svm_scoring¶

svm_scoring provides functions to perform speaker verification by using Support Vector Machines.

svm_scoring.svm_scoring(svm_filename_structure, test_sv, ndx, num_thread=1)[source]¶

Compute scores for SVM verification on multiple threads (two classes only as implementeed at the moment)

Parameters

svm_filename_structure – structure of the filename where to load the SVM models
test_sv – StatServer object of super-vectors. stat0 are set to 1 and stat1 are the super-vector to classify
ndx – Ndx object of the trials to perform
num_thread – number of thread to launch in parallel

Returns

a Score object.

svm_scoring.svm_scoring_singleThread(svm_filename_structure, test_sv, ndx, score, seg_idx=None)[source]¶

Compute scores for SVM verification on a single thread (two classes only as implementeed at the moment)

Parameters

svm_filename_structure – structure of the filename where to load the SVM models
test_sv – StatServer object of super-vectors. stat0 are set to 1 and stat1 are the super-vector to classify
ndx – Ndx object of the trials to perform
score – Scores object to fill
seg_idx – list of segments to classify. Classify all if the list is empty.