Science, Technology and Development ISSN : 0950-0707

Keyword Based Technique Using Python for C#

Somnath Hase Dr. Sunil Nimbhore Department of CS Department of CS & IT Smt. S. K. Gandhi Arts, Amolak Science & Dr.Babasaheb Ambedkar Marathwada P. H. Gandhi Commerce College, Kada, University, Aurangabad, (MS), India. (MS), India.

Abstract: awareand lacking what RSI is or how The Programming Language is serious it can be. text-oriented to develop software, with a Braille, gives the idea that no keyboard for input and as of typing development has empowered visually program source code.This content- impaired and outwardly disabled arranged nature of programming dialects individuals for contributing assistive is a barrier to people experiencing arms innovations that have madeComputers handicap. A person with sound and the Internet accessible. In a knowledge, splendid brain, and potential programming language, a visually for programming aptitudes also impaired programmer takes more time to experiences arm wounds or being fragile find syntactic errors than a sighted couldn't turn into a good software programmer. Novice programmer takes engineer. In case, if theprogrammer more time as it has to learn syntax as memorizes the syntax and keywords of well as programming skills the programming language then he will simultaneously.The text editor is an good programmer. Inthe essential instrument for writing computer proposedresearch programmer will speak programs. The text Editors are in English like a statement and code in manipulated entirely via keyboard and C# language will be written accordingly. mouse. Nowadays most peopleuse Keyword: Integrated Development Environment Text to Speech, SAPI,ASR, RSI,C# (IDE) that enables not only writing code but help to compile and debug a Introduction program.This is usually for any The software development programming language. While Text process is comprised of reasonably text- editors only allow editing files, but they intensive tasks such as program are not based on a particular language, composition, editing, and navigation. but on any sort of files. Apart from this, the tools that are used Speech Recognition is a boon for for the programming environment are programmers suffering from RSI because also text Oriented. All these results in itallows doing work without using long hours of RSI – worsen the situation injured hands. “Oneof the goals of for the programmer.Repetitive Strain speech recognition is toallow natural Injury (RSI) is a potentially adverse communication between humans condition resulting from overuse of the andcomputers via speech, where natural hands to perform a repetitive task, like impliessimilarity to the ways humans typing, clicking a mouse, or writing. The interact with eachother” [1].Speech person often using a computer regularly recognition is the ability to recognize and is at risk and should know about RSI. comprehend the spoken words of any Unfortunately, most people are not machine or electronic device. The words

Volume X Issue II FEBRUARY 2021 Page No : 453 Science, Technology and Development ISSN : 0950-0707

are translated into a format that is programs) and then displays it in a way machine-readable.For persons with that humans can understand (text, emotional or physical disabilities, Speech images, and sound). A graphical user recognition is useful. Many disabled interface programmers using voice recognition for programming are not well mapped onto the available application and programming environment. It is an effective solution that solves the problems described above. This solution requires that the should be attachedto the computer. A programmer should have all the essential C# language comprehension. He will speak his codein English but complies with C# Syntax and Semantics.Only code writing features will be supported by the framework.The user copies and pastes this code into any C# compiler and compiles the code. Fig. 1 System Structure

Proposed System The system is developed with on (GUI) gives an interface for a user to window environment. In 2007, ’s interact with the systems. It is more user- attempted speech Recognition called as friendly than a text-based command-line GOOG-441, which is a speech-enabled interface, such as MS-DOS. business finder that took in user-spoken A programmer will speak city and state, followed by a business English-like statements using a name. Google developed speaker- microphone and a voice to Text independent speech recognition using converter will convert this statement into deep neural networks and Hidden text. After this, C# syntax and semantics Markov Models (DNN-HMM). It are applied tothis text to produce the performs a lot of computing for the structured C# code. speech recognition task.The user starts a conversation with the system via an Related Research application using a mic. The user spoken Several other voice programming words are converted into text using the Systems available like VoiceGrip [3] that Google Cloud Application Programming allows the programmer to dictate code Interface (API). It translates the audio using pseudo-code syntax only. Voice sample in real-time format into text. Grip Translates pseudo code to native code in real-time. VoiceGrip uses a simple deterministic parsing algorithm System Structure for coding. The system mainly consists of NaturalJava is a prototype for an five-part as shown in Fig. 1 intelligent natural-languagebased user At the Core, there is Hardware, interface forcreating, modifying, and which is a physical part of the computer. examining Javaprograms. The interface Operating System is often described as a exploits three subsystems. The Sundance translator, which translates the language natural language processing system of the hardware (binary numbers) into accepts Englishsentences as input and the language of the software (written

Volume X Issue II FEBRUARY 2021 Page No : 454 Science, Technology and Development ISSN : 0950-0707

uses information extraction techniques create applications that can understand, for generating case frames representing view, and hear the world around program construction andediting it.Google Cloud Speech API consists of directives. A knowledge-based case Google Translate API and Cloud Vision frame interpreter, PRISM, uses a API in pre-trained machine Learning decision tree to infer program Models.With such a full API, developers modificationoperations from the case can build an application that can display, frames. A Java abstract syntax tree view, hear, and translate.The Google manager, TreeFace, provides the Cloud Speech API helps developers to interface that PRISM uses tobuild and turn audio into text by accessing the API navigate the tree representation of an by using neural network models.More evolving Java program. This paper than 110 languages and variants can be describes the technical details of recognized by the API to serve a global eachcomponent, explain the capabilities user base.It allows writingtext by of the user interface, and present dictating using the microphone, allow examples of NaturalJava in use. [4] voice command and control, or write VoiceCode is a project initiated audio files by recognizing the uploaded by the National Research Council of audioon-demand, also allow Canada. It works with a commercial to integrate with the audio storage in speech recognition program (Dragon Google Cloud Storage. NaturallySpeaking) and an editor (Emacs) and allowsthe programmer to Code Converter produce code by speaking fairly English- Code converter converts listened like pseudocode into a microphone. [ 5] words into C# Code. From the list of the “Programming by voice: A Domain- reserved word of C#, we finda word that specific Application of Speech hasa similar sound. Ex. ‘for’ will have Recognition “Begel describes “Spoken ‘phore’, ‘faure’, ‘fore’, ‘fore-, forr’, Java, a Syntactically similar, yet ‘four’, ‘fourre’, ‘phore’ word with semantically identical variant of java that similar sounds. And ‘char’ will have is easier to speak. An Eclipse IDE plugin ‘chaar’, ‘charr’, ‘charre’, ‘chvre’word called SPEED is made for (SPEech with similar sounds. A separate list of EDitor) to support the combination of words with a similar sound is created in Spoken Java and an associated command C# for each reserved word. Whenever a language [6] user speaks a reserved word that word is converted into text and this text is Leopold and Amber [7] have matched with a list of words.If match developed a method of“writing” code for found converted text is replaced with a Visual Programming Language corresponding reserved word otherwise thatuses a combination of Voice, text is written as it is. handwriting, and VocalProgrammer is I/P: - public static void main significantly different than O/P-public static void main () VoiceXML[8]. VoiceXML is an XML I/P:- using system language for writing voice-enabled O/P: -using System applications, not a general system for I/P: -class myapplication enteringXML documents. O/P- class MyApplication { } Speechto Text Converter I/P: -console readline Machine learning is an O/P: -Console.ReadLine(); important part of the that allows users to I/P: - while

Volume X Issue II FEBRUARY 2021 Page No : 455 Science, Technology and Development ISSN : 0950-0707

O/P: -while () Step 1: Start { Step 2: User Speak word. } Step 3: System listen to User Voice using Microphone. I/P: - a is equal to 1 Step 4: System convert user voice to Text O/P: - a=1 using built-in Google Speech RecognitionSystem. I/P: - for loop Step 5: System Translates Text matches O/P: -for (i=0; i

. Fig. 3. Voice input Recognized Fig. 2 Input/ Output Screen

The above Fig. 2 shows use of the Fig. 4. Output code of C# Program Input/Output User Interface developed word and using google API in python, Fiq.3 shows phrase vocabularies for the designated input voice recognized by the Software, speaker type of system should be grown and Fiq.4 showsthe final output code of in the next few years. A person with RSI will not be able to adapt software C# program in the‘ text file. development environment for long hours in front of a keyboard. It helps Conclusion programmers to make it easier by using Speech Recognition is an voice recognition. The robust solution for untapped source at its present stage. The

Volume X Issue II FEBRUARY 2021 Page No : 456 Science, Technology and Development ISSN : 0950-0707

speech-based programming in C#, in Languages (VL '97) Isle of Capri, which users speak a word that hasa Italy. similar sound to each reserved word of 8. VoiceXML – The World's Leading C#. All user-speech code will be written VoiceXML Advocate in the editor. 9. Gaikwad, S., Gawali, B., and This system is very good for Yannawar, P., (2010). “A Review individuals with disabilities or people on Speech Recognition Technique”. suffering from RSI. It needs a more In International Journal of Computer comprehensive experiments the project. Applications, Vol. 10, No.3 The current implementation of the 10. Schwoebel, J. (2018). An project is best suited for statement-level Introduction to Voice Computing in editing, local level editing, and writing Python. Boston; new source code. Seattle; Atlanta: NeuroLex In the future, this can be further Laboratories. https://github.com/jim- extended to all visual programming schwoebel/voicebook languages as well as all text-oriented 11. Arnold, S., Mark, L., Goldthwaite, programming languages. It can also be J. (2000) “Programming by voice, implemented in a Database management VocalProgramming”. Conference system for query writing. Paper. 12. Baba, N.,Daruisb,D., (2016) References “Repetitive Strain Injury (RSI) 1. Kepuska, V., (2011), “Wake-Up- among Computer Users: A Word Speech Recognition.” IN TECH. CaseStudy in Telecommunication 2. https://docs.microsoft.com/en- Company”.Malaysian Journal of us/archive/msdn- Public Health Medicine. magazine/2006/january/exploring- 13. Torfi, A., (2018) “ SpeechPy- A speech-recognition-and-synthesis- Library for Speech Processing and apis-in-windows-vista Recognition”. The Journal of Open 3. Desilets, A. (2001). “VoiceGrip: A Source Software. Tool for Programming byVoice”. 14. Kaushal, S., Mishra,M., (2020),“A International Journal of Speech Review on Voice Assistance using Technology, 4(2) pp.103-116. Python”. International Research 4. Price, D., Riloff, E., Zachary, J. Journal of Engineering and and Harvey, B. (2000). “NaturalJava: Technology (IRJET) Vol.7 No.09 A Natural Language Interface for 15. https://docs.microsoft.com/en- Programmingin Java “. In proceeding us/azure/cognitive-services/speech- of the International Conference on service/speech-to-text Intelligent User Interfaces. 16. https://cloud.google.com/speech-to- 5. Masuoka, C. (2008).” Java text Programming Using Voice Input”. 17. https://blog.api.rakuten.net/top-10- University of Maryland. best-speech-recognition-apis-google- 6. Begel,A. (2005). “Programming by speech---speechapi-and- Voice: A Domain-specific others/ Application ofSpeech Recognition. AVIOS Speech Technology Symposium–SpeechTek West. 7. Leopold, J., Amber, A.(1997) .” Keyboard less VisualProgramming Using Voice, Handwriting and Gesture” IEEE Symposiumon Visual

Volume X Issue II FEBRUARY 2021 Page No : 457