Generalization problem in ASR acoustic model training and adaptation

No abstract is available for this paper.

• Publication year

  2009

• Venue

  2009 IEEE Workshop on Automatic Speech Recognition & Understanding

• Publication date

  2009-12-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ASRU.2009.5373493
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Pattern Classification

  2021influential reference
• Pattern Classification

  2012influential reference
• Bayesian discriminative adaptation for speech recognition

  2009cited by this paper
• Discriminative Learning for Minimum Error Classification

  2009influential reference
• Unsupervisec cross-validation adaptation algorithms for improved adaptation performance

  2009cited by this paper
• Selected topics from 40 years of research on speech and speaker recognition

  2009cited by this paper
• Penalty function maximization for large margin HMM training

  2008cited by this paper
• Discriminative Learning for Speech Recognition: Theory and Practice

  2008cited by this paper
• Unsupervised discriminative adaptation using discriminative mapping transforms

  2008cited by this paper
• Large-margin Minimum Classification Error Training: a Theoretical Risk Minimization Perspective Computer Speech and Language Author's Personal Copy

  2008cited by this paper
• Towards Superhuman Speech Recognition

  2008cited by this paper
• Modified MMI/MPE: a direct evaluation of the margin in speech recognition

  2008cited by this paper
• MPE-based discriminative linear transforms for speaker adaptation

  2008cited by this paper
• The Application of Hidden Markov Models in Speech Recognition

  2007influential reference
• Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error

  2007cited by this paper
• Bayesian Adaptive Inference and Adaptive Training

  2007cited by this paper
• Impact of variabilities on speech recognition

  2006cited by this paper
• An Unsupervised Speaker Adaptation Method for Lecture-Style Spontaneous Speech Recognition Using Multiple Recognition Systems

  2005cited by this paper
• Confidence measures for speech recognition: A survey

  2005cited by this paper
• Why Is the Recognition of Spontaneous Speech so Hard?

  2005cited by this paper
• Recent Progress in Corpus-Based Spontaneous Speech Recognition

  2005cited by this paper
• Introduction to the Special Issue on Spontaneous Speech Processing

  2004cited by this paper
• MPE-based discriminative linear transform for speaker adaptation

  2004cited by this paper
• Hidden factor dynamic Bayesian networks for speech recognition

  2004cited by this paper
• Speech recognition system robust to noise and speaking styles

  2004cited by this paper
• Spontaneous speech recognition using a massively parallel decoder

  2004cited by this paper
• Fifty years of progress in speech and speaker recognition

  2004cited by this paper
• Time adjustable mixture weights for speaking rate fluctuation

  2003cited by this paper
• Hidden mode HMM using Bayesian network for modeling speaking rate fluctuation

  2003cited by this paper
• Speaking-rate dependent decoding and adaptation for spontaneous lecture speech recognition

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

  2002influential reference
• Factor analysed hidden Markov models

  2002cited by this paper
• Graphical models and automatic speech recognition

  2002cited by this paper
• Structural maximum a posteriori linear regression for fast HMM adaptation

  2002cited by this paper
• Eigenspace-based maximum a posteriori linear regression for rapid speaker adaptation

  2001cited by this paper
• Analytic Methods for Acoustic Model Adaptation : A Review

  2001cited by this paper
• A structural Bayes approach to speaker adaptation

  2001cited by this paper
• Large scale discriminative training for speech recognition

  2000cited by this paper
• Eigenvoices: A compact representation of speakers in model space

  2000cited by this paper
• Transformation-based Bayesian prediction for adaptation of HMMs

  2000cited by this paper
• Pattern classification, 2nd Edition

  2000cited by this paper
• Maximum a posteriori linear regression for hidden Markov model adaptation

  1999cited by this paper
• Maximum likelihood linear transformations for HMM-based speech recognition

  1998cited by this paper
• Cluster adaptive training for speech recognition

  1998cited by this paper
• Speaker clustering and transformation for speaker adaptation in speech recognition systems

  1998cited by this paper
• Eigenvoices for speaker adaptation

  1998cited by this paper
• Speech Recognition with Dynamic Bayesian Networks

  1998cited by this paper
• N-Best-based unsupervised speaker adaptation for speech recognition

  1998cited by this paper
• Jacobian approach to fast acoustic model adaptation

  1997cited by this paper
• Experiments in speaker normalisation and adaptation for large vocabulary speech recognition

  1997cited by this paper
• A compact model for speaker-adaptive training

  1996cited by this paper
• On-line adaptive learning of the correlated continuous density hidden Markov models for speech recognition

  1996cited by this paper
• Signal bias removal by maximum likelihood estimation for robust telephone speech recognition

  1996cited by this paper
• Speaker normalization using efficient frequency warping procedures

  1996cited by this paper
• Maximum Mutual Information Estimation of Hidden Markov Models

  1996cited by this paper
• The generation and use of regression class trees for MLLR adaptation

  1996cited by this paper
• Mean and variance adaptation within the MLLR framework

  1996cited by this paper
• Speaker adaptation with autonomous model complexity control by MDL principle

  1996cited by this paper
• Speaker adaptation based on transfer vector field smoothing using maximum a posteriori probability estimation

  1995cited by this paper
• Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models

  1995cited by this paper
• A study of speaker adaptation based on minimum classification error training

  1995cited by this paper
• Speaker adaptation using constrained estimation of Gaussian mixtures

  1995influential reference
• Speaker adaptation using combined transformation and Bayesian methods

  1995cited by this paper
• Vector-field-smoothed Bayesian learning for incremental speaker adaptation

  1995cited by this paper
• Speaker adaptation with autonomous control using tree structure

  1995cited by this paper
• Batch, incremental and instantaneous adaptation techniques for speech recognition

  1995cited by this paper
• Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains

  1994cited by this paper
• Tree-structured speaker clustering for speaker-independent continuous speech recognition

  1994cited by this paper
• Hidden Markov models, maximum mutual information estimation, and the speech recognition problem

  1992cited by this paper
• Speaker adaptation based on transfer vector field smoothing with continuous mixture density HMMs

  1992cited by this paper
• Discriminative learning for minimum error classification [pattern recognition]

  1992cited by this paper
• Speaker adaptation for demi-syllable based continuous density HMM

  1991cited by this paper
• Environmental robustness in automatic speech recognition

  1990cited by this paper
• Unsupervised speaker adaptation based on hierarchical spectral clustering

  1989cited by this paper
• A training procedure for isolated word recognition systems

  1980cited by this paper
• Normalization of vowels by vocal-tract length and its application to vowel identification

  1977cited by this paper
• 50 Years of Progress in Speech and Speaker Recognition Research

  1970cited by this paper

• What do self-supervised speech representations encode? An analysis of languages, varieties, speaking styles and speakers

  2023cites this paper
• Building ASR systems using Resource-Rich and Resource-Poor languages

  2022cites this paper
• Conversational Speech Recognition Needs Data? Experiments with Austrian German

  2022cites this paper
• Insights on Neural Representations for End-to-End Speech Recognition

  2021cites this paper
• Multi-Channel Speech Enhancement and Amplitude Modulation Analysis for Noise Robust Automatic Speech Recognition

  2017cites this paper
• A MAP-based Online Estimation Approach to Ensemble Speaker and Speaking Environment Modeling

  2014cites this paper
• Fuzzy Phoneme Classification Using Multi-speaker Vocal Tract Length Normalization

  2014cites this paper
• Objective-driven discriminative training and adaptation based on an MCE criterion for speech recognition and detection

  2013cites this paper
• Cross-lingual acoustic model adaptation based on transfer vector field smoothing with MAP

  2013cites this paper
• Speaker-invariant and rhythm-sensitive representation of spoken words

  2013cites this paper
• Towards an improved model of dynamics for speech recognition and synthesis

  2012cites this paper
• N-best entropy based data selection for acoustic modeling

  2012cites this paper
• A MODULATION-DEMODULATION MODEL FOR SPEECH COMMUNICATION AND ITS EMERGENCE

  2012cites this paper
• Speaker adaptation techniques for automatic speech recognition

  2011influential citation
• A modulation-demodulation model of speech communication

  2010cites this paper
• Proposal of a method for acoustic separation of the linguistic information and the extra-linguistic information conveyed in a single speech stream — An attempt toward realizing human-like speech processing on machines —

  2010cites this paper
• Special Section on Processing Natural Speech Variability for Improved Verbal Human-Computer Interaction Acoustic Model Adaptation for Speech Recognition

  2010influential citation
• Proposal of a Method to Extract the Linguistic Information in Speech Based on Acoustic Separation of the Linguistic and Extra-Linguistic Aspects of Speech — — An Attempt toward Realizing Human-Like Speech Processing on Machines — —

  2010cites this paper
• Acoustic Model Adaptation for Speech Recognition

  2010cites this paper