Web Content Display Web Content Display

Project Project

           SRS

  

On

 

 

              "Voice Language Translator"

 

 

 

 

 

 

 

Department of Information Technology

 

 

 

 

 

SUBMITTED BY:

Priyanka Sahni 15502
Abhinav Batra 15446

Nonika Sharma 15497

 

 

Department of  Information Technology(IT)

 

 

 

 

 

 

 

 

 

Dronacharya College of Engineering

Khentawas ,Farrukh Nagar,Gurgaon

 

 

 

 

 

 

 

 

TABLE OF CONTENT

  1. Introduction of the project            ………………………………………………………...  1

 

  1. Motivation behind the project………………………………………………………5
  2. Scope……………………………………………………………………….............5
  3. Theoretical and technical aspects………………………………………………….6

 

  1. Objective of the project…………………………………………………………….9
  2. Hardware and software requirements……………………………………………...9

 

  1. Project design

a.)System design (VLT/FLOWCHART/ERD/UML Diagram/Class diagram)….

 b.)Detailed design(Levels of VLT, Table Description)…………………………..

 

  1. Coding…………………………………………………………………………….10

 

  1. Testing……………………………………………………………………………10

 

  1. Output of the project………………………………………………………………10

 

  1. Future work/Scope of Improvement………………………………………………11

 

  1. References…………………………………………………………………………11

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Abstract:

Current voice Language translation application and services use natural language understanding and natural language processing to forn words and sentsnces. However, these parsing methods concentrate more on capturing keywords and translating them, completely neglecting the considerable amount of processing time involved. In this paper, we are converting voice of different language to any other language.

 

Introduction

This project is aimed at mobile phone especially Android users who can communicate with other users using offline software model that ensures effective real time communication between two users who do not speak a common language while ensuring minimal computing time. User can communicate in any language. Android devices that support VLT(voice Language translation) run in java platform. User just speak any sentence in any language which user know and that language will automatically converted  to listener language in same voice density of speaker.

 

 

 

 

MOTIVATION

The main motivation behind the voice Language translation is to read and listen any language and convert it to listener requirement language .Language has always been the basis of any form of written or speech communication. However, the presence of multiple language and dialects has been a hindrance to effective communication. Especially in a nation like India where the language and dialect changes with region, the requirement of a middle translation layer that can eliminate the linguistic barriers becomes essential. Speakers from different regional identities should be able to interact with one another without the need to understand individual languages.

                           

 

 

Theoretical and technical aspects

 

SEMIOTIC APPROACH

Language system is the part of semiotics dealing with sign systems.

Therefore, semiotic theories may be applied to language functioning. According tothe semiotic approach, translation is language code switching. When translating,we switch from one language to another one.American linguist Roman Jakobson in his article "On Linguistic Aspects of Translation"

spoke of three possibilities of code switching:

  1. Intralinguistic translation, or rewording, i.e. interpreting verbal signsthrough other signs of the same language. This can be done on diachroniclevel: Chaucer's text is translated into modern English. When done onsynchronic level, this kind of code switching is called a paraphrase. Weoften deal with paraphrasing when trying to explain or define things. Forexample, to explain the meaning of the phrase I am not much of a cook,we can paraphrase it by I do not like to cook, or I do not cook well. In thetheory of translation, this type of code switching is called a transformation

 

  1. Interlanguage translation, i.e. substituting verbal signs of one language by verbal signs of another language, or switching from one language code to another one. This type of code switching is translation proper, the object of Translation Studies.

 

  1. Intersemiotic translation, i.e. substituting signs of one semiotic system by signs of a different semiotic system. In its broad meaning, the term implies transmutation and can be illustrated by decoding some ideas and themes expressed, for example, in a poem through the "language" of music or dance.

 

 

COMMUNICATIVE APPROACH

 

 We communicate to transfer information from one person to another. Translation helps people communicate if they speak different languages. Thus, translation is a two-facet phenomenon: on the one hand, it is the process of transferring information; on the other hand, it is the result of this process. By the result is meant a new text created in translating. The communicative situation consists of several elements:

 

          

A speaker or writer (an author) makes a meaningful utterance called the text and addresses it to the listener, reader, or receptor, who understands the purport of the text and reacts to it. The translation situation doubles the elements of communication.8 The receptor of the original text in turn becomes a translator who makes a translated text, or target text intended for the receptor speaking another language:

The source text is the text to be translated. The target text is the end-product, the translated text.

For the translation to be adequate and effective, the target text should be equivalent to the source text. Indeed, when reading tragedies by Shakespeare in Russian, the receptor is but seldom aware that the words s/he sees in the text were not written by Shakespeare but by some other person, a translator. The form of the target text is new but the purport and the content are very close to the original. Paradoxically, the better a translator's work, the less his/her work is observed. The translated text is attributed to the author speaking another language and this text is used everywhere as if it were the original. Thus translation unifies two different language speech acts in one communicative situation. It can be defined as a special type of communication intended to convey information between the participants speaking two different languages. As"translating consists of reproducing in the receptor language the closest natural equivalent of the source-language meaning and secondly in terms of style.

 

Hardware and software requirements

Speech Recognition Component

 The initiator dials a number on his mobile phone. This number is connected to a centralized server. The first phase is the speech recognition component. Speech recognition is the process of converting an acoustic signal captured by the mobile's microphone to a set of meaningful words. An isolated word speech recognition system requires that the initiator on the mobile phone pause briefly between words, whereas a continuous speech recognition system does not. Speech recognition modules also take into consideration the speaking accents of the caller. Recognition is more difficult when vocabularies are large or have many similar-sounding words.

 

B. Language Interpretation and Analysis

The different techniques used for language interpretation can be listed as follows:-

1)Template Matching :-

Template matching checks the source input for commonly used phrases or sentences. Every language consists of a set of commonly spoken words or sentences. Converting such sentences to the target language and replacing when required drastically reduces the processing time needed for translating the sentences.

2) Indexing Frequently Used Words :-

The large lexical database of words will add to the time complexity of the process. The words are indexed based on the number of times a particular word has been used. The probability search algorithm is used to index the words in the database. In probability search the most probable element is brought at the beginning. When a key is found, it is swapped with the previous key. Thus if the key is accessed very often, it is brought at the beginning. Thus the most probable key is brought at the beginning. The efficiency of probability search increases as more and more words are being translated and indexed.

3)Session Based Cache :-

The system maintains a session-based cache for each user requesting for the service. This works on the lines of a web cache which caches web pages. This is done to reduce to reduce bandwidth usage, server load, and perceived lag. It is assumed that when a user engages in a conversation, there are bound to be multiple repetitions of certain words. Based on this assumption, we cache such words along with their translated text so that server processing time is saved.

4) Translation to Target Language:-

After the sentence passes through the first three phases of language interpretation and analysis, the final phase is translation to target language.

 

 

C. Sentence Generation

 

The collective set of translated word is converted to a meaningful sentence generation for the target language. Sentence generation is a natural language processing task of generating natural language from a logical form (set of translated words).

D. Text to Speech Synthesis

 

Text-to-speech synthesizer converts the sentence obtained from the sentence generation module into human speech form in the target language. This is done by using free TTS software. This process can be further explained as follows:-

SCOPE

 

Text-based translation services mainly focus around capturing words and converting them to target language.However, voice based translation services have remained few and slow. This is because most of these models concentrate mainly on language interpretation and language generation. They fail to take into consideration the large amount of back-end processing that takes place while translation. Most translation methods make use of customized dictionaries to find the translated words. However, searching for relevant words and synonyms from

such large dictionaries is slow and time-consuming. More so it also depends on the content of the sentence being translated. In this project, we propose language translation on mobile phones. This project is aimed at mobile phone users who can then communicate with other users, irrespective of the other user's ability to understand the speaker's language.

 

 

 

 

 

 

 

 CONCLUSION

 

Speech technology has now advanced to the stage where it offers great promise for human-computer interaction in a variety of applications. We are moving from a world of the visual paradigm to the voice paradigm. Thus Speech has the potential for future incorporation into a multi-modal interface thus leading to a new era. Techniques like template matching, indexing frequently used words using probability search and session-based cache can considerably enhance processing times. More so, these factors become all the more important when we need to achieve real-time translation on mobile phones.  template matching, indexing frequently used words using probability search and session-based cache can considerably enhance processing times. More so, these factors become all the more important when we need to achieve real-time translation on mobile phones.

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Coding:

 

Converting text to speech java code

 

 

import javax.speech.*;   

import java.util.*;   

import javax.speech.synthesis.*;   

 

public class Text2Speech   

{   

String speaktext;

public void dospeak(String speak,String  voicename)   

{   

    speaktext=speak;   

    String voiceName =voicename;   

    try   

    {   

        SynthesizerModeDesc desc = new SynthesizerModeDesc(null,"general",  Locale.US,null,null);   

        Synthesizer synthesizer =  Central.createSynthesizer(desc);   

        synthesizer.allocate();   

        synthesizer.resume();    

        desc = (SynthesizerModeDesc)  synthesizer.getEngineModeDesc();    

        Voice[] voices = desc.getVoices();     

        Voice voice = null;

        for (int i = 0; i < voices.length; i++)   

        {   

            if (voices[i].getName().equals(voiceName))   

            {   

                voice = voices[i];   

                break;    

            }    

        }   

        synthesizer.getSynthesizerProperties().setVoice(voice);   

        System.out.print("Speaking : "+speaktext);   

        synthesizer.speakPlainText(speaktext, null);   

        synthesizer.waitEngineState(Synthesizer.QUEUE_EMPTY);   

        synthesizer.deallocate();   

    }   

    catch (Exception e)  

    {   

        String message = " missing speech.properties in " + System.getProperty("user.home") + "\n";   

        System.out.println(""+e);   

        System.out.println(message);   

    }   

}   

 

public static void main(String[] args)   

{   

    Text2Speech obj=new Text2Speech(); obj.dospeak("Hello i am kevin ","kevin16");   

}   

}

 

 

 

 

Converting speech to text java code:

 

public class TextSpeech extends ListActivity implements

  TextToSpeech.OnInitListener {

  /** Called when the activity is first created. */

 

 private TextToSpeech tts;

 

 private TextView txtText;

 private List<Message> mess;

 List<String> titless;

 

@SuppressLint("NewApi")

@Override

public void onCreate(Bundle savedInstanceState) {

 super.onCreate(savedInstanceState);

 setContentView(R.layout.speach);

 

 tts = new TextToSpeech(this, this);

 

 

 BaseFeedParser parser = new BaseFeedParser();

 mess = parser.parse();

 titless = new ArrayList<String>(mess.size());

    speakOut();

}

 

@SuppressLint("NewApi")

 @Override

 public void onDestroy() {

 // Don't forget to shutdown tts!

 if (tts != null) {

tts.stop();

tts.shutdown();

  }

super.onDestroy();

  }