Scalable backoff language models

Keywords

Bigram, Trigram, Perplexity, Language model, Computer science

References

• Optimizing lexical and N-gram coverage via judicious use of linguistic dataRonald Rosenfeld — 1995
• Estimation of probabilities from sparse data for the language model component of a speech recognizerSlava M. Katz — 1987
• The CMU Statistical Language Modeling Toolkit and its use in the 1994 ARPA CSR EvaluationRoni Rosenfeld — 1995
• Scalable Trigram Backoff Language ModelsKristie Seymore, Ronald Rosenfeld — 1996
• Optimizing Lexical and Ngram Coverage via Judicious Use of Linguistic DataRoni Rosenfeld — 2018
• Self-organized language modeling for speech recognitionF. Jelinek — 1990
• -organized Language Modeling for Speech Recognition". In

Cited by

• Language models for automatic speech recognition : construction and complexity controlVesa Siivola — 2007
• On Cross-lingual Plagiarism Analysis using a Statistical ModelAlberto Barrón‐Cedeño, Paolo Rosso, David Pinto — 2008
• Language model size reduction by pruning and clusteringJoshua Goodman, Jianfeng Gao — 2000
• Multimodal intent recognition for natural human-robotic interactionJames Rossiter — 2011
• Study on interaction between entropy pruning and kneser-ney smoothingCiprian Chelba, Thorsten Brants, Will Neveitt — 2010
• The Juicer LVCSR Decoder - User Manual for Juicer version 0.5.0Darren Moore — 2006
• The Use of Clustering Techniques for Language Modeling V Application to Asian LanguageJianfeng Gao, Joshua Goodman, Jiangbo Miao — 2001
• Compressing Trigram Language Models With Golomb CodingKenneth Church, Ted Hart, Jianfeng Gao — 2007
• The AT&t large vocabulary conversational speech recognition systemAndrej Ljolje, Michael Riley, Donald Hindle — 1999
• Morfessor and variKN machine learning tools for speech and language technologyVesa Siivola, Mathias Creutz, Mikko Kurimo — 2007
• Spoken Content-Based Audio Navigation (SCAN)John Choi, Donald Hindle, Julia Hirschberg — 2007
• A comparison of two LVR search optimization techniquesStephan Kanthak, Hermann Ney, Michael Riley — 2002
• WFST compression for automatic speech recognitionDiamantino Caseiro — 2010
• Fast vocabulary-independent audio search using path-based graph indexingOlivier Siohan, Michiel Bacchiani — 2005
• Corpus Variation and Parser PerformanceDaniel Gildea — 2001
• Detecting Fake Content with Relative Entropy ScoringThomas Lavergne, Tanguy Urvoy, François Yvon — 2008
• Improving Translation Selection with a New Translation Model Trained by Independent Monolingual CorporaMing Zhou, Yuan Chun Ding, Changning Huang — 2001
• Improving Relative-Entropy Pruning using Statistical SignificanceLing Wang, Nadi Tomeh, Guang Xiang — 2012
• Statistical language understanding using frame semanticsDaniel Gildea — 2001
• A method to build a super small but practically accurate language model for handheld devicesGenQing Wu, Fang Zheng — 2003

Related papers

• Improving language models by using distant informationArmelle Brun, David Langlois, Kamel Smaı̈li — 2007
• Class phrase models for language modelingK. Ries, Finn Dag Buø, Alex Waibel — 1996
• Factored Language Models and Generalized Parallel BackoffJeff Bilmes, Katrin Kirchhoff — 2003
• Evaluation of a language model using a clustered model backoffJohn W. V. Miller, F. Alleva — 1996
• Decoupling Word-Pair Distance and Co-occurrence Information for Effective Long History Context Language ModelingTze Yuang Chong, Rafael E. Banchs, Eng Siong Chng — 2015
• Speech Recognition Using a Stochastic Language Model Integrating Local and Global ConstraintsRyosuke Isotani, Shoichi Matsunaga — 1994
• Cleaning statistical language modelsReda Jourani, David Langlois, Kamel Smaı̈li — 2010