Results 1 
8 of
8
Bayesian adaptive inference and adaptive training
 IEEE Transactions Speech and Audio Processing
, 2007
"... Abstract—Largevocabulary speech recognition systems are often built using found data, such as broadcast news. In contrast to carefully collected data, found data normally contains multiple acoustic conditions, such as speaker or environmental noise. Adaptive training is a powerful approach to build ..."
Abstract

Cited by 9 (7 self)
 Add to MetaCart
(Show Context)
Abstract—Largevocabulary speech recognition systems are often built using found data, such as broadcast news. In contrast to carefully collected data, found data normally contains multiple acoustic conditions, such as speaker or environmental noise. Adaptive training is a powerful approach to build systems on such data. Here, transforms are used to represent the different acoustic conditions, and then a canonical model is trained given this set of transforms. This paper describes a Bayesian framework for adaptive training and inference. This framework addresses some limitations of standard maximumlikelihood approaches. In contrast to the standard approach, the adaptively trained system can be directly used in unsupervised inference, rather than having to rely on initial hypotheses being present. In addition, for limited adaptation data, robust recognition performance can be obtained. The limited data problem often occurs in testing as there is no control over the amount of the adaptation data available. In contrast, for adaptive training, it is possible to control the system complexity to reflect the available data. Thus, the standard point estimates may be used. As the integral associated with Bayesian adaptive inference is intractable, various marginalization approximations are described, including a variational Bayes approximation. Both batch and incremental modes of adaptive inference are discussed. These approaches are applied to adaptive training of maximumlikelihood linear regression and evaluated on a largevocabulary speech recognition task. Bayesian adaptive inference is shown to significantly outperform standard approaches. Index Terms—Adaptive training, Bayesian adaptation, Bayesian inference, incremental, variational Bayes.
Adaptive Training for Large Vocabulary Continuous Speech Recognition
, 2006
"... Summary In recent years, there has been a trend towards training large vocabulary continuous speech recognition (LVCSR) systems on a large amount of found data. Found data is recorded from spontaneous speech without careful control of the recording acoustic conditions, for example, conversational te ..."
Abstract

Cited by 8 (2 self)
 Add to MetaCart
Summary In recent years, there has been a trend towards training large vocabulary continuous speech recognition (LVCSR) systems on a large amount of found data. Found data is recorded from spontaneous speech without careful control of the recording acoustic conditions, for example, conversational telephone speech. Hence, it typically has greater variability in terms of speaker and acoustic conditions than specially collected data. Thus, in addition to the desired speech variability required to discriminate between words, it also includes various nonspeech variabilities, for example, the change of speakers or acoustic environments. The standard approach to handle this type of data is to train hidden Markov models (HMMs) on the whole data set as if all data comes from a single acoustic condition. This is referred to as multistyle training, for example speakerindependent training. Effectively, the nonspeech variabilities are ignored. Though good performance has been obtained with multistyle systems, these systems account for all variabilities. Improvement may be obtained if the two types of variabilities in the found data are modelled separately. Adaptive training has been proposed for this purpose. In contrast to multistyle training, a set of transforms is used to represent the nonspeech variabilities. A canonical
Incremental adaptation using Bayesian inference
 in Proc. ICASSP, 2006
"... Adaptive training is a powerful technique to build system on nonhomogeneous training data. Here, a canonical model, representing “pure ” speech variability and a set of transforms representing unwanted acoustic variabilities are both trained. To use the canonical model for recognition, a transform f ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
(Show Context)
Adaptive training is a powerful technique to build system on nonhomogeneous training data. Here, a canonical model, representing “pure ” speech variability and a set of transforms representing unwanted acoustic variabilities are both trained. To use the canonical model for recognition, a transform for the test acoustic condition is required. For some situations a robust estimate of the transform parameters may not be possible due to limited, or no, adaptation data. One solution to this problem is to view adaptive training in a Bayesian framework and marginalise out the transform parameters. Exact implementation of this Bayesian inference is intractable. Recently, lower bound approximations based on variational Bayes have been used to solve this problem for batch adaptation with limited data. This paper extends this Bayesian adaptation framework to incremental adaptation. Various lowerbound approximations and options for propagating information within this incremental framework are discussed. Experiments using adaptive models trained with both maximum likelihood and minimum phone error training are described. Using incremental Bayesian adaptation gains were obtained over the standard approaches, especially for limited data. 1.
Discriminative Adaptive Training and Bayesian Inference for Speech Recognition
, 2009
"... ..."
(Show Context)
Bayesian Adaptive Inference and Adaptive Training Abstract — Large
"... vocabulary speech recognition systems are often built using found data, such as broadcast news. In contrast to carefully collected data, found data normally contains multiple acoustic conditions, such as speaker or environmental noise. Adaptive training is a powerful approach to build systems on suc ..."
Abstract
 Add to MetaCart
(Show Context)
vocabulary speech recognition systems are often built using found data, such as broadcast news. In contrast to carefully collected data, found data normally contains multiple acoustic conditions, such as speaker or environmental noise. Adaptive training is a powerful approach to build systems on such data. Here transforms are used to represent the different acoustic conditions and then a canonical model is trained given this set of transforms. This paper describes a Bayesian framework for adaptive training and inference. This framework addresses some limitations of standard ML approaches. In contrast to the standard approach, the adaptively trained system can be directly used in unsupervised inference, rather than having to rely on initial hypotheses being present. In addition, for limited adaptation data, robust recognition performance can be obtained. The limited data problem often occurs in testing as there is no control over the amount of the adaptation data available. In contrast, for adaptive training, it is possible to control the system complexity to reflect the available data. Thus, the standard point estimates may be used. As the integral associated with Bayesian adaptive inference is intractable, various marginalisation approximations are described, including a variational Bayes approximation. Both batch and incremental modes of adaptive inference are discussed. These approaches are applied to adaptive training of maximum likelihood linear regression and evaluated on a large vocabulary speech recognition task. Bayesian adaptive inference is shown to significantly outperform standard approaches.
unknown title
"... Adaptive training is a powerful technique to build system on nonhomogeneous training data. A canonical model, representing “pure” speech variability and a set of transforms representing unwanted acoustic variabilities are trained. It is necessary to have transforms in order to deal with the testing ..."
Abstract
 Add to MetaCart
(Show Context)
Adaptive training is a powerful technique to build system on nonhomogeneous training data. A canonical model, representing “pure” speech variability and a set of transforms representing unwanted acoustic variabilities are trained. It is necessary to have transforms in order to deal with the testing acoustic conditions. One problem here is to robustly estimate the transforms parameters where there is limited or even no adaptation data. Recently, Lower bound based Bayesian approaches have been used to solve this problem in batch adaptation mode, of which point estimates, MAP or ML, and variational Bayes are two main approximation forms. This paper extends the Bayesian adaptation framework to incremental mode. Strict Bayesian inference and various approximated information propagation strategies during adaptation are discussed in detail. The techniques are examined for both ML and discriminative systems. The experiments on a large vocabulary speech recognition task showed that the incremental Bayesian adaptation can lead to robust performance with limited data at the start and gradually improve with more data available. 1.
Bayesian Approaches to Acoustic Modeling: A Review
, 2012
"... This paper focuses on applications of Bayesian approaches to acoustic modeling for speech recognition and related speech processing applications. Bayesian approaches have been widely studied in the fields of statistics and machine learning, and one of their advantages is that their generalization ca ..."
Abstract
 Add to MetaCart
This paper focuses on applications of Bayesian approaches to acoustic modeling for speech recognition and related speech processing applications. Bayesian approaches have been widely studied in the fields of statistics and machine learning, and one of their advantages is that their generalization capability is better than that of conventional approaches (e.g., maximum likelihood). On the other hand, since inference in Bayesian approaches involves integrals and expectations that are mathematically intractable in most cases and require heavy numerical computations, it is generally difficult to apply them to practical speech recognition problems. However, there have been many such attempts, and this paper aims to summarize these attempts to encourage further progress on Bayesian approaches in the speech processing field. This paper describes various applications of Bayesian approaches to speech processing in terms of the four typical ways of approximating Bayesian inferences, i.e., maximum a posteriori approximation, model complexity control using a Bayesian information criterion based on asymptotic approximation, variational approximation, and Markov chain Monte Carlo based sampling techniques.