Improved discriminative training techniques for large vocabulary continuous speech recognition

No abstract is available for this paper.

• Publication year

  2001

• Venue

  2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)

• Publication date

  2001-05-07

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ICASSP.2001.940763
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Large scale discriminative training for speech recognition

  2000cited by this paper
• Frame discrimination training for HMMs for large vocabulary speech recognition

  1999cited by this paper
• Discriminative Training of Hidden Markov Models

  1998cited by this paper
• MMIE training of large vocabulary recognition systems

  1997cited by this paper
• Hidden Markov models, maximum mutual information estimation, and the speech recognition problem

  1992influential reference
• An inequality for rational functions with applications to some statistical estimation problems

  1991cited by this paper
• Decoder selection based on cross-entropies

  1988cited by this paper
• Maximum mutual information estimation of hidden Markov model parameters for speech recognition

  1986cited by this paper

• End-to-End Speech Recognition: A Survey

  2023cites this paper
• O-1: Self-training with Oracle and 1-best Hypothesis

  2023cites this paper
• Developing sequentially trained robust Punjabi speech recognition system under matched and mismatched conditions

  2022cites this paper
• Prosodic Feature-Based Discriminatively Trained Low Resource Speech Recognition System

  2022influential citation
• Enhancing accuracy of long contextual dependencies for Punjabi speech recognition system using deep LSTM

  2021cites this paper
• Calibrating DNN Posterior Probability Estimates of HMM/DNN Models to Improve Social Signal Detection from Audio Data

  2019cites this paper
• Sequence Student-Teacher Training of Deep Neural Networks

  2016cites this paper
• Handwritten Text Recognition for Bengali

  2016cites this paper
• Training HMMs in GMTK

  2015cites this paper
• The 2011 KIT QUAERO Speech-to-Text System for Russian

  2015cites this paper
• Anti-Models: - An Alternative Way to Discriminative Training

  2014cites this paper
• DISTINCT ACOUSTIC MODELING FOR AUTOMATIC SPEECH RECOGNITION

  2014cites this paper
• An Alternative Way to Discriminative Training

  2014cites this paper
• Homogenous ensemble phonotactic language recognition based on SVM supervector reconstruction

  2014cites this paper
• Porting concepts from DNNs back to GMMs

  2013cites this paper
• Generalized discriminative training for speech recognition

  2012cites this paper
• Noisy Constrained Maximum-Likelihood Linear Regression for Noise-Robust Speech Recognition

  2011cites this paper
• The 2011 KIT QUAERO speech-to-text system for Spanish

  2011cites this paper
• The 2011 KIT English ASR system for the IWSLT evaluation

  2011cites this paper
• Quaero 2010 Speech-to-Text Evaluation Systems

  2011cites this paper
• Speaker-Clustered Acoustic Models Evaluated on GPU for On-line Subtitling of Parliament Meetings

  2011cites this paper
• Quaero Speech-to-Text and Text Translation Evaluation Systems

  2010cites this paper
• Training of Speaker-Clustered Acoustic Models for Use in Real-Time Recognizers

  2009cites this paper
• Discriminative Training of Gender-Dependent Acoustic Models

  2009cites this paper
• Computers in the Human Interaction Loop

  2009cites this paper
• Discriminative training of n-gram language models for speech recognition via linear programming

  2009cites this paper
• Discriminative adaptive training with VTS and JUD

  2009cites this paper
• Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling

  2009cites this paper
• Robust Automatic Transcription of Lectures

  2009cites this paper
• Training of Speaker-clustered Acoustic Models for use in Real-time Recognizers

  2009cites this paper
• Boosted MMI for model and feature-space discriminative training

  2008cites this paper
• A New Method for MLE Training Based on Multi-model Weighting

  2008cites this paper
• The ISL RT-07 Speech-to-Text System

  2007cites this paper
• The ISL 2007 English speech transcription system for european parliament speeches

  2007cites this paper
• Gradient Boosting Learning of Hidden Markov Models

  2006influential citation
• The ISL RT-06S Speech-to-Text System

  2006cites this paper
• Optimizing acoustic models for commercial speech recognition using foreground scores and data weighting

  2004cites this paper
• Some Issues in Speech Recognizer Portability

  2003cites this paper
• Towards automatic closed captioning : low latency real time broadcast news transcription

  2002cites this paper
• Improved cross-task recognition using MMIE training

  2002cites this paper
• Minimum Phone Error and I-smoothing for improved discriminative training

  2002cites this paper
• Engineering Department Noisy Cmllr for Noise-robust Speech Recognition

  year unknowninfluential citation