Automatic speech recognition by using local adaptive thresholding in continuous speech segmentation

<p>Continuous speech is a form of natural human speech that is continuous without a clear boundary between words. In continuous speech recognition, a segmentation process is needed to cut the sentence at the boundary of each word. Segmentation becomes an important step because a speech can be recognized from the word segments produced by this process. The segmentation process in this study was carried out using local adaptive thresholding technique in the blocking block area method. This study aims to conduct performance comparisons for five local adaptive thresholding methods (Niblack, Sauvola, Bradley, Guanglei Xiong and Bernsen) in continuous speech segmentation to obtain the best method and optimum parameter values. Based on the results of the study, Niblack method is concluded as the best method for continuous speech segmentation in Indonesian language with the accuracy value of 95%, and the optimum parameter values for such method are window = 75 and k = 0.2.</p>

Speech recognition can be defined as the process of converting voice signals into the ranks of the word, by applying a specific algorithm that is implemented in a computer program. The research of speech recognition in Indonesia is relatively limited. This paper has studied methods of feature extraction which is the best among the Linear Predictive Coding (LPC) and Mel Frequency Cepstral Coefficients (MFCC) for speech recognition in Indonesian language. This is important because the method can produce a high accuracy for a particular language does not necessarily produce the same accuracy for other languages, considering every language has different characteristics. Thus this research hopefully can help further accelerate the use of automatic speech recognition for Indonesian language. There are two main processes in speech recognition, feature extraction and recognition. The method used for comparison feature extraction in this study is the LPC and MFCC, while the method of recognition using Hidden Markov Model (HMM). The test results showed that the LPC method is better than MFCC in Indonesian language speech recognition.

A statistically designed Automatic Speech Recognition (ASR) system extracts features from speech signals using feature extraction methods, links the extracted features with the expected phonetics of the hypothesis using acoustic models, uses language model to add prior information about the structure of the target language. For many years, Mel-frequency Cepstral coefficients (MFCC), n-gram, and Hidden Markov Model (HMM) approaches have been used predominantly for feature extraction, language modeling and acoustic modeling, respectively. However, performance degradation of MFCC in noisy conditions and inaccuracy of HMMs while handling large vocabularies have made researchers to propose more efficient methods. The proposed work uses noise robust method Gammatone Frequency Cepstral Coefficients(GFCC) for feature extraction, trigram language modeling, and HMM-Gaussian mixture model (GMM) based acoustic modeling to implement a continuous Hindi language ASR system. Also, it applies Differential Evolution (DE) technique to refine the GFCC features and discriminative techniques to enhance performance of the acoustic model. The performance of the implemented system has been evaluated by using different feature extraction methods, variants of n-gram language modeling techniques and different discriminative techniques in clean as well as noisy conditions. Initially, the results reveal that DE optimized GFCC with HMM-Gaussian Mixture Model (GMM) acoustic modeling performs better than MFCC, PLP and MF-PLP feature extraction methods. Secondly, the experimental results show that the Minimum Phone Error (MPE) outperforms Maximum Mutual Information (MMI) and Maximum Likelihood Estimation (MLE) and trigram based language modeling gives more accurate results than unigram and bigram language modeling. Finally, it has been concluded that the continuous Hindi language ASR system implemented using DE refined GFFC feature extraction method with MPE discriminative training technique and trigram based language modeling gives better accuracy in clean as-well-as noisy environments.

Automatic speech recognition (ASR) has been extensively studied during the past few decades. Today, most of the ASR system based on statistical modelling, and HMM is the most popular one among them. Now days, performance of ASR become one of the major bottleneck for its practical use. Literature of ASR shows that optimal performance could be achieved by using Gaussian mixture hidden Markov model (HMM) but choice of Gaussian mixture is arbitrary with little justification. If we use the different number of Gaussian Mixture then we get different results. In this paper, we compare the performance of continuous Hindi speech recognition by using different number of Gaussian mixture. The aim of this paper is to investigate the optimal number of Gaussian mixture that exhibits maximum accuracy in the context of Hindi speech recognition. HMM toolkit HTK 3.4.1 is used for the implementation of this system, in which Mel frequency cepstral coefficient (MFCC) is used as a feature extraction technique. The experimental results show that the maximum performance of the proposed system is achieved when we use four component Gaussian mixtures HMM model.

Speech production knowledge has been used to enhance the phonetic representation and the performance of automatic speech recognition (ASR) systems successfully. Representations of speech production make simple explanations for many phenomena observed in speech. These phenomena can not be easily analyzed from either acoustic signal or phonetic transcription alone. One of the most important aspects of speech production knowledge is the use of articulatory knowledge, which describes the smooth and continuous movements in the vocal tract. In this paper, we present a new articulatory model to provide available information for rescoring the speech recognition lattice hypothesis. The articulatory model consists of a feature front-end, which computes a voicing feature based on a spectral harmonics correlation (SHC) function, and a back-end based on the combination of deep neural networks (DNNs) and hidden Markov models (HMMs). The voicing features are incorporated with standard Mel frequency cepstral coefficients (MFCCs) using heteroscedastic linear discriminant analysis (HLDA) to compensate the speech recognition accuracy rates. Moreover, the advantages of two different models are taken into account by the algorithm, which retains deep learning properties of DNNs, while modeling the articulatory context powerfully through HMMs. Mandarin speech recognition experiments show the proposed method achieves significant improvements in speech recognition performance over the system using MFCCs alone.

This paper aims to design and implement English digits speech recognition system using Matlab (GUI). This work was based on the Hidden Markov Model (HMM), which provides a highly reliable way for recognizing speech. The system is able to recognize the speech waveform by translating the speech waveform into a set of feature vectors using Mel Frequency Cepstral Coefficients (MFCC) technique This paper focuses on all English digits from (Zero through Nine), which is based on isolated words structure. Two modules were developed, namely the isolated words speech recognition and the continuous speech recognition. Both modules were tested in both clean and noisy environments and showed a successful recognition rates. In clean environment and isolated words speech recognition module, the multi-speaker mode achieved 99.5% whereas the speaker-independent mode achieved 79.5%. In clean environment and continuous speech recognition module, the multi-speaker mode achieved 72.5% whereas the speaker-independent mode achieved 56.25%. However in noisy environment and isolated words speech recognition module, the multi-speaker mode achieved 88% whereas the speaker-independent mode achieved 67%. In noisy environment and continuous speech recognition module, the multi-speaker mode achieved 82.5% whereas the speaker-independent mode achieved 76.67%. These recognition rates are relatively successful if compared to similar systems.

Thresholding is a simple and effective technique for image segmentation. Thresholding techniques can be grouped into two categories, global thresholding and local thresholding. All local threshold method generally begins with determining thresholds in each pixel by checking the area centered on the pixel, using a box shape (x, y) which is fixed by the size of the neighborhood b. If the neighborhood is very small, then the algorithm will be sensitive to noise and excessive segmentation occurs. Whereas, if the size of the neighborhood is very large then the algorithm will apply resemble the global threshold method. In this study, we propose a method of calculation of Local Adaptive Region, to determine the value of each pixel that is flexible neighborhoods, where each pixel has values different neighborhoods based on the value of the standard deviation region. Adaptive method on the local region thresholding consists of several processes, namely: Image Enhancement, Adaptive Local Region and thresholding. Based on evaluation of ME, image result of threshold using the Adaptive Local Region method, giving an average ME smallest value, that is 16.99% at Niblack method and 19.46% at Sauvola method. And on evaluation of the RAE, image result of threshold using the Adaptive Local Region method, giving an average RAE smallest value, that is 15.26% at Niblack method and 25.58% at Sauvola method. In addition, the results of trials with various noise variance represent that the method of Adaptive Local Region resistant to noise.

Performance evaluation of Hindi speech recognition system using optimized filterbanks

In this dissertation, a novel approach of integrating template matching with statistical modeling is proposed to improve continuous speech recognition. Hidden Markov Modeling (HMMs) has been the dominant approach in statistical speech recognition since it provides a principled way of jointly modeling speech spectral variations and time dynamics. However, HMMs have the shortcoming of assuming the observations being independent within each state, which makes it ineffective in modeling the details of speech temporal evolutions that are important for characterizing nonstationary speech sounds. Template-based methods make comparisons between a test pattern and the templates derived from training data, and therefore they are able to capture speech dynamics and time correlation of speech frames better than HMM based methods. However, template matching requires large memory space and computational time since feature vectors of training data need to be stored in computer memory for access at the recognition stage, which is difficult in large vocabulary continuous speech recognition (LVCSR). Our proposed approach takes advantages of both statistical modeling and template matching, which overcomes the weakness of conventional template-based method and is feasible for LVCSR. We use multiple Gaussian Mixture Model (GMM) indices to represent each frame of speech templates, and define the template unit to be context-dependent phone segments (triphone context). We also use phonetic decision trees borrowed from those commonly used in HMMs to tie triphone templates and predict triphones unseen in training data. Two local distances, log likelihood ratio (LLR) and Kullback-Leibler (KL) divergence, are proposed for dynamic time warping (DTW) based template matching. In order to reduce computational complexity and storage space, we propose methods of minimum distance template selection (MDTS) and maximum log-likelihood template selection (MLTS), and investigate a template compression method on top of template selection to further improve recognition performance. The template based methods were used to rescore lattices generated by baseline HMMs on the tasks of TIMIT continuous phone recognition and teleheath LVCSR and experimental results demonstrated that the proposed approach of integrating template matching with statistical modeling significantly improved recognition performances over the HMM baselines. The template selection methods also provided significant recognition accuracy improvements over the HMM baseline while largely reducing the computation and storage complexities. When all templates or MDTS were used, using the LLR local distance obtained better recognition performance than the KL divergence local distance. For MLTS and template compression, KL divergence local distance provided better performance than the LLR local distance, and the template compression method made further improvements over KL based MLTS. Since the templates were constructed based on the GMM indices extracted from HMM baselines, we also validated the effectiveness of the proposed template methods based on enhanced HMM baselines. Experimental results showed that LLR based all template method was able to consistently improve TIMIT phone recognition accuracies based on four enhanced HMM baselines. Prosodic features such as duration, energy, and pitch can reflect longer span information of speech than conventional single frame vectors but they have commonly been ignored by HMMs. Template based methods provide possibilities to conveniently integrate prosodic features into speech recognition, which has not been well studied in the past. In this dissertation, we investigate combining template based methods with the speech prosodic features of duration, energy and pitch to further improve speech recognition accuracy. The scores of prosodic information were computed by a GMM based method and a non-parametric method, and the prosodic scores were combined with the acoustic scores in triphone template matching. Experimental results obtained on the telehealth task showed that prosodic information had positive effects on vowel sound recognition.

This paper proposes a new model for a noise-robust Automatic Speech Recognition (ASR) based on parallel branch Hidden Markov Model (HMM) structure with a novel approach for robust speech recognition. Automatic Speech Recognition applications such as voice command and control, audio indexing, speech-to-speech translation, do not usually work well in noisy environments. In this paper, we present the characteristics of a novel model by exploring vibrocervigraphic and electromyographic ASR methods and some other effective approaches to achieve the best results. By employing the proposed model, we obtain the word error rate, available bandwidths with cutoff frequencies, word recognition rate, etc. This paper includes advanced front-end processing with less computational requirements and a statistical modeling for large-vocabulary myoelectric speech. Therefore parameters estimation of ASR system like Mel-Frequency Cepstral Coefficients (MFCC) are investigated to create the statistically optimized model.

In recent years, speech processing resides a major application in the domain of signal processing. Due to the audibility loss of some speech signals, people with hearing impairment have difficulty in understanding speech, which reintroduces a crucial role in speech recognition. Automatic Speech Recognition (ASR) development is a major challenge in research in the case of noise, domain, vocabulary size, and language and speaker variability. Speech recognition system design needs careful attention to challenges or issues like performance and database evaluation, feature extraction methods, speech representations and speech classes. In this paper, HDF-DNN model has been proposed with the hybridization of discriminant fuzzy function and deep neural network for speech recognition. Initially, the speech signals are pre-processed to eliminate the unwanted noise and the features are extracted using Mel Frequency Cepstral Coefficient (MFCC). A hybrid Deep Neural Network and Discriminant Fuzzy Logic is used for assisting hearing-impaired listeners with enhanced speech intelligibility. Both DNN and DF have some problems with parameters to address this problem, Enhanced Modularity function-based Bat Algorithm (EMBA) is used as a powerful optimization tool. The experimental results show that the proposed automatic speech recognition-based hybrid deep learning model is effectively-identifies speech recognition more than the MFCC-CNN, CSVM and Deep auto encoder techniques. The proposed method improves the overall accuracy of 8.31%, 9.71% and 10.25% better than, MFCC-CNN, CSVM and Deep auto encoder respectively.

This chapter presents Bangla (widely known as Bengali) Automatic Speech Recognition (ASR) techniques by evaluating the different speech features, such as Mel Frequency Cepstral Coefficients (MFCCs), Local Features (LFs), phoneme probabilities extracted by time delay artificial neural networks of different architectures. Moreover, canonicalization of speech features is also performed for Gender-Independent (GI) ASR. In the canonicalization process, the authors have designed three classifiers by male, female, and GI speakers, and extracted the output probabilities from these classifiers for measuring the maximum. The maximization of output probabilities for each speech file provides higher correctness and accuracies for GI speech recognition. Besides, dynamic parameters (velocity and acceleration coefficients) are also used in the experiments for obtaining higher accuracy in phoneme recognition. From the experiments, it is also shown that dynamic parameters with hybrid features also increase the phoneme recognition performance in a certain extent. These parameters not only increase the accuracy of the ASR system, but also reduce the computation complexity of Hidden Markov Model (HMM)-based classifiers with fewer mixture components.

This paper addresses the development of an Automatic Speech Recognition (ASR) system for the Moroccan Dialect. Dialectal Arabic (DA) refers to the day-to-day vernaculars spoken in the Arab world. In fact, Moroccan Dialect is very different from the Modern Standard Arabic (MSA) because it is highly influenced by the French Language. It is observed throughout all Arab countries that standard Arabic widely written and used for official speech, news papers, public administration and school but not used in everyday conversation and dialect is widely spoken in everyday life but almost never written. we propose to use the Mel Frequency Cepstral Coefficient (MFCC) features to specify the best speaker identification system. The extracted speech features are quantized to a number of centroids using vector quantization algorithm. These centroids constitute the codebook of that speaker. MFCC’s are calculated in training phase and again in testing phase. Speakers uttered same words once in a training session and once in a testing session later. The Euclidean distance between the MFCC’s of each speaker in training phase to the centroids of individual speaker in testing phase is measured and the speaker is identified according to the minimum Euclidean distance. The code is developed in the MATLAB environment and performs the identification satisfactorily.

Inherent features of the Bangla (widely used as Bengali) language like long and short vowels and many instances of allophones make it difficult to build a continuous speech recognizer for the language. Stress and accent vary in spoken Bangla language from region to region. But in formal read Bangla speech, stress and accents are ignored. There are three approaches to continuous speech recognition (CSR) based on the sub-word unit viz. word, phoneme and syllable. Pronunciation of words and sentences are strictly governed by set of linguistic rules. Many attempts have been made to build continuous speech recognizers for Bangla for small and restricted tasks. However, medium and large vocabulary CSR for Bangla is relatively new and not explored. In this paper, the authors have attempted for extracting local features (LFs) from a Bangla input speech for tri-phone based automatic speech recognition (ASR) method. The method comprises two stages, where the first stage extracts LFs from input speech and the final stage generates word strings based on trip hone hidden Markov models (HMMs). The objective of this research is to build a medium vocabulary trip hone based continuous speech recognizer for Bangla language by extracting LFs over mel frequency cepstral coefficients (MFCCs). In this experimentation using Bangla speech corpus prepared by us, the recognizer provides higher word accuracy, word correct rate as well as sentence correct rate for trained and tested sentences with fewer mixture components in HMMs.

This work addresses the problem of lung sound classification, in particular, the problem of distinguishing between wheeze and normal sounds. Wheezing sound detection is an important step to associate lung sounds with an abnormal state of the respiratory system, usually associated with tuberculosis or another chronic obstructive pulmonary diseases (COPD). The paper presents an approach for automatic lung sound classification, which uses different state-of-the-art sound features in combination with a C-weighted support vector machine (SVM) classifier that works better for unbalanced data. Feature extraction methods used here are commonly applied in speech recognition and related problems thanks to the fact that they capture the most informative spectral content from the original signals. The evaluated methods were: Fourier transform (FT), wavelet decomposition using Wavelet Packet Transform bank of filters (WPT) and Mel Frequency Cepstral Coefficients (MFCC). For comparison, we evaluated and contrasted the proposed approach against previous works using different combination of features and/or classifiers. The different methods were evaluated on a set of lung sounds including normal and wheezing sounds. A leave-two-out per-case cross-validation approach was used, which, in each fold, chooses as validation set a couple of cases, one including normal sounds and the other including wheezing sounds. Experimental results were reported in terms of traditional classification performance measures: sensitivity, specificity and balanced accuracy. Our best results using the suggested approach, C-weighted SVM and MFCC, achieve a 82.1% of balanced accuracy obtaining the best result for this problem until now. These results suggest that supervised classifiers based on kernel methods are able to learn better models for this challenging classification problem even using the same feature extraction methods.