End-to-end Losses Based On Speaker Basis Vectors And All-speaker Hard Negative Mining For Speaker Verification

Abstract

In recent years, speaker verification has primarily performed using deep neural networks that are trained to output embeddings from input features such as spectrograms or Mel-filterbank energies. Studies that design various loss functions, including metric learning have been widely explored. In this study, we propose two end-to-end loss functions for speaker verification using the concept of speaker bases, which are trainable parameters. One loss function is designed to further increase the inter-speaker variation, and the other is designed to conduct the identical concept with hard negative mining. Each speaker basis is designed to represent the corresponding speaker in the process of training deep neural networks. In contrast to the conventional loss functions that can consider only a limited number of speakers included in a mini-batch, the proposed loss functions can consider all the speakers in the training set regardless of the mini-batch composition. In particular, the proposed l

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyheo2019end

Related papers

• Large Margin Softmax Loss For Speaker Verification (2019)14.66
• Angular Softmax Loss For End-to-end Speaker Verification (2018)11.19
• Generalized End-to-end Loss For Speaker Verification (2017)20.58
• Hiddenspeaker: Generate Imperceptible Unlearnable Audios For Speaker Verification System (2024)2.26
• Joint Speaker Encoder And Neural Back-end Model For Fully End-to-end Automatic Speaker Verification With Multiple Enrollment Utterances (2022)0.00
• End-to-end Residual CNN With L-GM Loss Speaker Verification System (2018)2.26
• Adapting End-to-end Neural Speaker Verification To New Languages And Recording Conditions With Adversarial Training (2018)9.59
• A Comparison Of Metric Learning Loss Functions For End-to-end Speaker Verification (2020)6.77