Model Based Speech Recognition System Research Articles

Improving ultrasound-based multimodal speech recognition with predictive features from representation learning.

Representation learning is believed to produce high-level representations of underlying dynamics in temporal sequences. A three-dimensional convolutional neural network trained to predict future frames in ultrasound tongue and optical lip images creates features for a continuous hidden Markov model based speech recognition system. Predictive tongue features are found to generate lower word error rates than those obtained from an auto-encoder without future frames, or from discrete cosine transforms. Improvement is apparent for the monophone/triphone Gaussian mixture model and deep neural network acoustic models. When tongue and lip modalities are combined, the advantage of the predictive features is reduced.

Speech recognition for under-resourced languages: Data sharing in hidden Markov model systems


 
 
 For purposes of automated speech recognition in under-resourced environments, techniques used to share acoustic data between closely related or similar languages become important. Donor languages with abundant resources can potentially be used to increase the recognition accuracy of speech systems developed in the resource poor target language. The assumption is that adding more data will increase the robustness of the statistical estimations captured by the acoustic models. In this study we investigated data sharing between Afrikaans and Flemish – an under-resourced and well-resourced language, respectively. Our approach was focused on the exploration of model adaptation and refinement techniques associated with hidden Markov model based speech recognition systems to improve the benefit of sharing data. Specifically, we focused on the use of currently available techniques, some possible combinations and the exact utilisation of the techniques during the acoustic model development process. Our findings show that simply using normal approaches to adaptation and refinement does not result in any benefits when adding Flemish data to the Afrikaans training pool. The only observed improvement was achieved when developing acoustic models on all available data but estimating model refinements and adaptations on the target data only.
 
 
 
 
 Significance: 
 
 
 
 Acoustic modelling for under-resourced languages
 Automatic speech recognition for Afrikaans
 Data sharing between Flemish and Afrikaans to improve acoustic modelling for Afrikaans
 
 
 

Robust speech recognition system using bidirectional Kalman filter

Kalman filter is normally used to enhance speech quality in a noisy environment, in which the speech signals are usually modelled as autoregressive (AR) process, and represented in the state-space domain. It is a known fact that to identify the changing AR coefficients in every time state requires extensive computation. In this paper, the authors develop a bidirectional Kalman filter and apply it in a speech processing system. The proposed filter uses a system dynamics model that utilises the past and the future measurements to form an estimate of the system's current time state. It provides efficient recursive means to estimate the state of a process that minimises the mean of the squared error. Compared to the conventional Kalman filter, the proposed filter reduces the computation time in two ways: (i) by avoiding the computation of AR parameters in each time state, and (ii) by reducing the dimension of the matrices involved in the difference equations and the measurement equations into constant (1 × 1) matrices. The speech recognition result shows that the developed speech recognition system becomes more robust after the proposed filtering process, and the proposed filter's low computational expense makes it applicable in the practical hidden Markov model-based speech recognition system.

A Gaussian Mixture Model Based Speech Recognition System Using Matlab

A Gaussian Mixture Model Based Speech Recognition System Using Matlab

Statistical modeling of speech Poincaré sections in combination of frequency analysis to improve speech recognition performance

This paper introduces a combinational feature extraction approach to improve speech recognition systems. The main idea is to simultaneously benefit from some features obtained from Poincaré section applied to speech reconstructed phase space (RPS) and typical Mel frequency cepstral coefficients (MFCCs) which have a proved role in speech recognition field. With an appropriate dimension, the reconstructed phase space of speech signal is assured to be topologically equivalent to the dynamics of the speech production system, and could therefore include information that may be absent in linear analysis approaches. Moreover, complicated systems such as speech production system can present cyclic and oscillatory patterns and Poincaré sections could be used as an effective tool in analysis of such trajectories. In this research, a statistical modeling approach based on Gaussian mixture models (GMMs) is applied to Poincaré sections of speech RPS. A final pruned feature set is obtained by applying an efficient feature selection approach to the combination of the parameters of the GMM model and MFCC-based features. A hidden Markov model-based speech recognition system and TIMIT speech database are used to evaluate the performance of the proposed feature set by conducting isolated and continuous speech recognition experiments. By the proposed feature set, 5.7% absolute isolated phoneme recognition improvement is obtained against only MFCC-based features.

Gaussian mixture models with covariances or precisions in shared multiple subspaces

We introduce a class of Gaussian mixture models (GMMs) in which the covariances or the precisions (inverse covariances) are restricted to lie in subspaces spanned by rank-one symmetric matrices. The rank-one basis are shared between the Gaussians according to a sharing structure. We describe an algorithm for estimating the parameters of the GMM in a maximum likelihood framework given a sharing structure. We employ these models for modeling the observations in the hidden-states of a hidden Markov model based speech recognition system. We show that this class of models provide improvement in accuracy and computational efficiency over well-known covariance modeling techniques such as classical factor analysis, shared factor analysis and maximum likelihood linear transformation based models which are special instances of this class of models. We also investigate different sharing mechanisms. We show that for the same number of parameters, modeling precisions leads to better performance when compared to modeling covariances. Modeling precisions also gives a distinct advantage in computational and memory requirements

Large vocabulary hidden markov model based speech recognition

AbstractThis paper gives an introduction to the use of Hidden Markov Models and Information Theory principles for speech recognition. The use of these techniques has led to powerful large vocabulary speech recognition systems developed in the recent years. The use of Hidden Markov Models for stochastic modeling of speech and the basic modules of a Hidden Markov Model based speech recognition system are explained. It is shown how the speech waveform can be transformed into acoustic features and into prototypes which characterize the acoustic state space of the given speaker. The phonemes of the language can be represented by Hidden Markov Models. The statistical parameters of these Markov models can be obtained during a training session. During recognition the input to the linguistic decoder is the acoustic label string resulting from the speech signal of a spoken sentence. The decoder picks the sentence which maximizes the probability of the word sequence of this sentence if the given label stream is seen. The paper concludes with a more detailed explanation of the acoustic processor of the speech recognition system and some proposed algorithms for its improvement which can lead to a better system performance.

Speech recognition using noise-adaptive prototypes

A probabilistic mixture mode is described for a frame (the short term spectrum) of speech to be used in speech recognition. Each component of the mixture is regarded as a prototype for the labeling phase of a hidden Markov model based speech recognition system. Since the ambient noise during recognition can differ from that present in the training data, the model is designed for convenient updating in changing noise. Based on the observation that the energy in a frequency band is at any fixed time dominated either by signal energy or by noise energy, the energy is modeled as the larger of the separate energies of signal and noise in the band. Statistical algorithms are given for training this as a hidden variables model. The hidden variables are the prototype identities and the separate signal and noise components. Speech recognition experiments that successfully utilize this model are described. >