Hybrid Hidden Markov Model Research Articles

Hybrid HMM Decoder for Convolutional Codes by Joint Trellis-Like Structure and Channel Prior

The anti-interference capability of wireless links is a physical layer problem for edge computing. Although convolutional codes have inherent error correction potential due to the redundancy introduced in the data, the performance of the convolutional code is drastically degraded due to multipath effects on the channel. In this paper, we propose the use of a Hidden Markov Model (HMM) for the reconstruction of convolutional codes and decoding by the Viterbi algorithm. Furthermore, to implement soft-decision decoding, the observation of HMM is replaced by Gaussian mixture models (GMM). Our method provides superior error correction potential than the standard method because the model parameters contain channel state information (CSI). We evaluated the performance of the method compared to standard Viterbi decoding by numerical simulation. In the multipath channel, the hybrid HMM decoder can achieve a performance gain of 4.7 dB and 2 dB when using hard-decision and soft-decision decoding, respectively. The HMM decoder also achieves significant performance gains for the RSC code, suggesting that the method could be extended to turbo codes.

A Hybrid Hidden Markov Model and Time-Frequency Approach to Impact Echo Signal Classification

A Hybrid Hidden Markov Model and Time-Frequency Approach to Impact Echo Signal Classification

Lipstick color suggested using hybrid hidden Markov model

In today’s lifestyle, facial makeup plays an important role in enhancing visual attractiveness a nd boosting one’s self-esteem. Makeup is known as the second skin of the women, and that too lipstick is a soul of the makeup. According to a survey, an average urban woman spends almost one year and three months of her life just wearing makeup. This much of the time is due to decision-making and choosing the best makeup style that would fit a particular age, skin complexion, profession, and occasion, requiring high imagination and full art. Many makeup recommendations systems exist, but no solitary system has existed to recommend a lipstick color properly to solve this problem computationally. Therefore, as a tiny step towards helping women save their time in decision-making, the proposed model puts forward an idea of a hybrid recommendation model for lipsticks alone. This proposed methodology uses a hidden Markov model to unleash the possible color of the lipsticks based on the given attributes. The collaborative filtering system catalyzes the process to recommend the best lipstick colors using a hybrid recommendation model.

Application of HMM and Ensemble Learning in Intelligent Tunneling

The cutterhead torque and thrust, reflecting the obstruction degree of the geological environment and the behavior of excavation, are the key operating parameters for the tunneling of tunnel boring machines (TBMs). In this paper, a hybrid hidden Markov model (HMM) combined with ensemble learning is proposed to predict the value intervals of the cutterhead torque and thrust based on the historical tunneling data. First, the target variables are encoded into discrete states by means of HMM. Then, ensemble learning models including AdaBoost, random forest (RF), and extreme random tree (ERT) are employed to predict the discrete states. On this basis, the performances of those models are compared under different forms of the same input parameters. Moreover, to further validate the effectiveness and superiority of the proposed method, two excavation datasets including Beijing and Zhengzhou from the actual project under different geological conditions are utilized for comparison. The results show that the ERT outperforms the other models and the corresponding prediction accuracies are up to 0.93 and 0.99 for the cutterhead torque and thrust, respectively. Therefore, the ERT combined with HMM can be used as a valuable prediction tool for predicting the cutterhead torque and thrust, which is of positive significance to alert the operator to judge whether the excavation is normal and assist the intelligent tunneling.

A Hybrid Hidden Markov Model for Pipeline Leakage Detection

In this paper, a deep neural network hidden Markov model (DNN-HMM) is proposed to detect pipeline leakage location. A long pipeline is divided into several sections and the leakage occurs in different section that is defined as different state of hidden Markov model (HMM). The hybrid HMM, i.e., DNN-HMM, consists of a deep neural network (DNN) with multiple layers to exploit the non-linear data. The DNN is initialized by using a deep belief network (DBN). The DBN is a pre-trained model built by stacking top-down restricted Boltzmann machines (RBM) that compute the emission probabilities for the HMM instead of Gaussian mixture model (GMM). Two comparative studies based on different numbers of states using Gaussian mixture model-hidden Markov model (GMM-HMM) and DNN-HMM are performed. The accuracy of the testing performance between detected state sequence and actual state sequence is measured by micro F1 score. The micro F1 score approaches 0.94 for GMM-HMM method and it is close to 0.95 for DNN-HMM method when the pipeline is divided into three sections. In the experiment that divides the pipeline as five sections, the micro F1 score for GMM-HMM is 0.69, while it approaches 0.96 with DNN-HMM method. The results demonstrate that the DNN-HMM can learn a better model of non-linear data and achieve better performance compared to GMM-HMM method.

Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview

We present a structured overview of adaptation algorithms for neural network-based speech recognition, considering both hybrid hidden Markov model / neural network systems and end-to-end neural network systems, with a focus on speaker adaptation, domain adaptation, and accent adaptation. The overview characterizes adaptation algorithms as based on embeddings, model parameter adaptation, or data augmentation. We present a meta-analysis of the performance of speech recognition adaptation algorithms, based on relative error rate reductions as reported in the literature.

Speaker Adaptation Using i-Vector Based Clustering

We propose a novel speaker adaptation method using acoustic model clustering. The similarity of different speakers is defined by the cosine distance between their i-vectors (intermediate vectors), and various efficient clustering algorithms are applied to obtain a number of speaker subsets with different characteristics. The speaker-independent model is then retrained with the training data of the individual speaker subsets grouped by the clustering results, and an unknown speech is recognized by the retrained model of the closest cluster. The proposed method is applied to a large-scale speech recognition system implemented by a hybrid hidden Markov model and deep neural network framework. An experiment was conducted to evaluate the word error rates using Resource Management database. When the proposed speaker adaptation method using i-vector based clustering was applied, the performance, as compared to that of the conventional speaker-independent speech recognition model, was improved relatively by as much as 12.2% for the conventional fully neural network, and by as much as 10.5% for the bidirectional long short-term memory.

Improving Low-Resource Speech Recognition Based on Improved NN-HMM Structures

The performance of the ASR system is unsatisfactory in a low-resource environment. In this paper, we investigated the effectiveness of three approaches to improve the performance of the acoustic models in low-resource environments. They are Mono-and-triphone Learning, Soft One-hot Label and Feature Combinations. We applied these three methods to the network architecture and compared their results with baselines. Our proposal has achieved remarkable improvement in the task of mandarin speech recognition in the hybrid hidden Markov model - neural network approach on phoneme level. In order to verify the generalization ability of our proposed method, we conducted many comparative experiments on DNN, RNN, LSTM and other network structures. The experimental results show that our method is applicable to almost all currently widely used network structures. Compared to baselines, our proposals achieved an average relative Character Error Rate (CER) reduction of 8.0%. In our experiments, the size of training data is ~10 hours, and we did not use data augmentation or transfer learning methods, which means that we did not use any additional data.

Hybrid hidden Markov models and artificial neural networks for handwritten music recognition in mensural notation

In this paper, we present a hybrid approach using hidden Markov models (HMM) and artificial neural networks to deal with the task of handwritten Music Recognition in mensural notation. Previous works have shown that the task can be addressed with Gaussian density HMMs that can be trained and used in an end-to-end manner, that is, without prior segmentation of the symbols. However, the results achieved using that approach are not sufficiently accurate to be useful in practice. In this work, we hybridize HMMs with deep multilayer perceptrons (MLPs), which lead to remarkable improvements in optical symbol modeling. Moreover, this hybrid architecture maintains important advantages of HMMs such as the ability to properly model variable-length symbol sequences through segmentation-free training, and the simplicity and robustness of combining optical models with N-gram language models, which provide statistical a priori information about regularities in musical symbol concatenation observed in the training data. The results obtained with the proposed hybrid MLP-HMM approach outperform previous works by a wide margin, achieving symbol-level error rates around 26%, as compared with about 40% reported in previous works.

Hybrid deep convolutional neural network and hidden Markov model for automatic seizure detection from long-term scalp EEG

Hybrid deep convolutional neural network and hidden Markov model for automatic seizure detection from long-term scalp EEG

Analysis of Handwritten Text Recognition System using EDAS Method

The recognition of sloppy handwriting for Using hybrid Hidden Markov Model (HMM)/Artificial Neural Network (ANN) models This article proposes that Text Recognition System. A single-valued complex neutrosophic EDAS (estimation based on distance from average temptation) model was established and used in green supplier selection. First, the definition and relatedness of a single-valued complex neutrosophic set Functional laws are briefly introduced. The handwritten text recognition system, Integration of Fuzzy AHP and Estimation Based on Distance from Average Solution (EDAS) presented a new unified model, in which Fuzzy AHP is used to calculate the priority weight of each criterion and is EDAS. Handwritten Text Recognition System was used to arrive at the final ranking. The alternatives are B-HTR, LM-HTR, ALIGN-HTR, HMM, EMAC, LSTM, MDLSTM, BLSTM and GMM. Evaluation parameter is WER and CER. The Handwritten Text Recognition System using EDAS method final result is given to by first rank is EMAC and LSTM is lowest rank.

A hybrid HMM model for travel path inference with sparse GPS samples

In this study, we propose a novel method for a travel path inference problem from sparse GPS trajectory data. This problem involves localization of GPS samples on a road network and reconstruction of the path that a driver might have been following from a low rate of sampled GPS observations. Particularly, we model travel path inference as an optimization problem in both the spatial and temporal domains and propose a novel hybrid hidden Markov model (HMM) that uses a uniform cost search (UCS)-like novel combinational algorithm. We provide the following improvements over the previous studies that use HMM-based methods: (1) for travel path inference between matched GPS positions, the proposed hybrid HMM algorithm evaluates all candidate paths to find the most likely path for both the temporal and spatial domains. In contrast, previous studies either create interpolated trajectories or connect matched GPS positions using the shortest path assumption, which might not be true, especially in urban road networks (Goh et al. 2012; Lou et al. 2009). (2) The proposed algorithm uses legal speed limits for the evaluation of discrepancy in the temporal domain as in Goh et al. (2012), and Lou et al. (2009) only if there is not sufficient historical average speed data; otherwise, we use historical average speed computed from data. Our experiments with real datasets show that our algorithm performs better than the state of the art VTrack algorithm (Thiagarajan et al. 2009), especially for cases where GPS data is sampled infrequently.

Automatic Speech Segmentation Using Hybrid Wavelet Features and HMM

In this research, a novel feature set is used to automatically segment speech signal. Automatic segmentation is veryuseful especially for large database. A hybrid features model is created from wavelet packet analysis and mel-scale is used to train Hidden Markov Model (HMM) for phone boundary detection. HMM is implemented using the Hidden Markov Model Toolkit (HTK).The database (Ked-TIMIT) is used for result verifications and Mel Frequency Cepstral Coefficients (MFCC) is used as reference for evaluating the results of the proposed Hybrid model. The results are categorized for vowels, consonants and short phones. Phone duration and start location are used as metrics to evaluate the system success rate. Success rate of 74% is achieved for consonant detection, 72% for vowel detection and 58% for short phone detection. Using the simple metric that relies only on boundary locations but ignoring duration, the achieved results are 92.5% for consonant detection, 90% for vowel detection and 77.5% for short phoneme detection. In addition to boundary detection the proposed hybrid model is utilized to compare newly developed features called Mel scale Best Tree Encoding (Mel-BTE ) to the mostly used popular features MFCC along with all experiments using the same database. The relative results for Mel-BTE with respect to MFCC are 94.77% for consonant detection, 87.5% for vowel detection and 93.33% for short phoneme detection.

A hybrid hidden Markov model towards fault detection of rotating components

A robust hybrid hidden Markov model-based fault detection method is proposed to perform multi-state fault classification of rotating components. The approach presented in this paper enhances the performance of the standard hidden Markov model (HMM) for fault detection by performing a series of pre-processing steps. First, the de-noised time-scale signatures are extracted using wavelet packet decomposition of the vibration data. Subsequently, the Teager Kaiser energy operator is employed to demodulate the time-scale components of the raw vibration signatures, following which the condition indicators are calculated. Out of several possible condition indicators, only relevant features are selected using a decision tree. This pre-processing improves the sensitivity of condition indicators under multiple faults. A Gaussian mixing model-based hidden Markov model (HMM) is then employed for fault detection. The proposed hybrid HMM is an improvement over traditional HMM in that it achieves better separation of the feature space leading to more robust state estimation under multiple fault states and measurement noise scenarios. A simulation employing modulated signals and two experimental validation studies are presented to demonstrate the performance of the proposed method.

Multi-scale hybrid HMM for tool wear condition monitoring

In a machining system, accurate tool wear condition monitoring is paramount for guaranteeing the quality of the workpiece and tool life. Cutting force signal is the most commonly used signal to depict the tool wear variation during the machining process. In this paper, a novel approach for tool wear condition monitoring is proposed, which is based on the multi-scale hybrid hidden Markov model (HHMM) analysis of cutting force signal. The proposed approach captures the deeply mined information of tool wear states and holds an accurate tool wear value monitoring performance from both local and global analyses point of view. The local model deals with the wavelet coefficients of cutting force in different frequencies as a cross-twist Markov depended structure within instant time resolution, which reflects the tool wear state feature from frequency dimension. The global model depicts the long time dynamical degradation of tool wear condition combined with the local model as a composite structure. Experimental studies on CNC turning of nickel alloy, Inconel 718, show that the proposed HHMM approach is efficient in tool wear monitoring and outperforms the single hidden Markov model (HMM).

RETRACTED: Hybrid Hidden Markov Models and Neural Networks Based on Face Recognition

Retracted paper: In this paper, the basic principles of HMM, HMM studied three major issues need to be addressed as well as overflow problems in the practical application of how to solve the HMM. Because artificial neural network (ANN) with anti-noise, adaptive, learning ability, recognition speed, etc., taking into account the characteristics of the common features of speech recognition and pattern recognition and artificial neural networks have, this article will get a mixed combination of HMM in ANN model, using ANN to make up for some deficiencies of HMM. Experiments show that the hybrid model recognition rate than the HMM model increased by 4%, but the algorithm still has many defects to be resolved.

Neural network language models for off-line handwriting recognition

Unconstrained off-line continuous handwritten text recognition is a very challenging task which has been recently addressed by different promising techniques. This work presents our latest contribution to this task, integrating neural network language models in the decoding process of three state-of-the-art systems: one based on bidirectional recurrent neural networks, another based on hybrid hidden Markov models and, finally, a combination of both. Experimental results obtained on the IAM off-line database demonstrate that consistent word error rate reductions can be achieved with neural network language models when compared with statistical N-gram language models on the three tested systems. The best word error rate, 16.1%, reported with ROVER combination of systems using neural network language models significantly outperforms current benchmark results for the IAM database.

Improving Offline Handwritten Text Recognition with Hybrid HMM/ANN Models

This paper proposes the use of hybrid Hidden Markov Model (HMM)/Artificial Neural Network (ANN) models for recognizing unconstrained offline handwritten texts. The structural part of the optical models has been modeled with Markov chains, and a Multilayer Perceptron is used to estimate the emission probabilities. This paper also presents new techniques to remove slope and slant from handwritten text and to normalize the size of text images with supervised learning methods. Slope correction and size normalization are achieved by classifying local extrema of text contours with Multilayer Perceptrons. Slant is also removed in a nonuniform way by using Artificial Neural Networks. Experiments have been conducted on offline handwritten text lines from the IAM database, and the recognition rates achieved, in comparison to the ones reported in the literature, are among the best for the same task.

Malay Language Speech Recogniser with Hybrid Hidden Markov Model and Artificial Neural Network(HMM/ANN)

There are many artificial intelligence approaches used in the development of Automatic Speech Recognition (ASR), and hybrid approach is one of them. The common hybrid method in speech recognition is the combination of Hidden Markov Model (HMM) and Artificial Neural Network (ANN). The hybrid HMM/ANN is able to combine the strength of HMM in sequential modeling structure and ANN in pattern classification. Thus, this paper proposed a speaker independent and continuous Malay language speech recogniser by using the hybrid HMM/ANN method. In addition to that, this paper presents a study on Standard Malay's phonetic and phonology to help in the recognition of Malay words. The CSLU toolkit is utilized for building the recogniser, and the experimental results showed that the proposed HMM/ANN model outperformed the conventional HMM model. The performances of the recognisers are measured in term of word accuracy and sentence accuracy.

Breast-Cancer identification using HMM-fuzzy approach

This paper presents an ensemble of feature selection and classification technique for classifying two types of breast lesion, benign and malignant. Features are selected based on their area under the ROC curves (AUC) which are then classified using a hybrid hidden Markov model (HMM)-fuzzy approach. HMM generated log-likelihood values are used to generate minimized fuzzy rules which are further optimized using gradient descent algorithms in order to enhance classification performance. The developed model is applied to Wisconsin breast cancer dataset to test its performance. The results indicate that a combination of selected features and the HMM-fuzzy approach can classify effectively the lesion types using only two fuzzy rules. Our experimental results also indicate that the proposed model can produce better classification accuracy when compared to most other computational tools.