Dimitri Kanevsky - IEEE Xplore Author Profile
Access provided by:

MIT Libraries

Sign Out
Access provided by:

MIT Libraries

Sign Out
ADVANCED SEARCH

Author details

< Back

Dimitri Kanevsky

Also published under: D. Kanevsky, D. S. Kanevsky

Publications
34
Citations
762
Publications by Year
19882013
Co-Authors:
Show All Co-Authors (57)
Headshot silhouette indicating that no photo is available for this author

Dimitri Kanevsky

Also published under: D. Kanevsky, D. S. Kanevsky

Affiliation

IBM Thomas J. Watson Research Center, NY, USA

Publication Topics

Biography

Dimitri Kanevsky photograph and biography not available at the time of publication.(Based on document published on 17 October 2013).
Publications
34
Citations
762
Publications by Year
19882013
Co-Authors:
Show All Co-Authors (57)
Author's Published Works

Showing 1-25 of 34 results

  • Sort

Filter Results

Show

Sort By

Results

An evaluation of posterior modeling techniques for phonetic recognition

Rohit Prabhavalkar;Tara N. Sainath;David Nahamoo;Bhuvana Ramabhadran;Dimitri Kanevsky

2013 IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2013 | Conference Paper |
Cited by: Papers (2)
Several methods have been proposed recently for modeling posterior representations derived from local classifiers [1, 2]. In recent work, Sainath et al. have proposed the use of a tied-mixture-based posterior modeling approach [3] to enhance exemplar-based posterior representations for phone recognition tasks. In this work, we conduct a detailed evaluation to determine the effectiveness of this te...Show More

An evaluation of posterior modeling techniques for phonetic recognition

Rohit Prabhavalkar;Tara N. Sainath;David Nahamoo;Bhuvana Ramabhadran;Dimitri Kanevsky

Year: 2013 | Conference Paper |

Optimization Algorithms and Applications for Speech and Language Processing

Stephen J. Wright;Dimitri Kanevsky;Li Deng;Xiaodong He;Georg Heigold;Haizhou Li

IEEE Transactions on Audio, Speech, and Language Processing
Year: 2013 | Volume: 21, Issue: 11 | Journal Article |
Cited by: Papers (19)
Optimization techniques have been used for many years in the formulation and solution of computational problems arising in speech and language processing. Such techniques are found in the Baum-Welch, extended Baum-Welch (EBW), Rprop, and GIS algorithms, for example. Additionally, the use of regularization terms has been seen in other applications of sparse optimization. This paper outlines a range...Show More

Optimization Algorithms and Applications for Speech and Language Processing

Stephen J. Wright;Dimitri Kanevsky;Li Deng;Xiaodong He;Georg Heigold;Haizhou Li

Year: 2013 | Volume: 21, Issue: 11 | Journal Article |

Exemplar-Based Processing for Speech Recognition: An Overview

Tara N. Sainath;Bhuvana Ramabhadran;David Nahamoo;Dimitri Kanevsky;Dirk Van Compernolle;Kris Demuynck;Jort Florent Gemmeke;Jerome R. Bellegarda;Shiva Sundaram

IEEE Signal Processing Magazine
Year: 2012 | Volume: 29, Issue: 6 | Magazine Article |
Cited by: Papers (33)
Solving real-world classification and recognition problems requires a principled way of modeling the physical phenomena generating the observed data and the uncertainty in it. The uncertainty originates from the fact that many data generation aspects are influenced by nondirectly measurable variables or are too complex to model and hence are treated as random fluctuations. For example, in speech p...Show More

Exemplar-Based Processing for Speech Recognition: An Overview

Tara N. Sainath;Bhuvana Ramabhadran;David Nahamoo;Dimitri Kanevsky;Dirk Van Compernolle;Kris Demuynck;Jort Florent Gemmeke;Jerome R. Bellegarda;Shiva Sundaram

Year: 2012 | Volume: 29, Issue: 6 | Magazine Article |

Unscented compressed sensing

Avishy Y. Carmi;Lyudmila Mihaylova;Dimitri Kanevsky

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2012 | Conference Paper |
Cited by: Papers (6)
In this paper we present a novel compressed sensing (CS) algorithm for the recovery of compressible, possibly time-varying, signal from a sequence of noisy observations. The newly derived scheme is based on the acclaimed unscented Kalman filter (UKF), and is essentially self reliant in the sense that no peripheral optimization or CS algorithm is required for identifying the underlying signal suppo...Show More

Unscented compressed sensing

Avishy Y. Carmi;Lyudmila Mihaylova;Dimitri Kanevsky

Year: 2012 | Conference Paper |

Overview of large scale optimization for discriminative training in speech recognition

Dimitri Kanevsky;Georg Heigold;Stephen Wright;Hermann Ney

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2012 | Conference Paper |
Cited by: Papers (1)
Over the past few decades, a variety of specialized approaches have been proposed to solve large problems in speech recognition. Conventional optimization techniques have not been widely applied, because the problems do not readily admit an objective for evaluating a given set of parameters and because of the large number of parameters. This situation is changing, due to recent developments in alg...Show More

Overview of large scale optimization for discriminative training in speech recognition

Dimitri Kanevsky;Georg Heigold;Stephen Wright;Hermann Ney

Year: 2012 | Conference Paper |

A convex hull approach to sparse representations for exemplar-based speech recognition

Tara N. Sainath;David Nahamoo;Dimitri Kanevsky;Bhuvana Ramabhadran;Parikshit Shah

2011 IEEE Workshop on Automatic Speech Recognition & Understanding
Year: 2011 | Conference Paper |
Cited by: Papers (3)
In this paper, we propose a novel exemplar based technique for classification problems where for every new test sample the classification model is re-estimated from a subset of relevant samples of the training data.We formulate the exemplar-based classification paradigm as a sparse representation (SR) problem, and explore the use of convex hull constraints to enforce both regularization and sparsi...Show More

A convex hull approach to sparse representations for exemplar-based speech recognition

Tara N. Sainath;David Nahamoo;Dimitri Kanevsky;Bhuvana Ramabhadran;Parikshit Shah

Year: 2011 | Conference Paper |

A-Functions: A generalization of Extended Baum-Welch transformations to convex optimization

Dimitri Kanevsky;David Nahamoo;Tara N. Sainath;Bhuvana Ramabhadran;Peder A. Olsen

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2011 | Conference Paper |
Cited by: Papers (7) | Patents (1)
We introduce the Line Search A-Function (LSAF) technique that generalizes the Extended-Baum Welch technique in order to provide an effective optimization technique for a broader set of functions. We show how LSAF can be applied to functions of various probability density and distribution functions by demonstrating that these probability functions have an A-function. We also show that sparse repres...Show More

A-Functions: A generalization of Extended Baum-Welch transformations to convex optimization

Dimitri Kanevsky;David Nahamoo;Tara N. Sainath;Bhuvana Ramabhadran;Peder A. Olsen

Year: 2011 | Conference Paper |

Defining the controlling parameter in constrained discriminative linear transform for supervised speaker adaptation

Danning Jiang;Dimitri Kanevsky;Emmanuel Yashchin;Yong Qin

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2011 | Conference Paper |
Constrained discriminative linear transform (CDLT) optimized with Extended Baum-Welch (EBW) has been presented in the literature as a discriminative speaker adaptation method that outperforms the conventional maximum likelihood algorithm. Defining the controlling parameter of EBW to achieve the best performance of speaker adaptation, however, still remains an open question. This paper presents an ...Show More

Defining the controlling parameter in constrained discriminative linear transform for supervised speaker adaptation

Danning Jiang;Dimitri Kanevsky;Emmanuel Yashchin;Yong Qin

Year: 2011 | Conference Paper |

Exemplar-based Sparse Representation phone identification features

Tara N. Sainath;David Nahamoo;Bhuvana Ramabhadran;Dimitri Kanevsky;Vaibhava Goel;Parikshit M. Shah

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2011 | Conference Paper |
Cited by: Papers (5) | Patents (1)
Exemplar-based techniques, such as k-nearest neighbors (kNNs) and Sparse Representations (SRs), can be used to model a test sample from a few training points in a dictionary set. In past work, we have shown that using a SR approach for phonetic classification allows for a higher accuracy than other classification techniques. These phones are the basic units of speech to be recognized. Motivated by...Show More

Exemplar-based Sparse Representation phone identification features

Tara N. Sainath;David Nahamoo;Bhuvana Ramabhadran;Dimitri Kanevsky;Vaibhava Goel;Parikshit M. Shah

Year: 2011 | Conference Paper |

Exemplar-Based Sparse Representation Features: From TIMIT to LVCSR

Tara N. Sainath;Bhuvana Ramabhadran;Michael Picheny;David Nahamoo;Dimitri Kanevsky

IEEE Transactions on Audio, Speech, and Language Processing
Year: 2011 | Volume: 19, Issue: 8 | Journal Article |
The use of exemplar-based methods, such as support vector machines (SVMs), k-nearest neighbors (kNNs) and sparse representations (SRs), in speech recognition has thus far been limited. Exemplar-based techniques utilize information about individual training examples and are computationally expensive, making it particularly difficult to investigate these methods on large-vocabulary continuous speech...Show More

Exemplar-Based Sparse Representation Features: From TIMIT to LVCSR

Tara N. Sainath;Bhuvana Ramabhadran;Michael Picheny;David Nahamoo;Dimitri Kanevsky

Year: 2011 | Volume: 19, Issue: 8 | Journal Article |

Kalman filtering for compressed sensing

Dimitri Kanevsky;Avishy Carmi;Lior Horesh;Pini Gurfil;Bhuvana Ramabhadran;Tara N Sainath

2010 13th International Conference on Information Fusion
Year: 2010 | Conference Paper |
Cited by: Papers (15)
Compressed sensing is a new emerging field dealing with the reconstruction of a sparse or, more precisely, a compressed representation of a signal from a relatively small number of observations, typically less than the signal dimension. In our previous work we have shown how the Kalman filter can be naturally applied for obtaining an approximate Bayesian solution for the compressed sensing problem...Show More

Kalman filtering for compressed sensing

Dimitri Kanevsky;Avishy Carmi;Lior Horesh;Pini Gurfil;Bhuvana Ramabhadran;Tara N Sainath

Year: 2010 | Conference Paper |

Bayesian compressive sensing for phonetic classification

Tara N. Sainath;Avishy Carmi;Dimitri Kanevsky;Bhuvana Ramabhadran

2010 IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2010 | Conference Paper |
In this paper, we introduce a novel Bayesian compressive sensing (CS) technique for phonetic classification. CS is often used to characterize a signal from a few support training examples, similar to k-nearest neighbor (kNN) and Support Vector Machines (SVMs). However, unlike SVMs and kNNs, CS allows the number of supports to be adapted to the specific signal being characterized. On the TIMIT phon...Show More

Bayesian compressive sensing for phonetic classification

Tara N. Sainath;Avishy Carmi;Dimitri Kanevsky;Bhuvana Ramabhadran

Year: 2010 | Conference Paper |

The Use of isometric transformations and bayesian estimation in compressive sensing for fMRI classification

Avishy Carmi;Tara N. Sainath;Pini Gurfil;Dimitri Kanevsky;David Nahamoo;Bhuvana Ramabhadran

2010 IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2010 | Conference Paper |
Cited by: Papers (2) | Patents (1)
Compressive sensing (CS) is a popular technique used to reconstruct a signal from few training examples, a problem which arises in many machine learning applications. In this paper, we introduce a technique to guarantee that our data obeys certain isometric properties. In addition, we introduce a bayesian approach to compressive sensing, which we call ABCS, allowing us to obtain complete statistic...Show More

The Use of isometric transformations and bayesian estimation in compressive sensing for fMRI classification

Avishy Carmi;Tara N. Sainath;Pini Gurfil;Dimitri Kanevsky;David Nahamoo;Bhuvana Ramabhadran

Year: 2010 | Conference Paper |

Methods for Sparse Signal Recovery Using Kalman Filtering With Embedded Pseudo-Measurement Norms and Quasi-Norms

Avishy Carmi;Pini Gurfil;Dimitri Kanevsky

IEEE Transactions on Signal Processing
Year: 2010 | Volume: 58, Issue: 4 | Journal Article |
Cited by: Papers (124)
We present two simple methods for recovering sparse signals from a series of noisy observations. The theory of compressed sensing (CS) requires solving a convex constrained minimization problem. We propose solving this optimization problem by two algorithms that rely on a Kalman filter (KF) endowed with a pseudo-measurement (PM) equation. Compared to a recently-introduced KF-CS method, which invol...Show More

Methods for Sparse Signal Recovery Using Kalman Filtering With Embedded Pseudo-Measurement Norms and Quasi-Norms

Avishy Carmi;Pini Gurfil;Dimitri Kanevsky

Year: 2010 | Volume: 58, Issue: 4 | Journal Article |

Map approach to learning sparse Gaussian Markov networks

N. Bani Asadi;I. Rish;K. Scheinberg;D. Kanevsky;B. Ramabhadran

2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2009 | Conference Paper |
Cited by: Papers (3)
Recently proposed l1-regularized maximum-likelihood optimization methods for learning sparse Markov networks result into convex problems that can be solved optimally and efficiently. However, the accuracy of such methods can be very sensitive to the choice of regularization parameter, and optimal selection of this parameter remains an open problem. Herein, we propose a maximum a posteriori probabi...Show More

Map approach to learning sparse Gaussian Markov networks

N. Bani Asadi;I. Rish;K. Scheinberg;D. Kanevsky;B. Ramabhadran

Year: 2009 | Conference Paper |

A generalized family of parameter estimation techniques

Dimitri Kanevsky;Tara N. Sainath;Bhuvana Ramabhadran

2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2009 | Conference Paper |
Cited by: Papers (1)
The extended Baum-Welch (EBW) transformations is one of a variety of techniques to estimate parameters of Gaussian mixture models. In this paper, we provide a theoretical framework for general parameter estimation and show the relationship between these different techniques. We introduce a general family of model parameter updates that generalizes a Baum-Welch (BW) recursive process to an arbitrar...Show More

A generalized family of parameter estimation techniques

Dimitri Kanevsky;Tara N. Sainath;Bhuvana Ramabhadran

Year: 2009 | Conference Paper |

Gradient steepness metrics using extended Baum-Welch transformations for universal pattern recognition tasks

Tara N. Sainath;Dimitri Kanevsky;Bhuvana Ramabhadran

2008 IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2008 | Conference Paper |
Cited by: Papers (1) | Patents (1)
In many pattern recognition tasks, given some input data and a family of models, the "best" model is defined as the one which maximizes the likelihood of the data given the model. Extended Baum- Welch (EBW) transformations are most commonly used as a discriminative technique for estimating parameters of Gaussian mixtures. In this paper, we use the EBW transformations to derive a novel gradient ste...Show More

Gradient steepness metrics using extended Baum-Welch transformations for universal pattern recognition tasks

Tara N. Sainath;Dimitri Kanevsky;Bhuvana Ramabhadran

Year: 2008 | Conference Paper |

MAAI: Media analytics for actionable intelligence

Upendra Chaudhari;Sarah Conrod;Alexander Faisman;Giridharan Iyengar;Dimitri Kanevsky;Mark Kogan;Ganesh Ramaswamy;Paola Virga

2008 IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2008 | Conference Paper |
Government agencies, corporations, and police departments are plagued by information overload. The inability of fully analyze fragments of data scattered across the organizations reduces productivity, and more and more of these fragments are being gathered every day thanks to tools like the Internet and digital audio/video recorders. However, since much of this information is stored in computer sy...Show More

MAAI: Media analytics for actionable intelligence

Upendra Chaudhari;Sarah Conrod;Alexander Faisman;Giridharan Iyengar;Dimitri Kanevsky;Mark Kogan;Ganesh Ramaswamy;Paola Virga

Year: 2008 | Conference Paper |

Boosted MMI for model and feature-space discriminative training

Daniel Povey;Dimitri Kanevsky;Brian Kingsbury;Bhuvana Ramabhadran;George Saon;Karthik Visweswariah

2008 IEEE International Conference on Acoustics, Speech and Signal Processing
Year: 2008 | Conference Paper |
We present a modified form of the maximum mutual information (MMI) objective function which gives improved results for discriminative training. The modification consists of boosting the likelihoods of paths in the denominator lattice that have a higher phone error relative to the correct transcript, by using the same phone accuracy function that is used in Minimum Phone Error (MPE) training. We co...Show More

Boosted MMI for model and feature-space discriminative training

Daniel Povey;Dimitri Kanevsky;Brian Kingsbury;Bhuvana Ramabhadran;George Saon;Karthik Visweswariah

Year: 2008 | Conference Paper |

Broad phonetic class recognition in a Hidden Markov model framework using extended Baum-Welch transformations

Tara N. Sainath;Dimitri Kanevsky;Bhuvana Ramabhadran

2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)
Year: 2007 | Conference Paper |
Cited by: Papers (2) | Patents (2)
In many pattern recognition tasks, given some input data and a model, a probabilistic likelihood score is often computed to measure how well the model describes the data. Extended Baum-Welch (EBW) transformations are most commonly used as a discriminative technique for estimating parameters of Gaussian mixtures, though recently they have been used to derive a gradient steepness measurement to eval...Show More

Broad phonetic class recognition in a Hidden Markov model framework using extended Baum-Welch transformations

Tara N. Sainath;Dimitri Kanevsky;Bhuvana Ramabhadran

Year: 2007 | Conference Paper |

Unsupervised Audio Segmentation using Extended Baum-Welch Transformations

Tara N. Sainath;Dimitri Kanevsky;Giridharan Iyengar

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07
Year: 2007 | Conference Paper |
Cited by: Papers (9) | Patents (3)
Audio segmentation has applications in a variety of contexts, such as audio information retrieval, automatic sound analysis, and as a pre-processing step in speech recognition. Extended Baum-Welch (EBW) transformations are most commonly used as a discriminative technique for estimating parameters of Gaussian mixtures. In this paper, we derive an unsupervised audio segmentation approach using these...Show More

Unsupervised Audio Segmentation using Extended Baum-Welch Transformations

Tara N. Sainath;Dimitri Kanevsky;Giridharan Iyengar

Year: 2007 | Volume: 1 | Conference Paper |

Adding User-Level SPACe: Security, Privacy, and Context to Intelligent Multimedia Information Architectures

Dawn N. Jutla;Dimitri Kanevsky

2006 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology Workshops
Year: 2006 | Conference Paper |
Cited by: Patents (4)
We provide a unified architecture, called SPACe, for secure, privacy-aware, and contextual multimedia systems in organizations. Many key and important architectural components already exist which contribute to a unified platform, including the classic data mining, security, and privacy-preserving components in conventional intelligent systems. After presenting an overview of our unified architectu...Show More

Adding User-Level SPACe: Security, Privacy, and Context to Intelligent Multimedia Information Architectures

Dawn N. Jutla;Dimitri Kanevsky

Year: 2006 | Conference Paper |

Accessibility, transcription, and access everywhere

K. Bain;S. Basson;A. Faisman;D. Kanevsky

IBM Systems Journal
Year: 2005 | Volume: 44, Issue: 3 | Journal Article |
Accessibility in the workplace and in academic settings has increased dramatically for users with disabilities, driven by greater awareness, legislative mandate, and technological improvements. Gaps, however, remain. For persons who are deaf and hard of hearing in particular, full participation requires complete access to audio materials, both for live settings and for prerecorded audio and visual...Show More

Accessibility, transcription, and access everywhere

K. Bain;S. Basson;A. Faisman;D. Kanevsky

Year: 2005 | Volume: 44, Issue: 3 | Journal Article |

Extended Baum transformations for general functions

D. Kanevsky

2004 IEEE International Conference on Acoustics, Speech, and Signal Processing
Year: 2004 | Conference Paper |
The discrimination technique for estimating the parameters of Gaussian mixtures that is based on the extended Baum transformations (EB) has had significant impact on the speech recognition community. There appear to be no published proofs that definitively show that these transformations increase the value of an objective function with iteration (i.e., so-called "growth transformations"). The proo...Show More

Extended Baum transformations for general functions

D. Kanevsky

Year: 2004 | Volume: 1 | Conference Paper |

Recent improvements to IBM's speech recognition system for automatic transcription of broadcast news

S.S. Chen;E.M. Eide;M.J.F. Gales;R.A. Gopinath;D. Kanevsky;P. Olsen

1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)
Year: 1999 | Conference Paper |
Cited by: Papers (9) | Patents (7)
We describe extensions and improvements to IBM's system for automatic transcription of broadcast news. The speech recognizer uses a total of 160 hours of acoustic training data, 80 hours more than for the system described in Chen et al. (1998). In addition to improvements obtained in 1997 we made a number of changes and algorithmic enhancements. Among these were changing the acoustic vocabulary, r...Show More

Recent improvements to IBM's speech recognition system for automatic transcription of broadcast news

S.S. Chen;E.M. Eide;M.J.F. Gales;R.A. Gopinath;D. Kanevsky;P. Olsen

Year: 1999 | Volume: 1 | Conference Paper |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.