JOINT FACTOR ANALYSIS SCORING FOR SPEECH PROCESSING SYSTEMS

摘要

Method, system, and computer program product are provided for Joint Factor Analysis (JFA) scoring in speech processing systems. The method includes: carrying out an enrolment session offline to enrol a speaker model in a speech processing system using JFA, including: extracting speaker factors from the enrolment session; estimating first components of channel factors from the enrolment session. The method further includes: carrying out a test session including: calculating second components of channel factors strongly dependent on the test session; and generating a score based on speaker factors, channel factors, and test session Gaussian mixture model sufficient statistics to provide a log-likelihood ratio for a test session.