 8, number = 6, year = 2000, month = "Nov." } @INPROCEEDINGS { clustering, author = "S. 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" } @Book { lanczosbook, author = "Cullom and Willoughby", title = "{Lanczos Algorithms for Large Symmetric Eigenvalue Computations}", volume = 1 } @Article { alok, author = { A. Sharma and K. K. Paliwal }, title = "{Fast principal component analysis using fixed-point algorithm}", journal = "Pattern Recognition Letters", volume = 28, pages = "1151--1155", year = 2007 } @INPROCEEDINGS{ poveyubm08, author = { D. Povey and S. M. Chu and Balakrishnan Varadarajan }, title = "{Universal Background Model Based Speech Recognition}", booktitle = "ICASSP", year = 2008 } @Article{ ubmfactor, author = "P. Kenny and P. Ouellet and N. Dehak and V. Gupta", title = "{A study of Interspeaker Variability in Speaker Verification}", journal = "IEEE Trans. on Audio, Speech and Language Processing", volume = "16", number = "5", pages = "980--987", year = 2008 } @INPROCEEDINGS{mpe, author = {D. Povey. and P. C. Woodland}, title = "{Minimum Phone Error and I-smoothing for Improved Discriminative Training}", booktitle = "ICASSP", year = 2002 } @PHDTHESIS{thesis, author = {D. Povey}, title = "{Discriminative Training for Large Voculabulary Speech Recognition}", school = "Cambridge University", year = 2004, } @INPROCEEDINGS{ fmpe05, author = { D. Povey and B. Kingsbury and L. Mangu and G. Saon and H. Soltau and G. Zweig }, title = "{fMPE: Discriminatively trained features for speech recognition}", booktitle = "ICASSP", year = 2005 } @INPROCEEDINGS{ fmpeinter05, author = { D. Povey }, title = "{Improvements to fMPE for discriminative training of features}", booktitle = "Interspeech", year = 2005 } @INPROCEEDINGS{ qfmllr08, author = { D. Povey and Balakrishnan Varadarajan }, title = "{Quick FMLLR for Speaker Adaptation in Speech Recognition}", booktitle = "ICASSP", year = 2008 } @INPROCEEDINGS{ jasonmap, author = {J. Pelecanos and R. Vogt and S. Sridharan}, title = "{A Study on Standard and Iterative MAP Adaptation for Speaker Recognition}", booktitle = "{Proc. 9th Australian International Conference on Speech Science and Technology}", year = 2002 }% , 3 - 5 December 2002, Melbourne, Victoria. @Article { spam, author = { S. Axelrod and V. Goel and R. A. Gopinath and P. A. Olsen and K. Visweswariah}, title = "{Subspace constrained Gaussian mixture models for speech recognition}", journal = "IEEE Transactions on Speech and Audio Processing", year = 2005, volume = 13, number = 6, pages = "1144--1160" } @INPROCEEDINGS{ ears05, author = { H. Soltau and B. Kingsbury and L. Mangu and D. Povey and G. Saon and G. Zweig }, title = "{The IBM 2004 Conversational Telephony System for Rich Transcription in EARS}", booktitle = "ICASSP", year = 2005 } @misc{ hagen07, author = { H. Soltau and G. Saon and D. Povey and L. Mangu and B. Kingsbury and M. Omar and G. Zweig}, title = "{The IBM 2006 GALE Arabic System}", howpublished = {submitted to: {\em ICASSP}, 2007} } @Article{ lintran, author = "M.J.F Gales", title = "{Maximum Likelihood Linear Transformations for HMM-based Speech Recognition}", journal = "Computer Speech and Language", year = {1997}, volume = {12}, pages = {75--98} } @inproceedings{NIST:2007, AUTHOR = "T. Hain and L. Burget and J. Dines and G. Garau and M. Karafiat and M. Lincoln and J. Vepa and V. Wan", TITLE = "The {AMI(DA)} System for Meeting Transcription", booktitle = "Proc. Rich Transcription 2007 Spring Meeting Recognition Evaluation Workshop", YEAR = "2007", month = "May", address = {Baltimore, USA}, } %% M. J. F. Gales and T. Hain and D. Kershaw and X. Liu and G. Moore and J. J. Odell and D. Ollason and D. Povey and V. Valtchev and P. Woodland}, @book{ htkbook, author = {S. Young and G. Evermann and others}, title = "The HTK Book (for version 3.4)", publisher = {Cambridge University Engineering Department}, year = {2009} } @INPROCEEDINGS { srilm, author = {A. Stolcke}, title = "{SRILM - An Extensible Language Modeling Toolkit}", booktitle = "ICSLP", year = 2002 } @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 } @inproceedings{roark2011lexicographic, title={Lexicographic semirings for exact automata encoding of sequence models}, author={Roark, B. and Sproat, R. and Shafran, I.}, booktitle={Proc. ACL-HLT, 2011, Portland, OR}, pages={1--5}, year={2011} } @inproceedings{shafran2011efficient, title={Efficient Determinization of Tagged Word Lattices using Categorial and Lexicographic Semirings}, author={I. Shafran and R. Sproat and M. Yarmohammadi and Brian Roark}, booktitle={Proc. ASRU, 2011, Hawai'i}, year={2011} } @Article{ wfst, author = {M. Mohri and F. Pereira and M. Riley}, title = "Weighted Finite-State Transducers in Speech Recognition", journal = "Computer Speech and Language", year = {2002}, pages = {69--88}, volume = {20}, number = {1} } %Weighted finite-state transducers in speech recognition %Authors: Mohri M.1; Pereira F.2; Riley M.1 %Source: Computer Speech & Language, Volume 16, Number 1, January 2002 , pp. 69-88(20) %% Sam says: %Most VTLN papers have a line that says - %The warping factor is computed per speaker and is estimated by a %maximum-likelihood (ML) approach [1]. %and the reference of that is - @inproceedings{ kaldi_paper, author = {D. Povey and A. Ghoshal and others}, title = "{The Kaldi Speech Recognition Toolkit}", year = {2011}, booktitle = {Proc. ASRU} } @INPROCEEDINGS { vtln, author = { L. Lee and R. C. Rose }, title = "Speaker normalization using efficient frequency warping procedures", booktitle = "ICASSP", pages = "353--356", year = 1996 } @Book { callhome, author = "A. Canavan and D. Graff and G. Zipperlen", title = "CALLHOME American English Speech", publisher = "Linguistic Data Consortium", year =1997 } @Book { gigaword, author = "D. Graff", title = "English Gigaword", publisher = "Linguistic Data Consortium", year = 2003 } @Book { pronlex, author = "Paul Kingsbury and others", title = "CALLHOME American English Lexicon (PRONLEX)", publisher = "Linguistic Data Consortium", year = 1997 } @Article { plp, author = {H. Hermansky}, title = "Perceptual linear predictive (PLP) analysis of speech", journal = "Journal of the Acoustical Society of America", volume = "87", pages = "1738--1752", year = 1990 } @INPROCEEDINGS { switchboard, author = "J.~J Godfrey and others", title = "Switchboard: Telephone speech corpus for research and development", booktitle = "ICASSP", year = 1992 }