speaker recognition using multimodal fusion techniques
₹12500-37500 INR
Zavřený
Zveřejněno před více než 7 roky
₹12500-37500 INR
Zaplaceno při doručení
speech database as input
fusion techniques are used at feature level extraction and decesion level also.
for feature extraction purpose need wavelet and MFCC ram is attached herewith
For classification need neural and SVM.
DETAILED FLOW OF PROPOSED FLOW block diag
Hello! I think I understand exactly the literature behind your project. I have worked on a very similar project before for real time speaker identification. The choice of mfccs is a good choice. Recently many hybrid algorithms have emerged, and I think it is a good idea to take a look on them before making the final decision.