An intreresting conversation about the state of art in sppech recognition appeared in PC Magazine. The key point is:
So, there is nothing really wrong [with speech recognition today] except that we are just at the beginning of this technology. But the surprising thing is that [at] the end, if you compare [a computer’s ability to understand speech] to human performance, it might not be too far apart. At IBM, we have this Superhuman Speech Recognition [program] that has a goal to get there, comparable to human performance, in the next five years.
sir, i am an undergraduate interested in speaker recognition n related topics. could u please give a brief overview as to how this technology works or any related links.
Speaker recognition techniques try to determine who the speaker is based on specific speech characteristics and patterns in audio signals. Currently most techniques use spectral characteristics, but soon the language usage is also likely to become an important component of speaker recognition.
There are many conferences and jurnals related to this field. Try starting with ASSP under IEEE and from there you will get pointers to many other sources.