The objective is to build a “text dependent speaker identification/verification system.”
- Record 5 utterances of the same “key phrase” (at least 0.5 second long, andcan be in any language). Collect the recorded data from all the students registered for this course.
- Extract features using standard cepstra (EE), and LPCC (CSE/PRMLstudents) from ALL the utterances. Keep 3 sequences of feature vectors for every speaker as train templates. Use the remaining two for test.
- Use time synchronous DTW to determine the identity of the speaker.CSE/PRML students perform score normalization (use Z and T norms), and obtain the EER. Others perform closed set identification, and produce a confusion matrix.
