2019 · 81 citations · 17 references
ComputingData ScienceFeature EngineeringNatural Language ProcessingPhoneticsDeep LearningSpeaker IdentificationSpeech RecognitionLong Short-term Memory NetworksRegularizationRegularization TechniquesSpeaker RecognitionSpeaker-independent Speech RecognitionText-independent Speaker Recognition
This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay neural network (TDNN) and long short-term memory neural networks (LSTM) to generate complementary speaker information at different levels; (2) a multi-level pooling strategy to collect speaker information from both TDNN and LSTM layers; (3) a regularization scheme on the speaker embedding extraction layer to make the extracted embeddings suitable for the following fusion step. The synergy of these improvements are shown on the NIST SRE 2016 eval test (with a 19% EER reduction) and SRE 2018 dev test (with a 9% EER reduction), as well as more than 10% DCF scores reduction on these two test sets over the x-vector baseline.
17
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Front-End Factor Analysis for Speaker Verification
Najim Dehak, Patrick Kenny, Réda Dehak et al. · IEEE Transactions on Audio Speech and Language Processing · 2010 · 3.6K citations
X-Vectors: Robust DNN Embeddings for Speaker Recognition
David Snyder, Daniel Garcia-Romero, Gregory Sell et al. · 2018 · 2.7K citations
Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks
Tara N. Sainath, Oriol Vinyals, Andrew Senior et al. · 2015 · 1.6K citations
Generalized End-to-End Loss for Speaker Verification
Li Wan, Quan Wang, Alan Papir et al. · 2018 · 837 citations