Scribd
Upload
95 views14 pages

Voice Recognition System: Third Year Electronics, Third Year Electronics

The document discusses voice recognition systems and how they work. It describes how humans recognize speech through articulation and sound waves processed by the brain. Computers can perform voice recognition through digitization, acoustic analysis of speech signals, and linguistic interpretation. Voice recognition systems can be isolated, continuous, speaker-dependent, or speaker-independent. The key steps to creating a voice recognition system are speech acquisition, analysis, and developing a user interface. Challenges include training systems to recognize different accents and developing technology that can understand speech in noisy environments.

Uploaded by

Nimesh Salunkhe
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
95 views14 pages

Voice Recognition System: Third Year Electronics, Third Year Electronics

The document discusses voice recognition systems and how they work. It describes how humans recognize speech through articulation and sound waves processed by the brain. Computers can perform voice recognition through digitization, acoustic analysis of speech signals, and linguistic interpretation. Voice recognition systems can be isolated, continuous, speaker-dependent, or speaker-independent. The key steps to creating a voice recognition system are speech acquisition, analysis, and developing a user interface. Challenges include training systems to recognize different accents and developing technology that can understand speech in noisy environments.

Uploaded by

Nimesh Salunkhe
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 14

Voice Recognition System

Ashwin Sinha, Balram Pandey Third Year Electronics, Third Year Electronics [email protected] [email protected]

INTRODUCTION

Voice Recognition Systems are those systems which can recognize the voices of the individuals

How Humans do This????????

Articulation produces sound waves which the ear conveys to the brain for processing

How might computers do this????

Digitization Acoustic analysis of the speech signal Linguistic interpretation

Isolated Systems requires a brief pause between the spoken words. While Continuous Systems doesnt. Speaker Dependent Systems recognize speech from only one speaker.

While Speaker-Independent Systems can recognize anyones speech.

How to create a Voice Recognition System

Speech Acquisition(Collection). Speech Analysis. User Interface Development.

Speech Acquisition

For training purpose the speech is acquired using the microphone, for the analysis. The sound card of PC converts the Analog Speech input into digital format for further analysis.

Speech Analysis

The First important step in Speech Analysis is to separate each word from the ambient noise. Further each spoken word is compared with the inbuilt acoustic model or dictionary which is created during the training session. The above step is done with the help of an efficient speech detection algorithm.

User Interface Development

Final Step is to Develop a User Interface, so that all users can use these system with ease. For Example: Speech Recognition System of Windows 7 looks so compact & is as shown below.

Taking Speech Recognition System To New Level

With the help of current trends in technology we can interpret these voice recognition systems for hearing handicapped persons in glasses.

How speech to text glasses work

Prototype Created By Mads hindhede & produced by BabelFisk. BabelFisk is essentially speech recognition software tied in with hearing aid algorithms that help recognize speech in the midst of white noise. Once words are heard, theyre converted to text on the fly. Embedded controllers turn this heavy task into an easily manageable one, while 2 microphones work together to show which direction the sound is coming from. And if youd like to get creative, you could use this lovely device for your schoolwork or office work. BabelFisk can be used to take dictation at meetings and lectures, saving the sound info on flash memory in both audio and text format. Super fabulous and awesome for both the hearing impaired and students.

The Big Challenge.

Training the device to work with most frequently spoken english ascent for each country. Projecting the text such a way that in can be read easily with human eye. Developing a powerful speech spotter technology that can detect speech even in noisy environment.

What are drawbacks of current speech recognition softwares till date.

Drawbacks Inability to sense Indian English ascent.


Cannot be used in heavy noisy environment. For completely accurate results a person should speak slowly.

How to overcome Choose more than 1 developer from India that can speak Indian English ascent. Develop an improved noise cancellation device that cancels noise above certain amplitude. Use automatic text correctors like in WORD processors to get error free sentences.

Thank You

You might also like