On Deep Speaker Embeddings For Text-independent Speaker Recognition
2018 · Sergey Novoselov, Andrey Shulipa, Ivan Kremnev, et al.
Abstract
We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple softmax activation allows to train a more generalized discriminative speaker embedding extractor. Cosine similarity is an effective metric for speaker verification in this embedding space. We also address the problem of choosing an architecture for the extractor. We found that deep networks with residual frame level connections outperform wide but relatively shallow architectures. This paper also proposes several improvements for previous DNN-based extractor systems to increase the speaker recognition accuracy. We show that the discriminatively trained similarity metric learning approach outperforms the standard LDA-PLDA method as an embedding backend. The results obtained on Speakers in the Wild and NIST SRE 2016 evaluation sets demonstrate robustness
Authors
(none)
Tags
Stats
Related papers
- Deep Speaker Embedding Learning With Multi-level Pooling For Text-independent Speaker Verification (2019)0.00
- An Improved Deep Neural Network For Modeling Speaker Characteristics At Different Temporal Scales (2020)6.34
- Adapting End-to-end Neural Speaker Verification To New Languages And Recording Conditions With Adversarial Training (2018)9.59
- Margin Matters: Towards More Discriminative Deep Neural Network Embeddings For Speaker Recognition (2019)15.25
- Deep Speaker Embeddings For Far-field Speaker Recognition On Short Utterances (2020)11.29
- How To Improve Your Speaker Embeddings Extractor In Generic Toolkits (2018)9.76
- A Study On Angular Based Embedding Learning For Text-independent Speaker Verification (2019)2.26
- Zero-shot Multi-speaker Text-to-speech With State-of-the-art Neural Speaker Embeddings (2019)15.67