I am trying to design a Speech Recognition Engine for MS Windows through VC++ v6.0.
Can you please suggest me, what should I do and what will I need for this.
I am intrested in making the Speech Recognition Engine which will just take our speech as input and give the corresponding text as output.
Q: What will I need to make this?(Knowledge, Software etc)
Q: How could I interact with the "Microphone" which will take the i/p?
Q: How could I break the i/p audio into mathematical representation of audio?(wave form) to Identify the speech.
Q: It is clear, that a Database will be needed, but how to use that database to compare voice with the strings stored?
Several Doubts I have...its a endless list.
waiting for replies