Fast Approach to Speaker Identification for Large Population Using MLLR and Sufficient Statistics
In speaker identification, most of the computational processing time is required to calculate the likelihood of the test utterance of the unknown speaker with respect to the speaker models in the database. When number of speakers in the database is in the order of 10,000 or more, then computational complexity becomes very high. In this paper, the authors propose a Maximum Likelihood Linear Regression (MLLR) based fast method to calculate the likelihood from the speaker model using the MLLR matrix. The proposed technique will help to quickly find the best N speakers during identification.