Adapting End-to-End Neural Speaker Verification to New Languages and Recording Conditions with Adversarial Training
원문 초록
In this article we propose a novel approach for adapting speaker embeddings to new domains based on adversarial training of neural networks. We apply our embeddings to the task of text-independent speaker verification, a challenging, real-world problem in biometric security. We further the development of end-to-end speaker embedding models by combing a novel 1-dimensional, self-attentive residual network, an angular margin loss function and adversarial training strategy. Our model is able to learn extremely compact, 64-dimensional speaker embeddings that deliver competitive performance on a number of popular datasets using simple cosine distance scoring. One the NIST-SRE 2016 task we are able to beat a strong i-vector baseline, while on the Speakers in the Wild task our model was able to outperform both i-vector and x-vector baselines, showing an absolute improvement of 2.19% over the latter. Additionally, we show that the integration of adversarial training consistently leads to a significant improvement over an unadapted model.
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
DS-TDNN: Dual-stream Time-delay Neural Network with Global-aware Filter for Speaker Verification
Cross-modal Audio-visual Co-learning for Text-independent Speaker Verification
Asymmetric and trial-dependent modeling: the contribution of LIA to SdSV Challenge Task 2
Enhancement of a Text-Independent Speaker Verification System by using Feature Combination and Parallel-Structure Classifiers
VoiceExtender: Short-utterance Text-independent Speaker Verification with Guided Diffusion Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.