Anda di halaman 1dari 7

Introduction

Speech recognition is the inter-disciplinary sub-field of computational


linguistics that develops methodologies and technologies that enables the
recognition and translation of spoken language into text by computers. It is also
known as automatic speech recognition (ASR), computer speech
recognition or speech to text (STT). It incorporates knowledge and research in
the linguistics, computer science, and electrical engineering fields.

Speech recognition applications include voice user interfaces such as voice


dialing (e.g. "Call home"), call routing (e.g. "I would like to make a collect
call"), domotic appliance control, search (e.g. find a podcast where particular
words were spoken), simple data entry (e.g., entering a credit card number),
preparation of structured documents (e.g. a radiology report), speech-to-text
processing (e.g., word processors or emails), and aircraft (usually termed direct
voice input).

The term voice recognition or speaker identification refers to identifying the


speaker, rather than what they are saying. Recognizing the speaker can simplify
the task of translating speech in systems that have been trained on a specific
person's voice or it can be used to authenticate or verify the identity of a speaker
as part of a security process.

These speech industries include various such as


Google, Microsoft, IBM, Apple, Amazon many of which have publicized the
core technology in their speech recognition systems as being based on deep
learning.

Page | 1
OBJECTIVE

Our project is on android which is named as "Speech to Text".


The motto of our application is to provide an interface through which users
speech can be converted into the text. The output text then can be share to
different other application according requirement.

The other important objectives of this application are to overtake the traditional
typing strategies for producing the text. This app will also increase the
interactivity between the user and the system.

Page | 2
TOOLS USED IN PROJECT

This project is developed using the tools, which are most suited for development
of the Application Package. These tools are as follows:
1. JAVA
2. Software Development Kit (SDK)
3. Android Studio
4. Android Development Tools (ADT)
5. Android Virtual Device (AVD)

PROGRAMMING LANGUAGE
The programming language used by Android is Java, so we have used core java
for coding services.

The programming language used for frontend coding is JAVA (CORE).


JAVA is used because it is the platform independent language, so the code once
compiled could be used on other operating systems also.

For backend graphics designing XML is used and for speech to text
transformation speech recognizer intent interface is embedded.

System Requirement
Mobile Version: Android 4.1 or upper versions
RAM: 512MB
Permissions: - Audio Recorder, Internet

Page | 3
MODULE USED IN THE PROJECT

The project includes the combination of various set of activities named as


modules for the development of the application. Each activity performs the
specific task and all the activity are related to one another. The activities used in
the project are:

1.SPLASH
The main motive behind creation of Splash screens for mobile apps is to hide
the loading or boot time of the app and make those few seconds engaging for
the users. It isn’t necessary to make a splash screen for your app but it has its
own perks when it comes to first impression on users.

3.HOMEACTIVITY
It is the major activity where various selection option or choices of user are
given.

4.NEPALI SPEECH
This activity will allow to translate Nepali speech to Nepali text with the helps
of speechRecognizerIntent from the google services.

5.HINDI SPEECH
This activity will allow to translate Hindi speech to Hindi text with the help of
speechRecognizerIntent from the google services.

Page | 4
6.ENGLISH SPEECH
This activity will allow to translate English speech to English text with the help
of speechRecognizerIntent from the google services.

7.TEXT_TO_SPEECH
This is an extra feature of the app. This activity is added to increase the usability
and functionality of app. This allow to dedicate the English Text to English
speech.

Page | 5
can
User
select

English Nepali
speak Text to
Speech speech
Speech

Hindi
Speech
Has
A

Has
A EditText

Mic
State Allow

Call English Onclick


Speech Recognizer On pressed Text dictate

Call English
Produce
Call Hindi Speech Recognizer

Speech
Recognizer

English
Produce
Text

Share Produce

Copy Delete

English
Text

Copy
Hindi Share Delete
Mic share
Text

delete
Copy

Fig: ER Diagram of Speech to Text App

Page | 6
DFD

HindiSpeech Speech HindiSpeech


to Text
App

HindiSpeech
HindiSpeech

HindiSpeech
HindiSpeech

Fig: 0 level DFD

Conclusion

Speech to Text app fulfills all its objectives and provides an interface to translate
the user voice into the text. We do our best to develop this app, but as with many
software we rely on Google as our service provider, which might change its
software without notice. Therefore, we cannot be responsible for any data loss,
or failure in the software performance.

Page | 7

Anda mungkin juga menyukai