Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition
Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy loss with softmax. However, this kind of loss function does not explicitly encourage inter-class separability and intra-class compactness. As a result, the embeddings are not optimal for speaker recognition tasks. In this paper, to address this issue, three different margin based losses which not only separate classes but also demand a fixed margin between classes are introduced to deep speaker embedding learning. It could be demonstrated that the margin is the key to obtain more discriminative speaker embeddings. Experiments are conducted on two public text independent tasks: VoxCeleb1 and Speaker in The Wild (SITW). The proposed approach can achieve the state-of-the-art performance, with 25% ~ 30% equal error rate (EER) reduction on both tasks when compared to strong baselines using cross entropy loss with softmax, obtaining 2.238% EER on VoxCeleb1 test set and 2.761% EER on SITW core-core test set, respectively.
Code (0)
등록된 구현이 없습니다.
Tasks
Speaker RecognitionSimilar Papers 제목 키워드 기반
Improved Large-margin Softmax Loss for Speaker Diarisation
Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers. It is well-known that large-margin training can improve…
A Study on Angular Based Embedding Learning for Text-independent Speaker Verification
Learning a good speaker embedding is important for many automatic speaker recognition tasks, including verification, identification and diarization. The embeddings learned by softmax are not discriminative enough for ope…
Speaker RecognitionSpeaker VerificationText-Independent Speaker VerificationSeeing voices and hearing voices: learning discriminative embeddings using cross-modal self-supervision
The goal of this work is to train discriminative cross-modal embeddings without access to manually annotated data. Recent advances in self-supervised learning have shown that effective representations can be learnt from …
Lip ReadingSelf-Supervised LearningSpeaker RecognitionNeural i-vectors
Deep speaker embeddings have been demonstrated to outperform their generative counterparts, i-vectors, in recent speaker verification evaluations. To combine the benefits of high performance and generative interpretation…
Speaker RecognitionSpeaker VerificationAdditive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representations
Self-Supervised Learning (SSL) frameworks became the standard for learning robust class representations by benefiting from large unlabeled datasets. For Speaker Verification (SV), most SSL systems rely on contrastive-bas…
Self-Supervised LearningSpeaker Verification