Results 1 - 10
of
570
Semi-tied covariance matrices for hidden Markov models,”
- IEEE Trans. Speech and Audio Processing,
, 1999
"... ..."
(Show Context)
Parametric Hidden Markov Models for Gesture Recognition
- IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 1999
"... A new method for the representation, recognition, and interpretation of parameterized gesture is presented. By parameterized gesture we mean gestures that exhibit a systematic spatial variation; one example is a point gesture where the relevant parameter is the two-dimensional direction. Our approa ..."
Abstract
-
Cited by 208 (3 self)
- Add to MetaCart
A new method for the representation, recognition, and interpretation of parameterized gesture is presented. By parameterized gesture we mean gestures that exhibit a systematic spatial variation; one example is a point gesture where the relevant parameter is the two-dimensional direction. Our approach is to extend the standard hidden Markov model method of gesture recognition by including a global parametric variation in the output probabilities of the HMM states. Using a linear model of dependence, we formulate an expectation-maximization (EM) method for training the parametric HMM. During testing, a similar EM algorithm simultaneously maximizes the output likelihood of the PHMM for the given sequence and estimates the quantifying parameters. Using visually derived and directly measured three-dimensional hand position measurements as input, we present results that demonstrate the recognition superiority of the PHMM over standard HMM techniques, as well as greater robustness in parameter estimation with respect to noise in the input features. Last, we extend the PHMM to handle arbitrary smooth (nonlinear) dependencies. The nonlinear formulation requires the use of a generalized expectation-maximization (GEM) algorithm for both training and the simultaneous recognition of the gesture and estimation of the value of the parameter. We present results on a pointing gesture, where the nonlinear approach permits the natural spherical coordinate parameterization of pointing direction.
Statistical parametric speech synthesis
- in Proc. ICASSP, 2007
, 2007
"... This paper gives a general overview of techniques in statistical parametric speech synthesis. One of the instances of these techniques, called HMM-based generation synthesis (or simply HMM-based synthesis), has recently been shown to be very effective in generating acceptable speech synthesis. This ..."
Abstract
-
Cited by 179 (18 self)
- Add to MetaCart
This paper gives a general overview of techniques in statistical parametric speech synthesis. One of the instances of these techniques, called HMM-based generation synthesis (or simply HMM-based synthesis), has recently been shown to be very effective in generating acceptable speech synthesis. This paper also contrasts these techniques with the more conventional unit selection technology that has dominated speech synthesis over the last ten years. Advantages and disadvantages of statistical parametric synthesis are highlighted as well as identifying where we expect the key developments to appear in the immediate future. Index Terms — Speech synthesis, hidden Markov models 1. BACKGROUND With the increase in power and resources of computer technology, building natural sounding synthetic voices has progressed from a
The Kaldi speech recognition toolkit,” in
- Proc. ASRU,
, 2011
"... Abstract-We describe the design of Kaldi, a free, open-source toolkit for speech recognition research. Kaldi provides a speech recognition system based on finite-state transducers (using the freely available OpenFst), together with detailed documentation and scripts for building complete recognitio ..."
Abstract
-
Cited by 147 (16 self)
- Add to MetaCart
(Show Context)
Abstract-We describe the design of Kaldi, a free, open-source toolkit for speech recognition research. Kaldi provides a speech recognition system based on finite-state transducers (using the freely available OpenFst), together with detailed documentation and scripts for building complete recognition systems. Kaldi is written is C++, and the core library supports modeling of arbitrary phonetic-context sizes, acoustic modeling with subspace Gaussian mixture models (SGMM) as well as standard Gaussian mixture models, together with all commonly used linear and affine transforms. Kaldi is released under the Apache License v2.0, which is highly nonrestrictive, making it suitable for a wide community of users.
Maximum Likelihood Modeling With Gaussian Distributions For Classification
- Proceedings of ICASSP
, 1998
"... Maximum Likelihood (ML) modeling of multiclass data for classication often suers from the following problems: a) data insuciency implying overtrained or unreliable models b) large storage requirement c) large computational requirement and/or d) ML is not discriminating between classes. Sharing param ..."
Abstract
-
Cited by 121 (26 self)
- Add to MetaCart
Maximum Likelihood (ML) modeling of multiclass data for classication often suers from the following problems: a) data insuciency implying overtrained or unreliable models b) large storage requirement c) large computational requirement and/or d) ML is not discriminating between classes. Sharing parameters across classes (or constraining the parameters) clearly tends to alleviate the rst three problems. It this paper we show that in some cases it can also lead to better discrimination (as evidenced by reduced misclassication error). The parameters considered are the means and variances of the gaussians and linear transformations of the feature space (or equivalently the gaussian means). Some constraints on the parameters are shown to lead to Linear Discrimination Analysis (a well-known result) while others are shown to lead to optimal feature spaces (a relatively new result) . Applications of some of these ideas to the speech recognition problem are also given. 1.
Channel compensation for SVM speaker recognition
- in Proceedings of Odyssey-04, The Speaker and Language Recognition Workshop
"... One of the major remaining challenges to improving accuracy in state-of-the-art speaker recognition algorithms is reducing the impact of channel and handset variations on system performance. For Gaussian Mixture Model based speaker recognition systems, a variety of channel-adaptation techniques are ..."
Abstract
-
Cited by 113 (16 self)
- Add to MetaCart
(Show Context)
One of the major remaining challenges to improving accuracy in state-of-the-art speaker recognition algorithms is reducing the impact of channel and handset variations on system performance. For Gaussian Mixture Model based speaker recognition systems, a variety of channel-adaptation techniques are known and available for adapting models between different channel conditions, but for the much more recent Support Vector Machine (SVM) based approaches to this problem, much less is known about the best way to handle this issue. In this paper we explore techniques that are specific to the SVM framework in order to derive fully non-linear channel compensations. The result is a system that is less sensitive to specific kinds of labeled channel variations observed in training. 1.
Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm
- IEEE Trans. Audio Speech Lang. Process
, 2009
"... Abstract—In this paper, we analyze the effects of several factors and configuration choices encountered during training and model construction when we want to obtain better and more stable adaptation in HMM-based speech synthesis. We then propose a new adaptation algorithm called constrained structu ..."
Abstract
-
Cited by 90 (28 self)
- Add to MetaCart
(Show Context)
Abstract—In this paper, we analyze the effects of several factors and configuration choices encountered during training and model construction when we want to obtain better and more stable adaptation in HMM-based speech synthesis. We then propose a new adaptation algorithm called constrained structural maximum a posteriori linear regression (CSMAPLR) whose derivation is based on the knowledge obtained in this analysis and on the results of comparing several conventional adaptation algorithms. Here, we investigate six major aspects of the speaker adaptation: initial models; the amount of the training data for the initial models; the transform functions, estimation criteria, and sensitivity of several linear regression adaptation algorithms; and combination algorithms. Analyzing the effect of the initial model, we compare speaker-dependent models, gender-independent models, and the simultaneous use of the gender-dependent models to single use of the gender-dependent models. Analyzing the effect of the transform functions, we compare the transform function for only mean vectors with that for mean vectors and covariance matrices. Analyzing the effect of the estimation criteria, we compare the ML criterion with a robust estimation criterion called structural MAP. We evaluate the sensitivity of several thresholds for the piecewise linear regression algorithms and take up methods com-bining MAP adaptation with the linear regression algorithms. We incorporate these adaptation algorithms into our speech synthesis system and present several subjective and objective evaluation results showing the utility and effectiveness of these algorithms in speaker adaptation for HMM-based speech synthesis. Index Terms—Average voice, hidden Markov model (HMM)-based speech synthesis, speaker adaptation, speech synthesis, voice conversion. I.
Large Scale Discriminative Training For Speech Recognition
, 2000
"... This paper describes, and evaluates on a large scale, the lattice based framework for discriminative training of large vocabulary speech recognition systems based on Gaussian mixture hidden Markov models (HMMs). The paper concentrates on the maximum mutual information estimation (MMIE) criterion whi ..."
Abstract
-
Cited by 88 (5 self)
- Add to MetaCart
This paper describes, and evaluates on a large scale, the lattice based framework for discriminative training of large vocabulary speech recognition systems based on Gaussian mixture hidden Markov models (HMMs). The paper concentrates on the maximum mutual information estimation (MMIE) criterion which has been used to train HMM systems for conversational telephone speech transcription using up to 265 hours of training data. These experiments represent the largest-scale application of discriminative training techniques for speech recognition of which the authors are aware, and have led to significant reductions in word error rate for both triphone and quinphone HMMs compared to our best models trained using maximum likelihood estimation. The MMIE latticebased implementation used; techniques for ensuring improved generalisation; and interactions with maximum likelihood based adaptation are all discussed. Furthermore several variations to the MMIE training scheme are introduced with the a...
Cluster adaptive training of hidden Markov models,”
- IEEE Trans. Speech and Audio Processing,
, 2000
"... ..."
(Show Context)
Feature engineering in context-dependent deep neural networks for conversational speech transcription
- in ASRU
, 2011
"... Abstract—We investigate the potential of Context-Dependent Deep-Neural-Network HMMs, or CD-DNN-HMMs, from a feature-engineering perspective. Recently, we had shown that for speaker-independent transcription of phone calls (NIST RT03S Fisher data), CD-DNN-HMMs reduced the word error rate by as much a ..."
Abstract
-
Cited by 76 (15 self)
- Add to MetaCart
(Show Context)
Abstract—We investigate the potential of Context-Dependent Deep-Neural-Network HMMs, or CD-DNN-HMMs, from a feature-engineering perspective. Recently, we had shown that for speaker-independent transcription of phone calls (NIST RT03S Fisher data), CD-DNN-HMMs reduced the word error rate by as much as one third—from 27.4%, obtained by discriminatively trained Gaussian-mixture HMMs with HLDA features, to 18.5%—using 300+ hours of training data (Switchboard), 9000+ tied triphone states, and up to 9 hidden network layers. In this paper, we evaluate the effectiveness of feature transforms developed for GMM-HMMs—HLDA, VTLN, and fMLLR—applied to CD-DNN-HMMs. Results show that HLDA is subsumed (expected), as is much of the gain from VTLN (not expected): Deep networks learn vocal-tract length invariant structures to a significant degree. Unsupervised speaker adaptation with discriminatively estimated fMLLR-like transforms works (as hoped for) nearly as well as fMLLR for GMM-HMMs. We also improve model training by a discriminative pretraining procedure, yielding a small accuracy gain due to a better internal feature representation.
