Hidden Markov Model-based Speech Recognition Research Articles

Noise and Echo Aware Accurate Dysarthria Speech Recognition Model

Dysarthria speech is the speech disorder which would be caused due to weakness of human muscles. The human with dysarthria disorder cannot speak normally whose speech will be very slow and congestive words which might be more difficult to understand. Thus it is required to create the environment where the speech of dysarthria disorder people can be recognized. This is done in our previous research work by introducing the method namely Hidden Markov Model based Speech Recognition (HMMSR). However this research work didn’t focus on accurate prediction and the echo noises presence in the speech signals. This would lead to inaccuracy in speech recognition. This is resolved by introducing the efficient dysarthria speech recognition framework namely Noise and Echo aware Dysarthria Speech Recognition Method (NE-DSRM). In this research work, Hybrid Least Mean Square-Adaptive Neuro Fuzzy Inference System (LMS-ANFIS) has been used for preprocessing. This method will remove both echo and noises present in the speech signals to ensure the accurate prediction outcome. And then speech recognition is performed by comparing the dysarthria speech with the phonological speech based on which relevancy would be identified. The accuracy of speech recognition can be improved by introducing the SVM based learning methodology which can classify the dysarthria speech based on which more relevant matching can be done. The objective of the system is, after being trained, to identify and classify limited-vocabulary sets of speaker-dependent. The overall assessment of the research work is done in the matlab simulation environment from which it is proved that the proposed method NE-DSRM tends to have better performance than the existing research works.

Many-to-many voice conversion using hidden Markov model-based speech recognition and synthesis

This paper describes a many-to-many voice conversion (VC) technique that does not require a parallel training set of source and target speakers. In a previous study, we already proposed many-to-one VC method that consists of decoding and synthesis parts, and it does not require a parallel training set. The basic idea of this system is that an input utterance is recognized utilizing the hidden Markov model (HMM) for speech recognition, and the recognized phoneme sequences are used as labels for speech synthesis. The aim of this work is to extend functionality from many-to-one to many-to-many VC. In particular, we focus on the VC of emotional speech. In order to achieve this, we utilize speaker adaptation techniques to adapt HMMs for speech synthesis. By using adaptation techniques, an arbitrary speaker’s voice can be produced. In this work, a combination of constrained structural maximum a posteriori linear regression and maximum a posteriori estimation is used for adaptation. In order to evaluate the proposed system, subjective speech intelligibility tests were conducted. In the experiments, the proposed adaptation with 10 utterances was compared with traditional parameter training with 450 utterances. The results showed that speaker adaptation could be carried out without performance degradation.

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.

Adaptation mode controller using multiple signal classification for GSC‐based beamforming

A new adaptation mode control method using the multiple signal classification (MUSIC) algorithm is proposed. The MUSIC algorithm is used to calculate the spatial spectral response to the direction of the target source with noisy inputs. Then, the statistical distribution of the MUSIC output is analysed and used to model the target signal presence probability. Using the probability, the filter adaptation mode of a multiple input canceller in a generalised sidelobe canceller is controlled. For performance evaluation, hidden Markov model-based speech recognition rates are measured. The results show that the proposed algorithm notably outperforms other conventional adaptation mode controllers.

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.

Specifics of Hidden Markov Model Modifications for Large Vocabulary Continuous Speech Recognition

Specifics of hidden Markov model-based speech recognition are investigated. Influence of modeling simple and context-dependent phones, using simple Gaussian, two and three-component Gaussian mixture probability density functions for modeling feature distribution, and incorporating language model are discussed. Word recognition rates and model complexity criteria are used for evaluating suitability of these modifications for practical applications. Development of large vocabulary continuous speech recognition system using HTK toolkit and WSJCAM0 English speech corpus is described. Results of experimental investigations are presented.

Hidden Markov model-based speech recognition with intermediate wavelet transform domains

A discrete wavelet transform algorithm segregates the operand data set sequentially. It generates computational intermediates which represent it at graded resolutions and leads to a reciprocal domain within which information is multiply resolved in terms of the time-frequency localization of the component wavelet basis vectors. Based on this we introduce the concept of wavelet subtransform domains and show that these can be used to selectively enhance acoustic events in a speech signal. Enhancement of phoneme classes improves segmentation and recognition performance for reasons that we have pointed out in the paper. As an experimental verification, we use subtransform domains to design a preprocessor for a Hindi database and evaluate the subsequent recognition performances using hidden Markov models and two standard parametrizations.

Analysis of parallel genetic algorithms on HMM based speech recognition system

A hidden Markov model (HMM) is a natural and highly robust statistical method for automatic speech recognition. It has been tested and proved effective in a wide range of applications. The HMM model parameters are used to describe the utterance of the speech segment presented by the HMM. Many successful heuristic algorithms are developed to optimize the model parameters to best describe the training observation sequences. However, all these methods are exploring for only one local maximum in practice. No single method can be recovered from the local maximum and to obtain the global maximum or other more optimized local maxima. In this paper, a stochastic search method called the genetic algorithm (GA) is presented for HMM training. GA mimics natural evolution and performs searching within the defined searching space. Experimental results showed that using GA for HMM training (GA-HMM training) can obtain better solutions than using heuristic algorithms. One of the major drawbacks is that GAs require a lot of computation power for global searching before it can converge. Therefore, in order to outperform heuristic algorithms, a parallel version of GA called the parallel genetic algorithm (PGA) is introduced. Experimental results showed that using PGA in speech recognition systems provides 18% improvement in recognition rate with the same amount of computational time.