Large-Margin Minimum Classification Error Training for Large-Scale Speech Recognition Tasks

63 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Learning: Methods and Applications (2014, methodology): “Many of the discriminative techniques for supervised learning in signal and information processing are shallow architectures such as HMMs [52, 127, 147, 186, 188, 290, 394, 418] and conditional random fields (CRFs) [151, 155, 281, 400, 429, 446].”
Large-margin minimum classification error training: A theoretical risk minimization perspective (2008, background): “recognition” at Interspeech 2006, Lisbon, Portugal (Yu et al., 2006) and ‘‘Large-margin minimum classification error training for largescale speech recognition tasks” at ICASSP 2007, HI, USA ( Yu et al., 2007 ).”
Parameter Estimation of Statistical Models Using Convex Optimization (2010, background): “Many discriminative criteria have been proposed for ASR, such as maximum mutual information estimation (MMIE) [2], [35], minimum classification error (MCE) [18], minimum phone (word) error (MPE/MWE) [29], and large margin estimation (LME) [13], [20], [31], [40].”
Large vocabulary continuous speech recognition with context-dependent DBN-HMMS (2011, unknown): “Index Terms— Speech recognition, deep belief network, context-dependent phone, LVCSR, DBN-HMM”