How To Improve Your Speaker Embeddings Extractor In Generic Toolkits

Abstract

Recently, speaker embeddings extracted with deep neural networks became the state-of-the-art method for speaker verification. In this paper we aim to facilitate its implementation on a more generic toolkit than Kaldi, which we anticipate to enable further improvements on the method. We examine several tricks in training, such as the effects of normalizing input features and pooled statistics, different methods for preventing overfitting as well as alternative non-linearities that can be used instead of Rectifier Linear Units. In addition, we investigate the difference in performance between TDNN and CNN, and between two types of attention mechanism. Experimental results on Speaker in the Wild, SRE 2016 and SRE 2018 datasets demonstrate the effectiveness of the proposed implementation.

Stats

• citations19
• S2 citations—
• github stars0
• HF likes0
• heat score9.76
• arxiv keyzeinali2018how

Related papers

• Deep Speaker Embeddings For Far-field Speaker Recognition On Short Utterances (2020)11.29
• Deep Speaker Embedding Learning With Multi-level Pooling For Text-independent Speaker Verification (2019)0.00
• A Comparative Re-assessment Of Feature Extractors For Deep Speaker Embeddings (2020)8.09
• On Deep Speaker Embeddings For Text-independent Speaker Recognition (2018)11.93
• Adapting End-to-end Neural Speaker Verification To New Languages And Recording Conditions With Adversarial Training (2018)9.59
• An Improved Deep Neural Network For Modeling Speaker Characteristics At Different Temporal Scales (2020)6.34
• Espnet-spk: Full Pipeline Speaker Embedding Toolkit With Reproducible Recipes, Self-supervised Front-ends, And Off-the-shelf Models (2024)0.00
• Improving Embedding Extraction For Speaker Verification With Ladder Network (2020)0.00