Modified MMI/MPE: a direct evaluation of the margin in speech recognition

No abstract is available for this paper.

• Publication year

  2008

• Venue

  International Conference on Machine Learning

• Publication date

  2008-07-05

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/1390156.1390205
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Discriminative learning in sequential pattern recognition

  2008cited by this paper
• Boosted MMI for model and feature-space discriminative training

  2008cited by this paper
• On the equivalence of Gaussian HMM and Gaussian HMM-like hidden conditional random fields

  2007cited by this paper
• A fast optimization method for large margin estimation of HMMs based on second order cone programming

  2007cited by this paper
• A study on soft margin estimation for LVCSR

  2007cited by this paper
• The RWTH 2007 TC-STAR evaluation system for european English and Spanish

  2007cited by this paper
• Large-Margin Minimum Classification Error Training for Large-Scale Speech Recognition Tasks

  2007cited by this paper
• Comparison of Large Margin Training to Other Discriminative Methods for Phonetic Recognition by Hidden Markov Models

  2007cited by this paper
• Max-Margin Markov Networks

  2003influential reference
• Hidden Markov Support Vector Machines

  2003influential reference
• Modified Logistic Regression: An Approximation to SVM and Its Applications in Large-Scale Text Categorization

  2003cited by this paper
• Minimum Phone Error and I-smoothing for improved discriminative training

  2002cited by this paper
• Discriminative, generative and imitative learning

  2002influential reference
• The Nature of Statistical Learning Theory

  2000influential reference

• Max-Margin Transducer Loss: Improving Sequence-Discriminative Training Using a Large-Margin Learning Strategy

  2024cites this paper
• Semi-supervised training for automatic speech recognition

  2019cites this paper
• Joint training methods for tandem and hybrid speech recognition systems using deep neural networks

  2017cites this paper
• Explorer End-to-end neural segmental models for speech recognition

  2017cites this paper
• Sequence Prediction with Neural Segmental Models

  2017cites this paper
• Optimizing Expected Word Error Rate via Sampling for Speech Recognition

  2017cites this paper
• End-to-End Neural Segmental Models for Speech Recognition

  2017cites this paper
• Optimization of discriminative models for speech and handwriting recognition

  2017cites this paper
• Differenced maximum mutual information criterion for robust unsupervised acoustic model adaptation

  2016cites this paper
• Maximum margin hidden Markov models for sequence classification

  2016cites this paper
• Large-Margin Structured Prediction Extensions of Neural Networks for Automatic Speech Recognition

  2015cites this paper
• Hybrid DNN-Latent structured SVM acoustic models for continuous speech recognition

  2015cites this paper
• Neural network based feature extraction for speech and image recognition

  2014cites this paper
• Bernoulli HMMs for Handwritten Text Recognition

  2014cites this paper
• A comparison of training approaches for discriminative segmental models

  2014cites this paper
• Minimum-risk training for semi-Markov conditional random fields with application to handwritten Chinese/Japanese text recognition

  2014cites this paper
• Efficient decoding with generative score-spaces using the expectation semiring

  2013cites this paper
• Handwritten Chinese/Japanese Text Recognition Using Semi-Markov Conditional Random Fields

  2013cites this paper
• Sequence-discriminative training of deep neural networks

  2013cites this paper
• Investigations on an EM-Style Optimization Algorithm for Discriminative Training of HMMs

  2013cites this paper
• Unsupervised discriminative adaptation using differenced maximum mutual information based linear regression

  2013influential citation
• Guide to OCR for Arabic Scripts

  2012influential citation
• ( Modeling, criteria, optimization, implementation, and performance )

  2012cites this paper
• RWTH OCR: A Large Vocabulary Optical Character Recognition System for Arabic Scripts

  2012cites this paper
• New Paradigms for Active Learning

  2012cites this paper
• Structured discriminative models for speech recognition

  2012cites this paper
• Generative Kernels and Score-Spaces for Classi cation of Speech : Progress Report iii

  2012cites this paper
• Loss-Scaled Large-Margin Gaussian Mixture Models for Speech Emotion Classification

  2012cites this paper
• Posterior-Scaled MPE: Novel Discriminative Training Criteria

  2012cites this paper
• Structural Classification Methods Based on Weighted Finite-State Transducers for Automatic Speech Recognition

  2012cites this paper
• Discriminative Training for Automatic Speech Recognition: Modeling, Criteria, Optimization, Implementation, and Performance

  2012cites this paper
• WFST Enabled Solutions to ASR Problems: Beyond HMM Decoding

  2012influential citation
• Hidden Conditional Neural Fields for Continuous Phoneme Speech Recognition

  2012cites this paper
• 音声ドキュメントの音声認識,整形,要約に関する研究

  2012cites this paper
• Maximum Margin Bayesian Network Classifiers

  2012cites this paper
• Probabilistic sequence models for image sequence processing and recognition

  2012cites this paper
• Confidence- and margin-based MMI/MPE discriminative training for off-line handwriting recognition

  2011influential citation
• Maximum margin structure learning of Bayesian network classifiers

  2011cites this paper
• Large-Margin Estimation of Hidden Markov Models With Second-Order Cone Programming for Speech Recognition

  2011cites this paper
• RWTH OCR : A Large Vocabulary Optical 1 Character Recognition System for Arabic

  2011influential citation
• Handbook of Natural Language Processing and Machine Translation: DARPA Global Autonomous Language Exploitation

  2011cites this paper
• Bayes risk decoding and its application to system combination

  2011cites this paper
• Hidden Boosted MMI and Hierarchical State Posterior Feature for Automatic Speech Recognition Based on Hidden Conditional Neural Fields

  2011cites this paper
• Machine Translation from Speech

  2011cites this paper
• Subspace pursuit method for kernel-log-linear models

  2011cites this paper
• Discriminative training and acoustic modeling for automatic speech recognition

  2010cites this paper
• A discriminative splitting criterion for phonetic decision trees

  2010cites this paper
• Efficient Heuristics for Discriminative Structure Learning of Bayesian Network Classifiers

  2010cites this paper
• Margin-Based Discriminative Training for String Recognition

  2010cites this paper
• Discriminative training based on an integrated view of MPE and MMI in margin and error space

  2010influential citation
• Discriminative HMMS, log-linear models, and CRFS: What is the difference?

  2010cites this paper
• Large Margin Learning of Bayesian Classifiers Based on Gaussian Mixture Models

  2010cites this paper
• A log-linear discriminative modeling framework for speech recognition

  2010cites this paper
• ICFHR 2010 - Arabic Handwriting Recognition Competition

  2010cites this paper
• 整合邊際資訊於鑑別式聲學模型訓練方法之比較研究 (A Comparative Study on Margin-Based Discriminative Training of Acoustic Models) [In Chinese]

  2010cites this paper
• A unified view for discriminative objective functions based on negative exponential of difference measure between strings

  2009cites this paper
• Acoustic modelling for speech recognition: Hidden Markov models and beyond?

  2009cites this paper
• Improved Modeling in Handwriting Recognition

  2009cites this paper
• Generalization problem in ASR acoustic model training and adaptation

  2009cites this paper
• Speech emotion recognition via a max-margin framework incorporating a loss function based on the Watson and Tellegen's emotion model

  2009cites this paper
• Margin-space integration of MPE loss via differencing of MMI functionals for generalized error-weighted discriminative training

  2009influential citation
• Modified MPE/MMI in a transducer-based framework

  2009cites this paper
• Investigations on features for log-linear acoustic models in continuous speech recognition

  2009cites this paper
• Adapting the RWTH-OCR Handwriting Recognition System to French Handwriting

  2009cites this paper
• ICDAR 2009 Arabic Handwriting Recognition Competition

  2009cites this paper
• Adapting the RWTH-OCR Handwriting Recognition System to French Handwriting

  2009cites this paper
• A Comparison of Graph Construction and Learning Algorithms for Graph-based Phonetic Classification a Comparison of Graph Construction and Learning Algorithms for Graph-based Phonetic Classification

  year unknowncites this paper