This IEEE Paper is on matching the patterns of two audio files to recognize speech. This paper uses FFT and correlation to match the two speech files. As we know, correlation is used to determine the similarity between the two signals. Thus, by correlating the stored signal with the unknown signal, and finding the correlation coefficient the similarity between the two signals can be found out. If the correlation coefficient is close to unity, their exists a strong relation between the two signals and hence, they can be said to be forming same speech pattern.
Its interesting to implement such a thing on a complex processor like DSP.
ReplyDeleteYes, it is just the basics it can be used for higher end applications as well
DeleteAn innovative application of correlation. It can be used for matching various other signals other than just speech.
ReplyDeleteYes, the concept can be applied on signals such as images!
DeleteNice topic!
ReplyDeleteIt can be used in Automatic Voice Recognition Systems as well!
DeleteThank u. There are other blogs as well. Check them out.
DeleteGood topic selection!
ReplyDeleteThank u. There are other blogs as well. Check them out.
Deleteinteresting topic
ReplyDeleteThank u. There are other blogs as well. Check them out.
DeleteNice topic
ReplyDeleteThank u. There are other blogs as well. Check them out.
DeleteSuch an application can be imjplemented on C2000 DSP. It can be used in security systems.
ReplyDeleteYes, also it can be used in home automation systems.
DeleteUse of speech recognition is diverse.
ReplyDeleteCorrelation of speech would be 1 dimensional, while that of images will be 2 dimensional
ReplyDeleteYes, however same algorithm can be used with slight modification for them too.
DeleteThank u. There are other blogs as well. Check them out.
ReplyDelete