The paper presents a language model that develops syntactic structure and uses it to extract meaningful information from the word history, thus enabling the use of long distance dependencies. The model assigns probability to every joint sequence of words-binary-parse-structure with headword annotation and operates in a left-to-right manner --- therefore usable for automatic speech recognition. The model, its probabilistic parameterization, and a set of experiments meant to evaluate its predictive power are presented; an improvement over standard trigram modeling is achieved.

/pdf/exploiting-syntactic-structure-for-language-modeling-cenz4tu052.pdf

Exploiting syntactic structure for language modeling

Speech recognition is one of the entrancing fields in the zone of computer science. Exactness of speech recognition framework may decrease because of the nearness of noise exhibited by the speech signal. Consequently, noise removal is a fundamental advance in automatic speech recognition (ASR) system. ASR is researched for various languages in light of the fact that every language has its particular highlights. Particularly, the requirement for ASR framework in Tamil language has been expanded broadly over the most recent couple of years. In this work, bidirectional recurrent neural network (BRNN) with self-organizing map (SOM)-based classification scheme is suggested for Tamil speech recognition. At first, the input speech signal is pre-prepared by utilizing Savitzky–Golay filter keeping in mind the end goal to evacuate the background noise and to improve the signal. At that point, Multivariate Autoregressive based highlights by presenting discrete cosine transformation piece to give a proficient signal investigation. And in addition, perceptual linear predictive coefficients likewise separated to enhance the classification accuracy. The feature vector is shifted in measure, for picking the right length of feature vector SOM utilized. At long last, Tamil digits and words are ordered by utilizing BRNN classifier where the settled length feature vector from SOM is given as input, named as BRNN-SOM. The experimental analysis demonstrates that the suggested conspire accomplished preferable outcomes looked at over exist deep neural network–hidden Markov model algorithm regarding signal-to-noise ratio, classification accuracy, and mean square error.

An Automatic Tamil Speech Recognition system by using Bidirectional Recurrent Neural Network with Self-Organizing Map

COCA: Constructing optimal clustering architecture to maximize sensor network lifetime

In this paper, we propose a method for detecting the vowel onset points (VOPs) for low bit rate coded speech. VOP is the instant at which the onset of the vowel takes place in the speech signal. VOP plays an important role for the applications, such as consonant-vowel (CV) unit recognition and speech rate modification. The proposed VOP detection method is based on the spectral energy present in the glottal closure region of the speech signal. Speech coders considered to carry out this study are Global System for Mobile Communications (GSM) full rate, code-excited linear prediction (CELP), and mixed-excitation linear prediction (MELP). TIMIT database and CV units collected from the broadcast news corpus are used for evaluation. Performance of the proposed method is compared with existing methods, which uses the combination of evidence from the excitation source, spectral peaks energy, and modulation spectrum. The proposed VOP detection method has shown significant improvement in the performance compared to the existing method under clean as well as coded cases. The effectiveness of the proposed VOP detection method is analyzed in CV recognition by using VOP as an anchor point.

Vowel Onset Point Detection for Low Bit Rate Coded Speech

The vast amounts of data being collected and analyzed have led to invaluable source of information, which needs to be easily handled by humans. Automatic Text Summarization (ATS) systems enable users to get the gist of information and knowledge in a short time in order to make critical decisions quickly. Deep neural networks have proven their ability to achieve excellent performance in many real-world Natural Language Processing and computer vision applications. However, it still lacks attention in ATS. The key problem of traditional applications is that they involve high dimensional and sparse data, which makes it difficult to capture relevant information. One technique for overcoming these problems is learning features via dimensionality reduction. On the other hand, word embedding is another neural network technique that generates a much more compact word representation than a traditional Bag-of-Words (BOW) approach. In this paper, we are seeking to enhance the quality of ATS by integrating unsupervised deep neural network techniques with word embedding approach. First, we develop a word embedding based text summarization, and we show that Word2Vec representation gives better results than traditional BOW representation. Second, we propose other models by combining word2vec and unsupervised feature learning methods in order to merge information from different sources. We show that unsupervised neural networks models trained on Word2Vec representation give better results than those trained on BOW representation. Third, we also propose three ensemble techniques. The first ensemble combines BOW and word2vec using a majority voting technique. The second ensemble aggregates the information provided by the BOW approach and unsupervised neural networks. The third ensemble aggregates the information provided by Word2Vec and unsupervised neural networks. We show that the ensemble methods improve the quality of ATS, in particular the ensemble based on word2vec approach gives better results. Finally, we perform different experiments to evaluate the performance of the investigated models. We use two kind of datasets that are publically available for evaluating ATS task. Results of statistical studies affirm that word embedding-based models outperform the summarization task compared to those based on BOW approach. In particular, ensemble learning technique with Word2Vec representation surpass all the investigated models.

Enhancing unsupervised neural networks based text summarization with word embedding and ensemble learning

Building a continuous speech recognizer for the Indian language like Tamil is a challenging task due to the unique inherent features of the language like long and short vowels, lack of aspirated stops, aspirated consonants and many instances of allophones. Stress and accent vary in spoken Tamil language from region to region. But in formal read Tamil 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. Like other Indian languages, Tamil is also syllabic in nature. Pronunciation of words and sentences is strictly governed by set of linguistic rules. Many attempts have been made to build continuous speech recognizers for Tamil for small and restricted tasks. However medium and large vocabulary CSR for Tamil is relatively new and not explored. In this paper, the authors have attempted to build a Hidden Markov Model (HMM) based word and triphone acoustic models. The objective of this research is to build a small vocabulary word based and a medium vocabulary triphone based continuous speech recognizers for Tamil language. In this experimentation, a word based Context Independent (CI) acoustic model for 371 unique words and a triphone based Context Dependent (CD) acoustic model for 1700 unique words have been built. In addition to the acoustic models a pronunciation dictionary with 44 base phones and trigram based statistical language model have also been built as integral components of the linguist. These recognizers give very good word accuracy for trained and test sentences read by trained and new speakers.

/pdf/word-and-triphone-based-approaches-in-continuous-speech-4qzizliem0.pdf

Word and triphone based approaches in continuous speech recognition for Tamil language

In automatic speech recognition, the phone has probably been a dominating sub-word unit for more than one decade. Context Dependent phone or triphone modeling accounts for contextual variations between adjacent phones and state tying addresses modeling of triphones that are not seen during training. Recently, syllable is gaining momentum as a new sub-word unit. Syllable being a larger unit than a phone addresses the severe contextual variations between phones within it. Therefore, it is more stable than a phone and models pronunciation variability in a systematic way. Tamil language has challenging features like agglutination and morpho-phonology. In this paper, attempts have been made to provide solutions to these issues by using the syllable as a sub-word unit in an acoustic model. Initially, a small vocabulary context independent word models and a medium vocabulary context dependent phone models are developed. Subsequently, an algorithm based on prosodic syllable is proposed and two experiments have been conducted. First, syllable based context independent models have been trained and tested. Despite large number of syllables, this system has performed reasonably well compared to context independent word models in terms of word error rate and out of vocabulary words. Subsequently, in the second experiment, syllable information is integrated in conventional triphone modeling wherein cross-syllable triphones are replaced with monophones and the number of context dependent phone models is reduced by 22.76% in untied units. In spite of reduction in the number of models, the accuracy of the proposed system is comparable to that of the baseline triphone system.

Syllable modeling in continuous speech recognition for Tamil language

Mutated k-means algorithm for dynamic clustering to perform effective and intelligent broadcasting in medical surveillance using selective reliable broadcast protocol in VANET

A novel algorithm for clustering and routing is proposed based on grid structure in wireless sensor networks. According to the size of the area and transmission range, a suitable grid size is calculated and a virtual grid structure is constructed. A cluster head is selected in each grid based on the nearest distance to the midpoint of grid. A localized single path strategy is followed in order to forward data within a grid. To forward aggregate data from cluster head to the Sink, angular inclination based combinational routing model is implemented. The simulation results show that the algorithm performs better in terms of improving the network lifetime and scalability compared to recent and relevant existing algorithms.

GCCR: An Efficient Grid Based Clustering and Combinational Routing in Wireless Sensor Networks

A Computer network or data communication network is a telecommunication network that allows computers to exchange data. Computer networks are typically built from a large number of network devices such as routers, switches and numerous types of middle boxes with many complex protocols implemented on them. They need to accomplish very complex tasks with access to very limited tools. As a result, network management and performance tuning is quite challenging. Software-Defined Networking (SDN) is an emerging architecture purporting to be adaptable, cost-effective, dynamic and manageable pursuing to be suitable for the high-bandwidth, changing nature of today's applications. SDN architectures decouples network control and forwarding functions, making network control to become directly programmable and the underlying infrastructure to be abstracted from applications and network services. The network security is a prominent feature of the network ensuring accountability, confidentiality, integrity, and protection against many external and internal threats. An Intrusion Detection System (IDS) is a type of security software designed to automatically alert administrators when someone or something is trying to compromise information system through malicious activities or through security policy violations. Security violation in SDN environment needs to be identified to prevent the system from an attack. The proposed work aims to detect the attacks on SDN environment. Detecting anomalies on SDN environment will be more manageable and efficient.

R. Thangarajan

Papers

Word and triphone based approaches in continuous speech recognition for Tamil language

Syllable modeling in continuous speech recognition for Tamil language

Mutated k-means algorithm for dynamic clustering to perform effective and intelligent broadcasting in medical surveillance using selective reliable broadcast protocol in VANET

GCCR: An Efficient Grid Based Clustering and Combinational Routing in Wireless Sensor Networks

Efficient anomaly detection and mitigation in software defined networking environment