Speaker verification

A method for use in speaker verification, comprising:

• for each person of a plurality of people forming a cohort:
• receiving a sample of the person's speech;
• estimating a noise measure in the received sample of the person's speech;
• if the estimated noise measure does not meet a predetermined criterion, rejecting the received sample of the person's speech;
• and
• if the estimated noise measure meets the predetermined criterion:
• adding noise to the received sample to form a sample with increased noise;
• extracting features of the sample with increased noise;
• and
• forming a model of the person's speech from the extracted features, and further comprising:
• for an enrolling user:
• receiving a sample of the enrolling user's speech;
• estimating a noise measure in the received sample of the enrolling user's speech;
• if the estimated noise measure does not meet a predetermined criterion, rejecting the received sample of the enrolling user's speech;
• and
• if the estimated noise measure meets the predetermined criterion:
• adding noise to the received sample to form a sample with increased noise;
• extracting features of the sample with increased noise;
• and
• forming a model of the enrolling user's speech from the extracted features,
• such that the models of the speech of the people forming the cohort, and the model of the enrolling user's speech can be used in a speaker verification.