Building a System for Arabic Dialects Identification based on Speech Recognition using Hidden Markov Models (HMMs)

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.

A model-based framework of classification error rate estimation is proposed for speech and speaker recognition. It aims at predicting the run-time performance of a hidden Markov model (HMM) based recognition system for a given task vocabulary and grammar without the need of running recognition experiments using a separate set of testing samples. This is highly desirable both in theory and in practice. However, the error rate expression in HMM-based speech recognition systems has no closed form solution due to the complexity of the multi-class comparison process and the need for dynamic time warping to handle various speech patterns. To alleviate the difficulty, we propose a one-dimensional model-based misclassification measure to evaluate the distance between a particular model of interest and a combination of many of its competing models. The error rate for a class characterized by the HMM is then the value of a smoothed zero-one error function given the misclassification measure. The overall error rate of the task vocabulary could then be computed as a function of all the available class error rates. The key here is to evaluate the misclassification measure in terms of the parameters of environmental-matched models without running recognition experiments, where the models are adapted by very limited data that could be just the testing utterance itself. In this paper, we show how the misclassification measure could be approximated by first computing the distance between two mixture Gaussian densities, then between two HMMs with mixture Gaussian state observation densities and finally between two sequences of HMMs. The misclassification measure is then converted into classification error rate. When comparing the error rate obtained in running actual experiments and that of the new framework, the proposed algorithm accurately estimates the classification error rate for many types of speech and speaker recognition problems. Based on the same framework, it is also demonstrated that the error rate of a recognition system in a noisy environment could also be predicted.

Arabic language can be used by native and non- native speakers; due to Arabic is the language of the holy book of Muslims. In this paper, Arabic phoneme recognition system is proposed based on Malay speakers. This system consists of three main stages. The first stage is noise reduction and it aims to enhance the phoneme signals by excluding the unvoiced signals and keep only the voiced signal. Wiener filter is adapted to accomplish this task. The second stage is based on Mel-Frequency Cepstral Coefficients method to extract a vector of features to represent each phoneme signal. Eventually, pattern recognition neural network is designed as recognizer. The proposed system produces sufficient outcomes with 20 hidden neurons. Keywords—Arabic; Malay; pattern recognition; Wiener; Mel- Frequency Cepstral Coefficients I. INTRODUCTION It is well known the wide range of Artificial Neural Networks (ANN) application in speech recognition, financial, telecommunications, electronics and medical. As for speech recognition system for Arabic language, (1) & (2) have addressed the implementation of recognition system based on Arabic native speakers. In general, neural networks (NNs) for phonemes recognition are divided into several categories for instance Very Large Scale Integration (VLSI) NN that can be divided into digital and analogue with digital NNs being more compatible with feed-forward neural networks while analogue NNs are found to be more successful with recurrent NNs (3). From Automatic Speech System (ASR) point of view, NNs for recognition purpose can be divided into two main category namely conventional neural networks such as Multilayer Perceptron (MLP) and Radial Basis Function (RBF) and secondly Recurrent Neural Networks (RNN). The first category of NNs was implemented as pattern classifiers and proven capable for recognition purpose but not at par as compared to Hidden Markov Model (HMM) performance (2). At present, HMM has been proven to be the most successful approach in ASR research area until recently the possibility to hybrid both HMM and ANN (4) & (5). In general, speech recognition systems consist of three stages specifically noise reduction, feature extraction and classification. The aim of noise reduction is to reduce the level of noise in the speech signal and make it more compatible for the ASR. As for feature extraction, this process attempted to extract the most relevant features related to the phoneme signal. The extracted features acted as input features of the NN during training and testing. Finally, the purpose of classification process is to arrange the most similar and related features in categories based on the training phase. Basically, networks training database are being observed and updated during training session of the networks, involving the weights and biases arguments. Networks with lower errors can be considered as better networks (6). Hence, this paper deems to explore further the ability of NN for Arabic phonemes recognition spoken by Malay individuals. This paper is arranged as following; related work is discussed in section II followed by section III that discussed method to be implemented based on Wiener filter, Mel-Frequency Cepstral Coefficients and pattern recognition neural network. Section IV elaborated experimental analysis and results and followed by Conclusion section.

A mathematical framework based on maximum likelihood stochastic matching is proposed to perform feature and model compensation for robust speech recognition. Speech recognition is often formulated as a matching problem between the feature vectors extracted from a test utterance and a set of speech models or patterns obtained from some training corpra. It is well known that a speech recognizer often degrades in performance when the testing data are not acoustically similar to the training data. One way to improve is to find features that are invariant under all acoustic conditions and distortions. Some form of compensation is often required. The proposed stochastic matching approach assumes a structure or a form of the feature and/or model transformations. Together with a set of nuisance parameters, the transformations approximate the distortion in the test utterance. To decrease the acoustic mismatch between a test utterance and a given set of speech models, e.g., hidden Markov models, the stochastic matching algorithm estimates the nuisance parameters and then applies the feature/model transformations during speech recognition. Simple channel distortion can be approximated with linear transformations. For more complicated distortions, such as environmental, speaker, and combined mismatches, nonlinear compensating transformations are needed. These compensations give a significant performance improvement in speech recognition over the systems without them when utterances are affected by additive ambient noises and convolutional channel distortions.

This study explores code-switching practices among bilingual Saudi Arabians within three language varieties: English, Standard Arabic (SA), and Dialectal Arabic (DA). While there are studies that examine the use of code-switching between SA and DA, and others that investigate Arabic-English code-switching, no study to date has examined natural code-switching into English in conversations of SA vs. DA as compared to code-switching into Arabic in English conversations. Controlling the language of the interviewer (English, SA, or DA), this study examines (1) the likelihood of code-switching relative to the language of the interview, (2) the rate of switches in each interview context, and (3) the mean duration of those switch segments. Results show that code-switching to Arabic was very rare in English interviews (only 0.89% of interview time was in Arabic with a switch rate of 1.74 switches/minute and average length of 0.59 s). However, participants in SA and DA interviews did code-switch to English 8.32% and 10.08% of the time, respectively. The mean rate of switches was about twice as frequent for participants interviewed in DA (14.18 switches/minute) than for participants interviewed in SA (7.21 switches/minute). Moreover, participants in SA interviews had significantly longer mean English segments than DA interviewees (1.21 s vs. 0.81 s, respectively). The results demonstrate that (1) English has the greatest impact on participants’ tendency to code-switch, (2) SA encourages code-switching in a way that aims to preserve its formal status, and (3) DA encourages code-switching the most, i.e., code-switching is an emblem of DA conversations.

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.

Growth in Digital signal processing technology gives positives influences in human life. One of the branch of science that gives significant influence is digital speech processing. It can be expand into some applications that make human life easier. Digital speech processing is appropriate to speech recognition. Speech recognition is used to arrange the movement of remote control car. The remote control car will move according to our speech. This final project is closely related with speech recognition. The LPC (Linear Predictive Coding) method will extract the speech signal features and HMM (Hidden Markov Model) to modelling the speech signal are used. It is done by comparing model from extracting feature that is available in HMM modelling. Models will be used in the speech recognition process, if the models have highest level of conformity. The experiment has been done in two conditions, i.e ideal condition in room wih low noise level and unideal condition in room with noise. Result of the experiment from the whole sistem performace at ideal condition is 97,71% for people that have been inputed in the database, and 95,42% for people which have not been inputed in the database. Result of the experiment of database say it regulary is 97,14%. Result of the experiment of database at unideal condition is 54,28% for inputing word at noisy area, result of the experiment of database for inputing word at high frequency from siren voice is 98,57% and result of the experiment of inputing similar word with database is 97,6% Keywords: speech recognition, LPC, HMM

The Relative Distance Vector Neural Network (RDVNN) Model: A Hybrid Approach to Speech Recognition

We present in this chapter a practical approach in building Arabic automatic speech recognition (ASR) system for mobile telecommunication service applications. We also present a procedure in conducting acoustic modelling adaptation to better take into account the pronunciation variation across the Arabic speaking countries. Modern Standard Arabic (MSA) is the common spoken and written language for all the Arab countries, ranging from Morocco in the west to Syria in the East, including Egypt, and Tunisia. However, the pronunciation varies significantly from one country to another to a degree that two persons from different countries may not be able understand each other. This is because Arabic speaking countries are characterized by a large number of dialects that differ to an extent that they are no longer mutually intelligible and could almost be described as different languages. Arabic dialects are often spoken rather than written varieties. MSA is common across the Arab countries, but it is often influenced by the dialect of the speaker. This particularity of the Arabic countries constitutes a practical problem in the development of a speech-based application in this region; suppose a speech application system is built for one country influenced by one dialect, what does it take to adapt the system to serve another country with a different dialect region? This is particularly challenging since resource to build accurate speaker independent Arabic ASR system for mobile telecommunication service applications are limited for most of the Arabic dialects and countries. Recent advances in speaker independent automatic speech recognition (SI-ASR) have demonstrated that highly accurate recognition can be achieved, if enough training data is available. However, the amount of available speech data that take into account the dialectal variation of each Arabic country is limited, making it challenging to build a high performance SI-ASR system, especially when we target specific applications. Another big challenge when building an SI-ASR is to handle speaker variations in spoken language. These variations can be due to age, gender, educational level as well as the dialectical variants of Arabic language. Usually an ASR system trained in one regional variation exhibits poorer performance when applied to another regional variation. Three problems may arise when a SI-ASR system built for one dialect but applied to target users with a different dialect: (1) Acoustic model mismatch, (2) Pronunciation lexicon mismatch and (3) Language model mismatch.

A low-power and real-time hidden Markov model (HMM) accelerator is proposed for gesture user interfaces on wearable smart devices. HMM algorithm is widely used for sequence recognitions such as speech recognition and gesture recognition due to its best-in-class recognition accuracy. However, the HMM algorithm incorporates high computational complexity and requires massive memory bandwidth for sequence matches. There have been studies on hardware acceleration of the HMM algorithm to resolve these issues, but they were focused on the speech recognition and did not incorporate the motion orientation capability required for the gesture recognition case. In this paper, we propose an HMM accelerator incorporating the motion orientation block for gesture recognitions on wearable devices. Binary search is exploited in the motion orientation to avoid the division and arctangent associated with the orientation and reduce its arithmetic complexity. In addition, gesture models are clustered in the gesture database to save the memory bandwidth by reducing memory transactions. Moreover, logarithmic arithmetic is used in Viterbi decoding in the HMM for more reduction in its complexity. Thanks to these schemes, this work achieves 25.6% power reduction compared with a plain hardware implementation of the gesture recognizing HMM.

This paper describes the fifth edition of the Multi-Genre Broadcast Challenge (MGB-5), an evaluation focused on Arabic speech recognition and dialect identification. MGB-5 extends the previous MGB-3 challenge in two ways: first it focuses on Moroccan Arabic speech recognition; second the granularity of the Arabic dialect identification task is increased from 5 dialect classes to 17, by collecting data from 17 Arabic speaking countries. Both tasks use YouTube recordings to provide a multi-genre multi-dialectal challenge in the wild. Moroccan speech transcription used about 13 hours of transcribed speech data, split across training, development, and test sets, covering 7-genres: comedy, cooking, family/kids, fashion, drama, sports, and science (TEDx). The fine-grained Arabic dialect identification data was collected from known YouTube channels from 17 Arabic countries. 3,000 hours of this data was released for training, and 57 hours for development and testing. The dialect identification data was divided into three sub-categories based on the segment duration: short (under 5 s), medium (5–20 s), and long (>20 s). Overall, 25 teams registered for the challenge, and 9 teams submitted systems for the two tasks. We outline the approaches adopted in each system and summarize the evaluation results.

The movements of talkers' face, nose, mouth and throat are known to convey visual cues and represent several different kinds of informationl, and that can improve speech recognition rate, especially for persons with speech-impairments. We proposed a new speech recognition method using these visual features and hidden Markov model (HMM). Based on global optimisation, a new genetic algorithm (GA) for training HMM was proposed. Six chinese vowels were taken as the experimental data, ten handicapped speakers were taken as the testee. Recognition experiments show that the method is effective and high speed and accuracy for speech recognition. At present, the average recognition rate is 91.47% using improved HMM and 88.96% using the classic training HMM algorithm, So the features has very good robustness and the improved HMM is very good.

In this paper we investigated Artificial Neural Networks (ANN) based Automatic Speech Recognition (ASR) by using limited Arabic vocabulary corpora. These limited Arabic vocabulary subsets are digits and vowels carried by specific carrier words. In addition to this, Hidden Markov Model (HMM) based ASR systems are designed and compared to two ANN based systems, namely Multilayer Perceptron (MLP) and recurrent architectures, by using the same corpora. All systems are isolated word speech recognizers. The ANN based recognition system achieved 99.5% correct digit recognition. On the other hand, the HMM based recognition system achieved 98.1% correct digit recognition. With vowels carrier words, the MLP and recurrent ANN based recognition systems achieved 92.13% and 98.06, respectively, correct vowel recognition; but the HMM based recognition system achieved 91.6% correct vowel recognition.

This study analyzes the effect of stress in human and automatic stressed speech processing tasks for speech collected from non-professional speakers. The database of 33 keywords is collected under five stress conditions, namely, neutral, angry, happy, sad and Lombard from fifteen speakers. The first study is to understand the ability to identify stress by human and automatic speech processing. The average performance of human stress classification is 59.44%. The average performance of automatic stress classifier using Vector Quantization (VQ) and Hidden Markov model (HMM) is 54.65% and 56.02%, respectively. The second study has been done to understand the effect of stress in human and automatic speech recognition. The average performance of human stressed speech recognition is 99.60%. The automatic stressed speech recognition performance using VQ and HMM is 82.42% and 76.79%, respectively. Even in the non-professional speakers scenario, human performance is better than automatic processing. Also, automatic processing seem to show considerable degradation in performance that warrant development of new methods to handle stress information.

The first periodical publications carrying news written by and for Arabs appeared during the first part of the 19th century. The major developments in the field of non-governmental Arabic press occurred, however, only during the second half of that century. That was also the time when Jews started to take an active part in founding, editing, and writing for Arabic newspapers, periodicals, and professional journals in various parts of the Arab world. First it included newspapers and periodicals in Judeo – Arabic dialects and only later in standard Arabic language. The main centres of journalistic activity by Jews in the Arab world were Baghdad, Cairo, Beirut, Alexandria, Damascus and Tunis. Newspapers founded by Jews were mostly ephemeral, however, there were also periodicals that prospered for decades. There was a connection between the involvement of Arab Jews in canonical Arab culture and the development of the Arabic – Jewish press and journalism: wherever Jews tried to integrate politically, socially and culturally into society (Iraq, to a lesser extent in Egypt, Lebanon and Syria) there were always active Jewish owners of Arabic newspapers and periodicals as well as editors and journalists writing in standard literary Arabic. But wherever Jews showed no significant interest in the canonical Arabic cultural activities of their society (e.g. North Africa), only periodicals in Judeo – Arabic dialects written in Hebrew letters are to be found (in addition to newspapers in other languages). Jewish newspapers published in both Judeo – Arabic dialects and standard Arabic had generally one main aim in common: promoting modernisation of Jewish life in Arab societies and encouraging Jews to become acquainted with the achievements of Western civilisation. After the establishment of the State of Israel in 1948, there has been a sharp decline in Arabic journalism by Jews; in fact we are currently witnessing the demise of Arab – Jewish culture. A tradition that started more than fifteen hundred years ago is vanishing before our eyes.