HLT-NUS Submission for NIST 2019 Multimedia Speaker Recognition Evaluation
This work addresses speaker recognition in multimedia contexts, which is incremental as it applies existing methods to a new multimodal dataset.
The paper tackles speaker verification using both audio and visual information for the 2019 NIST Multimedia Speaker Recognition Evaluation, achieving an equal error rate of 0.88% and an actual detection cost function of 0.026 on the evaluation set.
This work describes the speaker verification system developed by Human Language Technology Laboratory, National University of Singapore (HLT-NUS) for 2019 NIST Multimedia Speaker Recognition Evaluation (SRE). The multimedia research has gained attention to a wide range of applications and speaker recognition is no exception to it. In contrast to the previous NIST SREs, the latest edition focuses on a multimedia track to recognize speakers with both audio and visual information. We developed separate systems for audio and visual inputs followed by a score level fusion of the systems from the two modalities to collectively use their information. The audio systems are based on x-vector based speaker embedding, whereas the face recognition systems are based on ResNet and InsightFace based face embeddings. With post evaluation studies and refinements, we obtain an equal error rate (EER) of 0.88% and an actual detection cost function (actDCF) of 0.026 on the evaluation set of 2019 NIST multimedia SRE corpus.