1. A presentation on Basics of Speech Recognition Systems
- Sushant S. Patil (SE ELN)

2. Introduction
How does our brain recognize
sound????
Sound wave sampling
Basic hardware idea
The software algorithm
What’s there in future ??

3. Introduction Current software systems - Dragon Windows 7 VoiceXML
Sound recognition – a natural act than any other
Will lead our life in more intuitive way
More user friendly & interactive.

4. How our brain goes about it ??
Why can’t a dumb speak ??
Why can’t child speak ???
Have you ever stumbled upon a word – that you thought is different which others mean a different one ????
Brain is first to be trained & then used.

5. Types of SR systems
Continuous Speech
Dictation
Command & Control

6. Sound Wave Has frequency range of 80 Hz – 5000Hz.
Can be converted to electronic i.e. Analog signal easily.
But can that be stored ??????

7. Flowchart

8. The frequency Spectrum of word “Hello”

10. Every time a user speaks a word it sounds different
Every time a user speaks a word it sounds different. Users do not produce exactly the same sound for the same phoneme.
The background noise from the microphone and user’s office sometimes causes the recognizer to hear a different vector than it would have if the user was in a quiet room with a high quality microphone.
The sound of a phoneme changes depending on what phonemes surround it. The "t" in "talk" sounds different than the "t" in "attack" and "mist".
The sound produced by a phoneme changes from the beginning to the end of the phoneme, and is not constant. The beginning of a "t" will produce different feature numbers than the end of a "t".

11. The SR Jargon Features Hidden Markov Model Triphones Disambiguation
FFT(Fast Fourier Transform)

12. Ambiguity
“Recognize speech" and “Wreck a nice beach" quickly; They both sound similar.
Too,Two & To….

13. The main challenges Low signal-to-noise ratio Overlapping speech
Intensive use of computer power
Homonyms

14. Basic Hardware Idea
A-D converter
A digital Sampler

15. HM2007

16. The software algorithm
Hidden Markov Model – The Smart probibility Approach

17. Future Opportunities Biometrics Voice controlled Bots Dictation
A helping tool for disabled
Interactive system
Software enhancement
Literary everywhere……..

18. VR main challenges

19. THANK YOU