Minimum classification error rate methods for speech recognition

By Biing-Hwang Fred Juang, Wu Hou, Chin-Hui Lee. 1997

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks (2017, background): “, [11, 8]), the attention-driven image-text matching score between the entire image (Q) and the whole text description (D) is defined as”
Stacked Cross Attention for Image-Text Matching (2018, methodology): “Inspired by the minimum classification error formulation in speech recognition [18, 15], the similarity between image I and sentence T is calculated by LogSumExp pooling (LSE), i.”
Deep Learning: Methods and Applications (2014, background): “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].”
A tutorial survey of architectures, algorithms, and applications for deep learning (2014, background): “Many of the discriminative techniques in signal and information processing apply to shallow architectures such as HMMs (e.g., [87–94]) or CRFs (e.g., [95–100]).”
Minimum Phone Error and I-smoothing for improved discriminative training (2002, background): “Over the years, several discriminative training criteria, including Maximum Mutual Information Estimation (MMIE) [1] [5] and Minimum Classification Error (MCE) [4] [6], have been successfully applied to small vocabulary speech recognition tasks.”
Optimization Algorithms and Applications for Speech and Language Processing (2013, background): “However, the recognition task often involves unknown languages—the so-called “open-set” scenario.”
Spoken Language Recognition: From Fundamentals to Practice (2013, background): “Furthermore, it remains a challenge to reliably extract prosodic features [100], [101].”
Parameter Estimation of Statistical Models Using Convex Optimization (2010, background): “The natural parameters of the product distribution can be easily constructed by concatenating natural parameters of all member distributions.”
Spoken Content Retrieval—Beyond Cascading Speech Recognition with Text Retrieval (2015, methodology): “[117] Q. Fu and B.-H. Juang, Automatic speech recognition based on weighted minimum classi.cation error (W-MCE) training method, in Proc.”
Bayesian reasoning and machine learning (2012, unknown): “In discriminative training, see for example [150], one defines a new single discriminative model, formed from the C HMMs using p(c|v1:T ) = p(v1:T |c)p(c) ∑C c′=1 p(v1:T |c′)p(c′) (23.”
Machine Learning Paradigms for Speech Recognition: An Overview (2013, methodology): “One functional form that fits this intuition is introduced in the minimum classification error (MCE) training [79], [80] commonly used in ASR: (30) where is a smooth function, which is non-convex and which maps the " margin " to a 0–1 continuum.”
Large-margin minimum classification error training: A theoretical risk minimization perspective (2008, methodology): “Discriminative training for hidden Markov models (HMMs) has become one of the core technologies in speech recognition research over the past dozen years or so ( Juang et al., 1997; Juang and Katagiri, 1992; McDermott, 1997; McDermott et al., 2007; Povey et al., 2004; Woodland and Povey, 2000).”
Semi-supervised maximum mutual information training of deep neural network acoustic models (2015, methodology): “A number of discriminative criteria such as MMI [1], MCE[2], MPE [3], sMBR [4, 5] and bMMI [6] have been developed and used in HMM-based speech recognition [7, 8, 9, 10].”
Discriminative learning in sequential pattern recognition (2008, methodology): “One popular definition takes the following form [29]: G S r (X r ; ) = log 1 N N i =1 p η (X r , s r,i”
Phone-discriminating minimum classification error (p-MCE) training for phonetic recognition (2007, methodology): “) is the misclassification measure, both are defined in the same way as in the conventional MCE training [1].”
Online and offline handwritten Chinese character recognition: Benchmarking on new databases (2013, methodology): “The LOGM is a modification of the minimum classification error (MCE) criterion [26] for improving the training convergence and generalization performance.”
Automatic Speech Recognition - A Brief History of the Technology Development (2004, methodology): “10/08/2004 09:56:44 AM 16 required estimation of distributions for the data, was transformed into an optimization problem involving minimization of the empirical recognition error [44].”
Context-dependent deep neural networks for commercial Mandarin speech recognition applications (2013, methodology): “Expectation-maximization (EM) algorithm is usually used for HMM training, while further recognition accuracy improvement can be achieved using discriminative training algorithms [1-3] such as MMI, MCE and MPE, etc.”
A Tutorial on Energy-Based Learning (2006, background): “in the context of discriminative training for speech recognition systems [37].”