paper-with-me

Papers

Improved Large-margin Softmax Loss for Speaker Diarisation

2019-11-10 · Yassir Fathullah, Chao Zhang, Philip C. Woodland

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 the generalisation ability to unseen data, and its use in such open-set problems has been widespread. Therefore, this paper introduces a general approach to the large-margin softmax loss without any approximations to improve the quality of speaker embeddings for diarisation. Furthermore, a novel and simple way to stabilise training, when large-margin softmax is used, is proposed. Finally, to combat the effect of overlapping speech, different training margins are used to reduce the negative effect overlapping speech has on creating discriminative embeddings. Experiments on the AMI meeting corpus show that the use of large-margin softmax significantly improves the speaker error rate (SER). By using all hyper parameters of the loss in a unified way, further improvements were achieved which reached a relative SER reduction of 24.6% over the baseline. However, by training overlapping and single speaker speech samples with different margins, the best result was achieved, giving overall a 29.5% SER reduction relative to the baseline.

📄 PDF Abstract BibTeX arXiv:1911.03970

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Additive Margin SincNet for Speaker Recognition

2019-01-28 · João Antônio Chagas Nunes, David Macêdo, Cleber Zanchettin

Speaker Recognition is a challenging task with essential applications such as authentication, automation, and security. The SincNet is a new deep learning based model which has produced promising results to tackle the me…

Deep LearningSpeaker Recognition

Adaptive Margin Circle Loss for Speaker Verification

2021-06-15 · Runqiu Xiao

Deep-Neural-Network (DNN) based speaker verification sys-tems use the angular softmax loss with margin penalties toenhance the intra-class compactness of speaker embeddings,which achieved remarkable performance. In this …

Speaker Verification

Real Additive Margin Softmax for Speaker Verification

2021-10-18 · Lantian Li, Ruiqian Nai, Dong Wang

The additive margin softmax (AM-Softmax) loss has delivered remarkable performance in speaker verification. A supposed behavior of AM-Softmax is that it can shrink within-class variation by putting emphasis on target log…

Speaker Verification

Scoring of Large-Margin Embeddings for Speaker Verification: Cosine or PLDA?

2022-04-08 · Qiongqiong Wang, Kong Aik Lee, Tianchi Liu

The emergence of large-margin softmax cross-entropy losses in training deep speaker embedding neural networks has triggered a gradual shift from parametric back-ends to a simpler cosine similarity measure for speaker ver…

Speaker Verification

Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification

2023-06-06 · Theo Lepage, Reda Dehak

Most state-of-the-art self-supervised speaker verification systems rely on a contrastive-based objective function to learn speaker representations from unlabeled speech data. We explore different ways to improve the perf…

Speaker Verification