%0 Journal Article %1 noauthororeditor %A Rai, Neerparaj %A Rai, Bijay %D 2014 %J International Journal of Applied Control, Electrical and Electronics Engineering (IJACEEE) %K Feed-forward Linear Mobile Neural Robot Speech back-propagation coding networks predictive recognition %N 4 %P 13-22 %T AN ANN BASED MOBILE ROBOT CONTROL THROUGH VOICE COMMAND RECOGNITION USING NEPALI LANGUAGE %U http://airccse.com/ijaceee/papers/2414ijaceee02.pdf %V 2 %X The analog speech signal can be used for interacting with machines, computers or robots. In this case, speech algorithm is capable to recognize the voice commands that are given as inputs to a mobile robot through wireless XBee modules. It is actually a form of Word Recognition. In this presented paper, a voice command recognition system is going to be developed by using Artificial Neural Network (ANN). The Commands that used here are all in Nepali Languages (used in North East India). LPC analyzes the speech signal by estimating the formants, removing their effects from the speech signal. The process of removing the formants is called inverse filtering, and the remaining signal after the subtraction of the filtered modelled signal is called the residue. Back propagation method is used to train the ANN. For each voice signal, LPC method produces 256 data in a frame. Then, these data become the input of the ANN. The ANN was trained by using 120 data training. This data training includes the pronunciation of the six words used as the command, which are created from 20 different people. Experimental results show that the highest recognition rate that can be achieved by this system is 94%.

@article{noauthororeditor, abstract = {The analog speech signal can be used for interacting with machines, computers or robots. In this case, speech algorithm is capable to recognize the voice commands that are given as inputs to a mobile robot through wireless XBee modules. It is actually a form of Word Recognition. In this presented paper, a voice command recognition system is going to be developed by using Artificial Neural Network (ANN). The Commands that used here are all in Nepali Languages (used in North East India). LPC analyzes the speech signal by estimating the formants, removing their effects from the speech signal. The process of removing the formants is called inverse filtering, and the remaining signal after the subtraction of the filtered modelled signal is called the residue. Back propagation method is used to train the ANN. For each voice signal, LPC method produces 256 data in a frame. Then, these data become the input of the ANN. The ANN was trained by using 120 data training. This data training includes the pronunciation of the six words used as the command, which are created from 20 different people. Experimental results show that the highest recognition rate that can be achieved by this system is 94%. }, added-at = {2018-07-17T11:43:47.000+0200}, author = {Rai, Neerparaj and Rai, Bijay}, biburl = {https://www.bibsonomy.org/bibtex/20ed83b621f48b8b3cb1ef27f47eaac13/electical12345}, interhash = {7c0a4e754c155628b9c0c7a0afab69e1}, intrahash = {0ed83b621f48b8b3cb1ef27f47eaac13}, issn = {2394 - 0816}, journal = {International Journal of Applied Control, Electrical and Electronics Engineering (IJACEEE) }, keywords = {Feed-forward Linear Mobile Neural Robot Speech back-propagation coding networks predictive recognition}, language = {English}, month = nov, number = 4, pages = {13-22}, timestamp = {2018-07-17T11:43:47.000+0200}, title = {AN ANN BASED MOBILE ROBOT CONTROL THROUGH VOICE COMMAND RECOGNITION USING NEPALI LANGUAGE}, url = {http://airccse.com/ijaceee/papers/2414ijaceee02.pdf}, volume = 2, year = 2014 }