Large-margin minimum classification error training: A theoretical risk minimization perspective

By Dong Yu, Li Deng, Xiaodong He, A. Acero. 2008

15 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): “In the implementation of DSSM learning described in [172], a subset of the negative candidates are used, following the common practice adopted in MCE (Minimum Classification Error) training in speech recognition [52, 118, 417, 418].”
Roles of Pre-Training and Fine-Tuning in Context-Dependent DBN-HMMs for Real-World Speech Recognition (2010, methodology): “These GMM-HMMs are typically first trained to maximize the likelihood of generating the observed features and then fine-tuned using discriminative training and/or large margin techniques [1][2].”
Machine Learning Paradigms for Speech Recognition: An Overview (2013, methodology): “With a slight modification of the original MCE objective function where the bias parameter in the sigmoid smoothing function is annealed over each training iteration, highly desirable discriminative margin is achieved while producing the best ASR accuracy result for a standard ASR task (TI-Digits) i”
A Novel Framework and Training Algorithm for Variable-Parameter Hidden Markov Models (2009, methodology): “Many efforts have been put during the past two decades in search for new modeling, adaptation, and training technologies (e.g., [1], [3], [5], [6], [9], [10], [13], [14], [21], [24], [25], [27]–[29]) that can deliver sufficiently high recognition accuracy under all deployment conditions.”