摘要 |
<p>PROBLEM TO BE SOLVED: To improve speaker recognition performance. SOLUTION: When a speech for model registration (or speech for model update) is inputted, it is converted into a time series of feature parameters (S1 ), and a model (HMM) for the speech is generated from the time series and registered (or updated)(S2 ). Then an assumed person is regarded as a registered person other than the person himself or herself, speaker recognition experimentation is carried out by using the registered speech (or updated speech), andϕ'=wϕ1 +(1-w)ϕ0 , w=2/(1+exp(0.25t) (t=0, 1, 2...; model update frequency) are calculated from a threshold valueϕ1 which provides an assumed person acceptance rate that is the upper-limit value (x) of an estimated error rate of the system than the valueε0 where the very person rejection rate and assumed person acceptance rate are equal and the threshold valueϕ0 ofε0 , so thatϕis registered (or updated) as a threshold value (S5 ).</p> |