Online learning of large margin hidden Markov models for automatic speech recognition

Keywords

Margin (machine learning), Discriminative model, Hidden Markov model, Computer science, Speech recognition

References

• Support vector machines for multi-class pattern recognitionJason Weston, Chris Watkins — 1999
• Penalty function maximization for large margin HMM trainingGeorge Saon, Daniel Povey — 2008
• Maximum conditional mutual information projection for speech recognitionMohamed Kamal Omar, Mark Hasegawa‐Johnson — 2003
• A fast online algorithm for large margin training of continuous density hidden Markov modelsChih‐Chieh Cheng, Fei Sha, Lawrence K. Saul — 2009
• Stochastic gradient adaptation of front-end parametersSreeram Balakrishnan, Karthik Visweswariah, Vaibhava Goe — 2004
• Adaptation of front end parameters in a speech recognizerKarthik Visweswariah, Ramesh A. Gopinath — 2004
• Dimensionality reduction for speech recognition using neighborhood components analysisNatasha Singh-Miller, Michael Collins, Timothy J. Hazen — 2007
• Automatic Speech Recognition - A Brief History of the Technology DevelopmentLawrence R. Rabiner — 2004
• Online Learning of Approximate Dependency Parsing AlgorithmsRyan McDonald, Fernando C. N. Pereira — 2006
• Discriminative adaptation for log-linear acoustic modelsJonas Lööf, Ralf Schlüter, Hermann Ney — 2010
• Optimization methods for discriminative trainingJonathan Le Roux, Erik McDermott — 2005
• Estimation of Dependences Based on Empirical DataVladimir Vapnik — 2006
• Extracting Support Data for a Given TaskBernhard Schölkopf, Chris Burges, Vladimir Vapnik — 1995
• MLLR transforms as features in speaker recognitionAndreas Stolcke, Luciana Ferrer, Sachin Kajarekar — 2005
• Neural networks for pattern recognitionBishop, Christopher M. 1959- — 1995
• Discriminative kernel-based phoneme sequence recognitionJoseph Keshet, Shai Shalev‐Shwartz, Samy Bengio — 2006
• Fundamentals of speech recognitionLawrence R. Rabiner, Biing‐Hwang Juang — 1993
• The Sound Pattern of EnglishNoam Chomsky, Morris Halle — 1968
• On the Learnability and Design of Output Codes for Multiclass ProblemsKoby Crammer, Yoram Singer — 2002
• Discriminant Analysis by Gaussian MixturesTrevor Hastie, Robert Tibshirani — 1996

Cited by

• A Review of Multimodal InteractionRongjian Liang, Bin Liang, Xueqian Wang — 2016
• Chinese Handwriting Recognition: An Algorithmic PerspectiveTonghua Su — 2013
• Ferramentas e Recursos Livres para ReconhecimentoN. Cruz, S. Neto — 2011

Related papers

• SVMs for Automatic Speech Recognition: A SurveyRubén Solera-Ureña, Jaume Padrell-Sendra, D. Martín-Iglesias — 2005
• Energy-Based Models in Document Recognition and Computer VisionYann LeCun, Sumit Chopra, M. Ranzato — 2007
• Hope and Fear for Discriminative Training of Statistical Translation ModelsDavid Chiang — 2012
• Automatic Speaker Recognition with Limited DataRuirui Li, Jyun‐Yu Jiang, Jiahao Liu — 2020
• Scalable inference in max-margin topic modelsJun Zhu, Xun Zheng, Zhou Li — 2013
• Advanced state clustering for very large vocabulary HMM-based on-line handwriting recognitionA. Kosmala, Daniel Willett, Gerhard Rigoll — 1999
• Training Continuous Space Language Models: Some Practical IssuesHai Son Le, Alexandre Allauzen, Guillaume Wisniewski — 2010
• On updates that constrain the features' connections during learningOmid Madani, Jian Huang — 2008
• Joint Feature Selection in Distributed Stochastic Learning for Large-Scale Discriminative Training in SMTPatrick Simianer, Stefan Riezler, Chris Dyer — 2012