LEAP System for SRE19 CTS Challenge -- Improvements and Error Analysis
This work addresses speaker verification for telephony applications, but it is incremental, building on existing methods like x-vector embeddings.
The paper tackled speaker verification in challenging conditions by improving the back-end system modeling of the LEAP SRE system for the SRE19 CTS challenge, resulting in significant improvements through system combination and additional gains from score normalization and calibration.
The NIST Speaker Recognition Evaluation - Conversational Telephone Speech (CTS) challenge 2019 was an open evaluation for the task of speaker verification in challenging conditions. In this paper, we provide a detailed account of the LEAP SRE system submitted to the CTS challenge focusing on the novel components in the back-end system modeling. All the systems used the time-delay neural network (TDNN) based x-vector embeddings. The x-vector system in our SRE19 submission used a large pool of training speakers (about 14k speakers). Following the x-vector extraction, we explored a neural network approach to backend score computation that was optimized for a speaker verification cost. The system combination of generative and neural PLDA models resulted in significant improvements for the SRE evaluation dataset. We also found additional gains for the SRE systems based on score normalization and calibration. Subsequent to the evaluations, we have performed a detailed analysis of the submitted systems. The analysis revealed the incremental gains obtained for different training dataset combinations as well as the modeling methods.