Triplet Based Embedding Distance and Similarity Learning for Text-independent Speaker Verification
원문 초록
Speaker embeddings become growing popular in the text-independent speaker verification task. In this paper, we propose two improvements during the training stage. The improvements are both based on triplet cause the training stage and the evaluation stage of the baseline x-vector system focus on different aims. Firstly, we introduce triplet loss for optimizing the Euclidean distances between embeddings while minimizing the multi-class cross entropy loss. Secondly, we design an embedding similarity measurement network for controlling the similarity between the two selected embeddings. We further jointly train the two new methods with the original network and achieve state-of-the-art. The multi-task training synergies are shown with a 9% reduction equal error rate (EER) and detected cost function (DCF) on the 2016 NIST Speaker Recognition Evaluation (SRE) Test Set.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Universal Pooling Method of Multi-layer Features from Pretrained Models for Speaker Verification
SHIELD: A Secure and Highly Enhanced Integrated Learning for Robust Deepfake Detection against Adversarial Attacks
A Comparative Evaluation of Deep Learning Models for Speech Enhancement in Real-World Noisy Environments
From Dialect Gaps to Identity Maps: Tackling Variability in Speaker Verification
Investigation of Speaker Representation for Target-Speaker Speech Processing
Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels
토론
이 논문과 연결된 포럼 글이 아직 없습니다.