Machine learning
Download as PPTX, PDF0 likes138 views
This document discusses a speech to text machine learning project done by group 10. It contains an introduction to machine learning and speech to text. It describes the components of a speech to text system including the interface, voice recognition algorithm (Hidden Markov model and N-gram), and applications in English. It also discusses the architecture, main parts of the project (voice recognition activity, SMS class, XML files), and some code examples. Finally, it discusses the economic feasibility of using the Android platform for this project.
Machine learning
- 1. Apurva Mittal (20141009) Ketan Gyanchandani (20141028) Riya Giri (20141058) Sanjeev Kumar (20141063) Saurabh Ojha (20141064) Vikash Kumar (20141072) Group 10
- 3. What is Machine Learning? Machine learning is a type of artificial intelligence (AI) that provides computers with the ability to learn without being explicitly programmed. Speech to Text as a part of Machine Learning
- 4. Components of Speech To Text Interface
- 5. Voice recognition Algorithm i)Hidden Markov ii) N-gram •It is currently the most successful and most flexible approach to speech recognition. •Speech to text application is adapted to input messages in English.
- 6. • What is Hidden Markov ? • Urn & Ball Model • Development of Hidden Markov Library Hidden Markov
- 7. N-Gram Language Model •N-gram : contiguous sequence of n items from given sequence of text or speech. •What is language model? •Markov Assumption: P(w1 w2 ……wn) ≈ ∏iP(wi/wi-k….wi-1) •Simplest case of markov model is unigram.
- 8. • Unigram Model: P(w1 w2…….wn)≈ ∏P(wi) • Bigram Model: P(wi/w1 w2…….wn) ≈ P(wi/wi-1) • We can extend this to trigram, 4-gram, 5-grams and continue.
- 9. • Hands free computing • Education and daily life • Blindness & Education Problems faced in today’s world
- 11. Architecture
- 13. MAIN PARTS OF THE PROJECT A. Voice Recognition Activity class
- 14. B. SMS class
- 15. C. XML files
- 16. Some Part of Code to trigger Speech to Text 1. Speech is turned into a list 2. Voice recognition result.
- 17. • Operating System used for development id free of cost and so is the eclipse ide used as an interface for application development. • Free use and adaptation of operating system to manufacturers of mobile devices. • Equality of basic core applications and additional applications in access to resources. • Optimized use of memory and automatic control of applications which are being executed. • Quick and easy development of applications using development tools and rich database of software libraries. • High quality of audiovisual content, it is possible to use vector graphics, and most audio and video formats. • Ability to test applications on most computing platforms, including Windows, Linux. Thus saving time and money. Economic Feasibility