Speech Recognition using Epochwise Back Propagation

Speech Recognition using Epochwise Back Propagation International Journal of Computer Applications (0975 – 8887) Volume *– No.*, ___________ 2013 Speech Recognition using the Epochwise Back Propagation through time Algorithm Neelima Rajput S.K.Verma Department of C.S.E. Department of C.S.E. GBPEC, Pauri Gharwal, GBPEC, Pauri Gharwal, Uttrakhand, India. Uttrakhand, India ABSTRACT In this paper, artificial neural networks are used to accomplish the English alphabet speech recognition. The challenging issue in the area of speech recognition is to design an accurate and effective speech recognition system. We implemented a new data classification method, where we use neural networks, which are trained using the calculated epoch values of audio signal. This method gave comparable result to the already implemented neural networks. In this paper, Back propagation neural network architecture used to recognize the time varying input data, and provides better accurate results for the English Alphabet speech recognition. The Epochwise Back Propagation through time (BPTT) algorithm uses the epoch values of input signal to train the network structures and yields the satisfactory results. Keywords Artificial Neural Network, Back Propagation Neural Network, Epoch, Speech Recognition. I INTRODUCTION Speech recognition system enables the machine to understand the human speech and react accordingly. It allows the machine to automatically understand the human spoken utterances with the speech signal processing and pattern recognition. In this approach is the machine converts the voice signal into the suitable text or command through the process of identification and understanding. Speech recognition is emerges as a vast technology in current time. It also plays an important role in information theory, acoustics, phonetics, linguistics, and pattern recognition theory and neurobiology disciplines. speech recognition technology become a key technology in the computer information processing technology as there is rapid advancement in the software, hardware and information technology. The features of input audio signal are compared with the voice template stored in the computer database in speech recognition system by using the computer systems. Recognition results are mainly depends up on the matching techniques used for matching the audio signal characteristics. To improve the recognition rate and better recognition results neural networks are used. A neural network is a powerful tool which used to adapt and represent the complicated input outputs. Neural nets are basically interconnected networks of relatively simple processing units, or nodes that work simultaneously. They are designed to mimic the function of human neuron biological networks. The processing units of neural networks are termed as neurons. A neural network provides better results over the existing approaches in speech recognition systems [1]. 2 BASICS OF NEURAL NETWORKS The basics of neural networks are discussed as follows. There are many different types of neural networks, but they all have four basic and common attributes: †¢ Processing units †¢ Connections †¢ Computing procedure †¢ Training procedure . Processing Units A neural network contains several processing units, which are roughly analogous to neurons in the human brain. All these units activate in parallel and perform the task simultaneously. Processing units are responsible for the overall computation; there is no any other unit for the corporation of their activity. Each processing unit computes a scalar function of all its local inputs at every moment of time and then further broadcast the result to their neighboring units [2]. The units in a neural network are basically classified into input units, which used to receive data from the outside; hidden units, used to internally transform the data; and output units, which serve decisions or target signals. 2.2 Connections All processing units in a neural network are organized in to a defined topology by a set of connections, or weights, shown as lines in a diagram. Each weight consist a real value, which ranging from ∞ to + ∞. The value of a weight represents how much impact a unit has on its neighbor units a positive weight causes one unit to excite another, while a negative weight causes one unit to inhibit another. Weights of the processing units are usually one-directional (from input units towards output units), but it may be two-directional sometimes, especially when there is no distinction between input and output units. Figure 1.Neural network topologies: (a) unstructured, (b) layered, (c) recurrent, (d) modular [3]. The above figure shows the topology of different neural networks. Unstructured Neural Network is mainly used in processor which is operated in parallel to provide the computational power for the speech recognition system. Layered neural net algorithms are self-organizing and their internal speech model maximizes the performance and produces better results comparable to existing systems. Recurrent Neural network are mainly used in pattern sequencing as it follows the sequences changes time to time. Modular neural network are used in designing of complex systems by using simple components. Neural nets offer an approach to computation that mimics biological nervous systems. Algorithms based on neural nets have been proposed to address speech recognition tasks which humans perform with little apparent effort. 2.3 Computation Procedure Computation of neural networks begins after applying an input data to the input units of the network. Then the activation function of all the units is calculated either simultaneously or independently depends upon the structure of the neural network. The computation process in the unstructured network is termed as spreading activation and in layered network is known as forward propagation as it proceed from the input units to the output units. First we compute the net input of the processing unit and then we compute the output activation function of the net input to update a given processing unit. 2.4 Training Procedure Training a network means enable the connections adaptive so that the network shows the actual computational behavior for all the input patterns. In training process usually weights are updated but sometimes the modification of network topology also takes place, i.e., addition and deletion of connections from the network topology [4]. Modification of weight is easy and beneficial than topology modification as a network with bulk connections able to set any of its weight zero, which is equivalent as deleting such weights. 3. RELATED WORK The past research concluded that the use of the neural networks in the speech recognition system provides the better recognition result compared to the other existing approaches. The latest study of neural networks actually started in the 19th century, when neurobiologists first introduce the extensive studies of the human nervous system [5]. Cajal (1892) determined that the nervous system is comprised of some basic units i.e. discrete neurons, which communicate with the other neurons by sending electrical signals down their long axons, which ultimately activated and touch the dendrites(receptive areas) of thousands of other neurons, transmitting the electrical signals through synapses (points of contact, with variable resistance). Firstly, the different kinds of neurons were identified, and then analyze their electrical responses, and finally their patterns of connectivity and the brain’sgross functional areas were mapped out. According to the neurobiologists study the functi onality of individual neurons are quite simple and easy. Whereas to determine how neurons worked together to achieve high level functionality, such as perception and cognition are very difficult.[6] In 1943 McCulloch and Pitts proposed the first enumeration model of a neuron, named as binary threshold unit, whose output was either 0 or 1 depending on whether its net input exceeded a given threshold. There are various approaches proposed by the researchers to design an accurate speech recognition system for various purposes. In [7] Al-Alaoui algorithm is used to train the neural network. This method gives the comparable better results to the already implemented hidden markov model (HMM) for the recognition of the words. This algorithm also overcomes the disadvantages of the HMM in the recognition of sentences. An algorithm based on neural network classifier [8] for speech recognition used a new Viterbi net architecture which is recognized the input patterns and provided an accuracy of recognition rate more than 99% on a large speech database. This system is used for isolated word recognizer. In [9] author accomplishes the isolated word speech recognition using the neural network. The methodology of this approach is to extract the feature of speech signals using the Digital Signal Processing techniques and then classification using the Artificial Neural Network. This algorithm concluded that the better accurate recognition results are obtained from the probalistic Neural Network PNN. In [10] author implemented a pre- trained deep neural network using the hidden markov model (DNN-HMM) hybrid architecture which is used to train the DNN to produce the better recognition results of large vocabulary speech database. 4. PROPOSED WORK Speech recognition using the Epochwise Back propagation through time algorithm is proposed in this paper.In the proposed system neural network training is based on the calculation of epoch of the audio signal and then used these epoch value for the training of the neural network. The input data sets used to train the neural network can be partitioned in to the independent epochs. Each epoch representing a temporal value of the input data. Back propagationneural network used in the system in following steps. First choose and fix the architecture for the network, which will contain input, hidden and output units, all of which will contain sigmoid functions. Assign the weights between all the nodes. The assignments of weights usually between -0.5 and 0.5. Each training example is used, one after another, to re-train the weights in the network. After calculating each epoch for input audio data, a termination condition is checked. In neural network architecture the weights of input and hidden layers are adjusted according to the target output values [11] The input data is considered as E which is propagated through the network so that we can record all the observed values Oi(E) for the output nodes Oi. At the same time, we record all the observed values hi(E) for the hidden nodes. Then, for each output unit Ok, we calculate its epoch as follows: (1) The epoch terms from the output units are used to calculate epoch terms for the hidden units. In fact, this method gets its name because we propagate this information backwards through the network [12]. For each hidden unit Hk, we calculate the epoch as follows: (2) Here, we take the epoch term for every output unit and multiply it by the weight from hidden unit Hk to the output unit. We then add all these together and multiply the sum by hk(E)*(1 hk(E)). Having calculated all the epoch values associated with each unit (hidden and output), we can now transfer this information into the weight changes Δij between units i and j. The calculation is as follows: for weights wij between input unit Ii and hidden unit Hj, and summation of all units are as: (3) Back Propagation Neural Network architecture is shown in below figure Fig.2 Back propagation Neural Network The main steps of this system are defined as follows. Read the input audio Signal. Extract the epoch values Train the neural network on the basis of epoch values. Applied the back propagation neural network for the classification. Matching the input data with the trained data. Recognized the input. The data flow diagram of the proposed system represented in given figure C Figure 2 Proposed approaches for Speech Recognition 5. EXPERIMENTAL RESULTS The experiment conducted on the audio database of English alphabets. Matlab R2010a (Math works) in Windows 7 was used to implement the proposed algorithm. The input signal is used to calculate the epoch values and then by using calculated epoch values the neural network is trained.The epoch rate of multi-layered networks over a training set could be calculated as the number of miss-classified data values. There are many output nodes, all of which could potentially misfire (e.g., giving a value close to 1 when it should have output 0 and vice-versa), we can be more sophisticated in our epoch evaluation. In practice the overall network epoch is calculated as: This is not as complicated as it first appears. The calculation simply involves working out the difference between the observed output for each output unit and the target output and squaring this to make sure it is positive, then adding up all these squared differences for each output unit and for each input signal. The calculated epoch values for audio signal A is listed in tabular form. Table: 1 Calculated Epoch values for input data Then epoch values are basically instant of significant excitation of the vocal-tract system during production of speech. Table 1 represented the Epoch values for the input English alphabet A in terms of time in mili seconds. These epoch values are stored in the computer for the further matching by using the neural networks to the recognition purpose. Similarly, epoch values are calculated for each input English alphabet and then train the network through these input patterns and stored in the system for recognition Figure 3 Performance graphs of epoch values. The figure 3 shows the performance of the system based on epoch values. The best validation performance epoch value is selected from the different epoch on the basis of Mean Square error. The graph is plotted on epoch and means squared error values. Table: 2 Performance of the proposed system In Table: 2 the recognition rate is calculated for five input English alphabet which is 98.8%. The new proposed Epochwise Back propagation through time algorithm yields the satisfactory results. 6. CONCLUSION In this paper, we implemented the Epochwise Back propagation through the time varying epoch calculation. The experiment is conducted on the small set of English Language alphabet to calculate the recognition rate of the system. Some different sound samples (i.e., with different sampling frequency) of each alphabet are taken and used for testing the system. The above results show the performance of our proposed algorithm in speech recognition. 7. REFERENCES Jianliang Meng, Junwei Zhang,Haoquan Zhao, â€Å"Overview of the speech Recognition Technology†, 2012 Fourth International Conference on Computational and Information Sciences. L. Fausset, Fundamentals of Neural Networks. PrenticeHall Inc., 1994, ch 4. Jiang Ming Hu, in the Yuan Baozong, Lin Biqin. Neural networks for speech recognition research and progress. Telecommunications Science, 1997, 13(7):1-6. H. Boulard and N. Morgan, â€Å"Continuous speech recognition by connectionist statistical methods,† IEEE Trans. Neural Netw., vol. 4, no. 6, pp. 893–909, Nov. 1993. Mohamad Adnan Al-Alaoui, Lina Al-Kanj, Jimmy Azar, and Elias Yaacoub, â€Å"Speech recognition using Artificial Neural Network and Hidden Markov Model†, IEEE Multidisciplinary Engineering Education Magazine Vol. 3, No.3, September 2008. RICHARD P. LIPPMANN, â€Å"Neural Network Classifiers for Speech Recognition† The Lincoln Laboratory Journal, Volume 1, Number 1 (1988) Gulin Dede, Murat Husnu SazlÄ ±, â€Å"Speech recognition using artificial neural network.† Digital signal processing  © 2009 Elsevier Inc. George E. Dahl, Dong Yu, Li Deng, Alex Acero,† Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition† , IEEE Transaction on Audio, and Language Processing, Vol. 20, No.1, January 2012. H. Paugam-Moisy, ‘Parallel neural computing based on network duplicating’,in Parallel Algorithms for Digital Image Processing, Computer Vision and Neural Networks, ed., I. Pitas, 305–340, JohnWiley, (1993). Stefano Scanzio, Sandro Cumani, Roberto Gemello, Franco Mana, P. Laface, â€Å"Parallel implementation of Artificial Neural Network Training for Speech Recognition.† Pattern recogonition letters,  © 2010 Elsevier B.V. N. Morgan and H. Bourlard, â€Å"Continuous speech recognition using multilayer perceptrons with hidden Markov models,† in Proc. ICASSP,1990, pp. 413–416. Y. Hifny and S. Renals, â€Å"Speech recognition using augmented conditional random fields,† IEEE Trans. Audio, Speech, Lang. Process., vol.17, no. 2, pp. 354–365, Feb. 2009.

Pain Poem

PAIN Innocent plumes out of the lonely seed, Illusion of darkness was seen, Things seen were absorbed, Sun, water, alarm what happened? Fell in a tunnel, Lights were not yet seen, Faith slowly became weak, Failings, please stops Dodge, defense and attack like a boxer, Easy start yet harder comes, Not a single blink of an eye, Be firm and don't loosen up a single muscle! Fill with all bright colors, Four bright colors over one dark color, Darkness was unseen yet brightness was clearly seen, This is what the world is supposed to be! Walking on a dark street,Rusted street light soul working, Street light can't yet street lights can, Street is dark no more but now bright. Summary Answer Pain, right at this moment honestly I can't think of anything that makes me feel pain. I don't think I have been through the deep pain that people can't get rid of, but there is one thing that makes me feel pain and that is when see others in pain and to see this beautiful world suffering with so many kin ds of things. So basically based on this poem I wrote about what pain I faced and what I think I can do and what others can o to give solutions for this pain.This is a very short summary of the poem I wrote. Ã'›â€ ¦ In today's world, It has changed so badly and it's obvious. An innocent child will receive things that the world Is doing and It will ruin their Innocent mind, Life will get harder and harder and it is so dark and tough to achieve what you want to achieve, you fail so many times and it will Just make you give up easily. If your life is so dark by doing so many bad things, do more good things and it definitely will cover up all the ad things and it will also cover up all the bad memories that you had.And so now, you will definitely find your life different and continue moving forward In your life. One person definitely can't light up the whole world; we can't be so selfish and wait 1 OFF tort others to be the light tot the world and tot other people. It must sat rat trot us. We can't Just sit in our comfort zone by watching what happened; we must really do something and give other people the light they need to make the world a better place to live in.

Hotel and Travel Vocabulary in Spanish

Hotel reserved? Flights booked? Bags packed? Whats next is learning a few essential words to make your hotel stay a little easier. If youre headed to a Spanish-speaking country, your hotel is as good a place as any to practice Spanish. Your concierge or host will appreciate the effort and can help you with tricky pronunciations along the way. Different Hotel Types When in a country where Spanish is the primary language, travelers spend more time in their lodgings, called hospedajes, than any other place. If you have arrived in a Spanish-speaking  ubicacià ³n, which means location, nail down the type of hotel that you would prefer, also called a  hotel in Spanish, too.   Looking for a spa or resort? Then ask for the nearest balneario.  Want something deluxe, then you want something  de lugo!  Or looking more for a motel or inn, ask for el motel or la posada.  There are unique types of accommodations, or alojamientos, such as a  bed-and-breakfast, which is called a pensià ³n, or bungalows, called a bungalow in Spanish, too. Reservation Desk You have decided on the type of lodging, now you need to make reservations, called ​reservaciones. You will negotiate the costs, or tarifa, with the  hotelero, or hotelkeeper. It is appropriate to ask what the standard tip or propina should be for your bellhop, also called the botones. Upon checkout, you handle the bill, or la cuenta, with the hotelero. All About Your Room What kind of room, or  habitacià ³n, do you want? Want a suite, ask for a ​suite in Spanish, too. Do you need a single room, or  habitacià ³n sencilla?  Do you want a double, a habitacià ³n  doble, or a triple, also called a triple. Want to make sure you have a bathroom in your room, ask if it has a  baà ±o.   How about your bed, called a cama? Do you want a single bed, a cama de monja, or do you want a double bed, called a cama de matriomonio? Does it matter which floor, or piso, you are on? If you want to make sure you are on the ground floor ask for el piso bajo. Need directions to the ice machine? Ask for el hielo. How about a view, or vista, out your window? If you are in a beach locale, then perhaps la vista al mar, or a sea or ocean view, is important to you. Nice amenities to know about your room would be: Is there room service, or  el  servicio  en  cuarto? How about an in-room safe, called la caja de seguridad? Hotel Features The room is booked. You are officially a guest, or huesped. You are ready to explore the hotel amenities. Does it have a bar, also called bar, or a restaurant, called a restaurante? How about coffee in the morning? Where is  el cafà ©? The person who can guide you would be the concierge, or el conserje.   Are you in town for a convention, called la convencià ³n? Need to ask how to get to the convention hall? That would be called el salà ³n de convenciones. How about going out dancing after the convention? Ask about where to find a  discoteca. Other hotel amenities that can boost your vacation experience include free parking, called estacionamiento, a swimming pool, called a piscina, and a workout room, or gimnasio. English Guidance Due  to the widespread adoption of English, particularly at upper-end hotels, it may be more common to find signage for English words used to describe certain facilities or services. Do not be surprised if words like spa,concierge, and room service are used instead of the Spanish equivalent.