project indesh
Download as PPTX, PDF3 likes895 views
The document proposes a sign language to multi-language speech converter system. The system uses gesture recognition technology to identify sign language gestures and convert them to text, which is then passed to a text-to-speech processor to output speech in multiple languages such as Hindi or English. The system is intended to help visually impaired, vocally disabled, and aged persons communicate more easily. It detects hand gestures using flex sensors and microcontrollers, encodes the gestures, transmits the data via RF, decodes and converts the gestures to text using a database, and synthesizes speech output through a text-to-speech processor and speaker.
![Literature Search
Arokia Raj et al in [1]. This paper explained the nature and
difficulties associated with building text processing components of
TTS systems in Indian languages. They discussed the relevancy of
font identification and font-to-Akshara conversion and proposed a
TF-IDF based approach for font-identification and a novel approach
of conversion from font-to-Akshara using the shapes of the glyphs
and the assimilation rules was explained.
Kaveri Kamble et al in [2] Proposed a System Translation of Text to
Speech Conversion for Hindi Language. A database has been created
from the various domain words and syllables. The given text is
analyzed and syllabified based on the syllable segmentation rules.
6](https://image.slidesharecdn.com/e2e8b9d4-8b43-4cd8-82d6-8af9be6103c3-160210023805/85/project-indesh-6-320.jpg)
![Literature Search
Hay Mar Htun, Theingi Zin et al in [5] Proposed a system Text
To Speech Conversion Using Different Speech Synthesis.
Develop a TTS model for numbers and words in MATLAB
and discuss the speech generating technology concatenative
synthesis and is operations and types Unit Selection Synthesis,
Diphone Synthesis and Domain Synthesis.
Francesc Al´ıas, Joan Claudi Socor´o et al in [6] discuss a
multi-domain text-to-speech (MD-TTS) synthesis strategy for
generating speech among different domains and so increasing
the flexibility of high quality TTS systems
7](https://image.slidesharecdn.com/e2e8b9d4-8b43-4cd8-82d6-8af9be6103c3-160210023805/85/project-indesh-7-320.jpg)
![Literature Search
Mithileysh Sathiyanarayanan et al in [7] proposed an
unmanned ground vehicle (UGV) capable of being controlled
using hand gestures.
R.Sandanalakshmi, P.Abinaya viji et al in[8] proposed that
speech to text converter consist of two stages front end
analysis and pattern recognisation.
Moniruzzaman bhuiyam and Rich Picking et al in[13] Gesture
controlled user interface and identify trends in technology
,application and usability.
8](https://image.slidesharecdn.com/e2e8b9d4-8b43-4cd8-82d6-8af9be6103c3-160210023805/85/project-indesh-8-320.jpg)
project indesh
- 1. Under Supervision of: Presented By: Mr. Mayank Tripathi Vibek Kumar Maurya Lecturer Roll. No. 1216630049 Electronics Department EL – Final Year Dr. A.I.T.H. Kanpur EL- Final Year Sign Language to Multi Language Speech Converter 1 Dr. Ambedkar Institute of Technology for Handicapped Kanpur U.P -208024
- 2. "Disability will affect the lives of everyone at some point in their life, it is time society changed to acknowledge this" Disabled World 2
- 3. Introduction The word “Disabled" is defined as having a physical or mental disability : unable to perform one or more natural activities (such as walking or seeing) because of illness, injury, etc. 3 Figure. 1
- 4. Facts Over a billion people, around 15% of the world's population, have some form of disability. Between 110 million and 190 million adults worldwide have significant difficulties in functioning. Physical disability is defined as when a person's physical functioning, mobility, dexterity, or stamina is limited. Rates of disability are increasing due to population aging and increases in chronic health conditions - among other causes. 4
- 5. Assistive Technology Assistive Technology (AT) includes a range of technologies, which enable people to build on their abilities and participate as fully as possible at home, school, work and in their community. AT is used to describe both the products and the services for people with special needs. 5 Figure. 2
- 6. Literature Search Arokia Raj et al in [1]. This paper explained the nature and difficulties associated with building text processing components of TTS systems in Indian languages. They discussed the relevancy of font identification and font-to-Akshara conversion and proposed a TF-IDF based approach for font-identification and a novel approach of conversion from font-to-Akshara using the shapes of the glyphs and the assimilation rules was explained. Kaveri Kamble et al in [2] Proposed a System Translation of Text to Speech Conversion for Hindi Language. A database has been created from the various domain words and syllables. The given text is analyzed and syllabified based on the syllable segmentation rules. 6
- 7. Literature Search Hay Mar Htun, Theingi Zin et al in [5] Proposed a system Text To Speech Conversion Using Different Speech Synthesis. Develop a TTS model for numbers and words in MATLAB and discuss the speech generating technology concatenative synthesis and is operations and types Unit Selection Synthesis, Diphone Synthesis and Domain Synthesis. Francesc Al´ıas, Joan Claudi Socor´o et al in [6] discuss a multi-domain text-to-speech (MD-TTS) synthesis strategy for generating speech among different domains and so increasing the flexibility of high quality TTS systems 7
- 8. Literature Search Mithileysh Sathiyanarayanan et al in [7] proposed an unmanned ground vehicle (UGV) capable of being controlled using hand gestures. R.Sandanalakshmi, P.Abinaya viji et al in[8] proposed that speech to text converter consist of two stages front end analysis and pattern recognisation. Moniruzzaman bhuiyam and Rich Picking et al in[13] Gesture controlled user interface and identify trends in technology ,application and usability. 8
- 9. Inferences Drawn Out of Literature Review A database has been created from the various domain words and Syllables. The given text is analyzed and syllabified based on segmentation rules. The and desired speech is produced by Concatenative speech Synthesis approach, and a system Develop For visually impaired person. Text to speech system for Hindi using English language is able to speak a loud Hindi word which is typed in English. Gesture interface is an important technology that support the non-verbal communication language to verbal communication. 9
- 10. Scope of the Proposed system To Help the Visually Impaired, Vocally Disabled Aged Persons Patient admitted in Hospital 10 Figure. 3
- 11. Proposed System Technology used For Proposed Project Gesture Recognition Technology Text To Speech Technology A Device that convert sign language in multiple speech language. 11
- 12. Block Diagrams Proposed System Micro- Controller Atmega 16 Flex Sensor Compara -tor Encoder RF Trans- mitter 12 Figure. 4 Block Diagram Of Transmitter
- 13. Block Diagrams Proposed System Receiver Decoder Display TTS processor Micro- Controller Atmega 16 Audio amplifier Speaker 13 Figure. 5 Block Diagram of Receiver
- 14. Gesture Recognition Technology Gesture Recognition is the process of understanding and interpreting meaningful movements of the hands, arms, face, or sometimes head. Gesture Recognition is to recognize specific human Gestures and process them to control device or convey some meaning full data. 14
- 15. Text To speech Technology Text To Speech (TTS) synthesis is to convert input text into intelligible and natural sound speech. Text Analysis Phonatic Analysis Prosodic Analysis 15
- 16. Block Diagram of Text to Speech Text analysis Phonetic conversion Prosodic phrasing Speech database Unit selection synthesis Concatenate speech Input text Speech Figure. 6 Block Diagram of Text to Speech
- 17. Flow chart for Speech to Text Start Input number Compare and extract number Compare and concatenate number Output speech End Lexicon of digit Recorded sounds 17Figure. 7 Block Diagram of Text to Speech
- 18. Components list Flex sensors Microcontroller Comparator RF Encoder/Decoder Transmitter/Receiver Text To Speech Processor Display Speaker Audio Amplifier 18
- 19. Flex Sensor 19 Figure. 8 Flex Sensor Angle Displacement Measurement Height: 0.43mm (0.017") Flat Resistance: 10K Ohms Resistance Tolerance: ±30% Bend Resistance Range: 60K to 110K Ohms Key Features
- 20. Micro-Controller 20 Figure 9 Micro-Controller Atmega 16 8-bit Microcontroller with 16K Bytes In-System Programmable Flash Memory 131 Powerful Instructions Up to 16 MIPS Throughput at 16 MHz Key Features
- 21. Encoder 21 Figure . 10 Encoder
- 23. RF Transmitter and Receiver 23 Figure. 12 RF Transmitter and Receiver Range in open space(Standard Conditions) : 100 Meters RX Receiver Frequency : 433 MHz RX Operating Voltage : 5V TX Frequency Range : 433.92 MHz TX Supply Voltage : 3V ~ 6V Key Features
- 24. Text To Speech Processor 24 Figure . 13 Text To Speech Processor The TTS256 is an 8-bit microprocessor programmed with 600 letter-to-sound rules for the automatic, real-time translation of English text to allophone addresses.
- 25. Speaker 25 Figure. 14 Speaker Small Size Power rating: 0.5W Impedance: 8 ohm Key Features
- 26. Liquid Crystal Display (16x2 LCD) 26 Figure. 15 Display
- 27. Circuit Diagram of Transmitter 27
- 28. Circuit Diagram of Receiver 28
- 29. Software's • Proteus 8.1 • Win AVR • Atmel Studio 6 • MATLAB 29
- 30. Conclusions Assistive Technology service that directly assists a seekers with a disability in the selection, acquisition, or use of an assistive technology device. Our device Help the Visually Impaired, Vocally and Aged Persons at every steps of thier lifes. Device is proposed for multi language communication system like Hindi, English or any other language with sign language. 30
- 32. Estimated Cost for The Proposed Work The estimated cost for the proposed work is in between 8000 – 10000 Rs. 32
- 33. PERT CHART 33
- 34. References 1) Arokia Raj, Tanuja Sarkar, Satish Chandra Pammi, Santhosh Yuvaraj, Mohit Bansal, Kishore Prahallad, ‘Text Processing for Text-to-Speech Systems in Indian Languages’ . 2) Kaveri Kamble and Ramesh Kagalkar, ‘Translation of Text to Speech Conversion for Hindi Language’ . 3) Gargi Rajadhyaksha, Siddharth Mody and Sneha Venkateswar, ‘Text to Speech Converter’ . 4) Jaka Sodnik and Sašo Tomažičdescribes, ‘Spatial Speaker: 3D Java Text-to-Speech Converter’ . 5) Hay Mar Htun, Theingi Zin and Hla Myo Tun, ‘Text To Speech Conversion Using Different Speech Synthesis’ . 34
- 35. References 8) Nabil Eid, ‘Innovation and technology for person with disabilities’ . 9) Marcelo M. Wanderley, ‘Gesture control of music’ . 10) Padmavathi. S, Saipreethy M.S. and Valliammai. V , ‘Indian sign language character recognition using neural networks’ . 11) Noor Adnan ibraheem, RafiqulZaman Khan, ‘Survey on various Gesture Recognition technologies and techniques’ . 12) Sangam P. Borkar and Prof. S.P. Patil, ‘Text to speech system for konkani (goan) language’ . 13) Moniruzzaman bhuiyam and Rich Picking,‘gesture controlled user interface and identify trends in technology ,application and usability. recognition process was complex 35
- 36. 36 Thank you