Sie sind auf Seite 1von 21

|  


 

 

 


 


   
 !"!"#
m Introduction
m Project Beneficiaries
m General Objectives
m Modules
m Java Speech API
m Interfaces and Methods
m Screen shots
m ³Demo´
m Future Enhancements
m Thank you
6
 
 

m This project is done in Capgemini.
m Under the guidance of Mr. Srini
Kancha, Senior Project Manager.
m Capgemini serves industries like
Automotive, Consumer Products,
Financial Services, Health, Retail etc.
m My project comes under consumer
products.
$ %
  

m Kisually impaired people


m Potential users of Computer System
m Students and researchers
m IT companies
m General public
w
&$  '

This project performs the task of


developing an application
program which can read out an
input text typed at a source.
Ú&
m „  

Process the input text to determine


where paragraphs, sentences and
other structures start and end. For
most languages, punctuation and
formatting data are used in this
stage.
Ú&
m |   



Analyze the input text for special


constructs of the language. In
English, special treatment is required
for abbreviations, acronyms, dates,
times, numbers, currency amounts,
email addresses and many other
forms.
Ú&
m |  
 


Convert each word to › .


. A
phoneme is a basic unit of sound in a
language. US English has around 45
phonemes including the consonant
and vowel sounds. Different
languages have different sets of
sounds (different phonemes).
Ú&
m 2
 

Process the sentence structure, words


and phonemes to determine appropriate
› for the sentence. This includes
the pitch (or melody), the timing (or
rhythm), the pausing, the speaking
rate, the emphasis on words and many
other features.
Ú&
m [  

The phonemes and prosody


information are used to produce the
audio waveform for each sentence.
The current systems do it by
à à  of chunks of recorded
human speech, or  
 

.

 

.
' (6
m The Java Speech API enables developers
of speech-
speech-enabled applications to
incorporate more sophisticated and
natural user interfaces into Java
applications and applets.

m Two core speech technologies are


supported through the Java Speech API:
API:
‡
à à  
‡
à
 

.

 

.
¢  
  
  
m Provide support for speech synthesizers and for
both command-
command-and-
and-control and dictation speech
recognizers.
m Provide a robust cross-
cross-platform, cross-
cross-vendor
interface to speech synthesis and speech
recognition.
m Enable access to state-
state-of
of--the-
the-art speech
technology.
m Support integration with other capabilities of the
Java platform, including the suite of Java Media
APIs.
m Be simple, compact and easy to learn.
6
  
Ú 
m com.sun.speech.freetts.voice
‡ Class Koice
‡ allocate()
‡ deallocate()
‡ getDomain()
‡ speak()

m com.sun.speech.freetts.KoiceManager
‡ KoiceManager getInstance()
‡ getKoice()
Ú)
h 

 

m [ith various types of given text the
TTS conversion tool will be tested for
naturalness and accuracy and
examined by linguistic experts to
achieve more correct pronunciation.
The outcomes of these examinations
shall be incorporated to the TTS.
h 

 

m A new button is created by name ³Image
converter´

m This can be used to recognize the


characters of languages like Chinese,
Japanese, Mongolian.

m Each character of that language is


recognized and converted into English and
then converted into speech.
h 

 


m Input text which is converted into


speech is stored as a wave file.

m Stream the audio thus obtained to a


destination, which can be any
computer in a network.
Thank you
one and all

Das könnte Ihnen auch gefallen