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

Sainath, Tara N.; Kanevsky, Dimitri; Ramabhadran, Bhuvana

doi:10.1109/asru.2007.4430129

Cited by 5 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The larger the value in T indicates that the gradient to adapt the initial model to the data is steeper and the data is much better explained by the updated modelλ j (C). These gradient steepness metrics were succesfully used in various speech recognition classification, segmentation and decoding tasks (see [7], [8]…”

Section: Linearization Of Ebw Gradient Steepnessmentioning

confidence: 99%

A generalized family of parameter estimation techniques

Kanevsky

Sainath²,

Ramabhadran

2009

2009 IEEE International Conference on Acoustics, Speech and Signal Processing

Self Cite

View full text Add to dashboard Cite

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 approaches. Namely, we introduce a general family of model parameter updates that generalizes a Baum-Welch (BW) recursive process to an arbitrary objective function of Gaussian Mixture Models, and show how other commonly used parameter estimation techniques belong to this family of model update rules. We present a linearlized formulation that allows for the construction of an even more general family of update rules with any specified value for the gradient that measures how much an initial model is moved to an estimated updated model.

show abstract

Section: Linearization Of Ebw Gradient Steepnessmentioning

confidence: 99%

A generalized family of parameter estimation techniques

Kanevsky

Sainath²,

Ramabhadran

2009

2009 IEEE International Conference on Acoustics, Speech and Signal Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [5], we compared scoring b k (ot) using likelihood and the gradient metric given in Equation 6 for the recognition of Broad Phonetic Classes (BPC). Below, we discuss novel learning rate and model update methods in the EBW framework.…”

Section: Ebw Gradient Metricmentioning

confidence: 99%

Generalization of extended baum-welch parameter estimation for discriminative training and decoding

et al. 2008

Self Cite

View full text Add to dashboard Cite

We demonstrate the generalizability of the Extended Baum-Welch (EBW) algorithm not only for HMM parameter estimation but for decoding as well. We show that there can exist a general function associated with the objective function under EBW that reduces to the well-known auxiliary function used in the Baum-Welch algorithm for maximum likelihood estimates. We generalize representation for the updates of model parameters by making use of a differentiable function (such as arithmetic or geometric mean) on the updated and current model parameters and describe their effect on the learning rate during HMM parameter estimation. Improvements on speech recognition tasks are also presented here.

show abstract

“…In a phoneme recognition study [12], it was found that almost 80% of misclassified phonemes were within the same broad phonetic class: vowels/semi-vowels, nasals/flaps, stops, weak fricatives, strong fricatives, and closures/silence. Broad phonetic classes have been applied for improved phone recognition [13,14], and have been shown to be more robust in noise [14,15]. Broad phonetic classes have also been used in large vocabulary ASR to overcome the issue of data sparsity and robustness.…”

Section: Introductionmentioning

confidence: 99%

Robust speaking rate estimation using broad phonetic class recognition

Yuan

Liberman

2010

2010 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

Robust speaking rate estimation can be useful in automatic speech recognition and speaker identification, and accurate, automatic measures of speaking rate are also relevant for research in linguistics, psychology, and social sciences. In this study we built a broad phonetic class recognizer for speaking rate estimation. We tested the recognizer on a variety of data sets, including laboratory speech, telephone conversations, foreign accented speech, and speech in different languages, and we found that the recognizer's estimates are robust under these sources of variation. We also found that the acoustic models of the broad phonetic classes are more robust than those of the monophones for syllable detection. KeywordsSpeaking rate estimation, syllable detection, robustness, broad phonetic class ©2010 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.This conference paper is available at ScholarlyCommons: http://repository.upenn.edu/cis_papers/444 ROBUST SPEAKING RATE ESTIMATION USING BROAD PHONETIC CLASS RECOGNITION Jiahong Yuan and Mark LibermanUniversity of Pennsylvania ABSTRACTRobust speaking rate estimation can be useful in automatic speech recognition and speaker identification, and accurate, automatic measures of speaking rate are also relevant for research in linguistics, psychology, and social sciences. In this study we built a broad phonetic class recognizer for speaking rate estimation. We tested the recognizer on a variety of data sets, including laboratory speech, telephone conversations, foreign accented speech, and speech in different languages, and we found that the recognizer's estimates are robust under these sources of variation. We also found that the acoustic models of the broad phonetic classes are more robust than those of the monophones for syllable detection.

show abstract

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

Cited by 5 publications

References 14 publications

A generalized family of parameter estimation techniques

A generalized family of parameter estimation techniques

Generalization of extended baum-welch parameter estimation for discriminative training and decoding

Robust speaking rate estimation using broad phonetic class recognition

Contact Info

Product

Resources

About