End-to-end Trainable Self-attentive Shallow Network For Text-independent Speaker Verification
2020 · Hyeonmook Park, Jungbae Park, Sang Wan Lee
Abstract
Generalized end-to-end (GE2E) model is widely used in speaker verification (SV) fields due to its expandability and generality regardless of specific languages. However, the long-short term memory (LSTM) based on GE2E has two limitations: First, the embedding of GE2E suffers from vanishing gradient, which leads to performance degradation for very long input sequences. Secondly, utterances are not represented as a properly fixed dimensional vector. In this paper, to overcome issues mentioned above, we propose a novel framework for SV, end-to-end trainable self-attentive shallow network (SASN), incorporating a time-delay neural network (TDNN) and a self-attentive pooling mechanism based on the self-attentive x-vector system during an utterance embedding phase. We demonstrate that the proposed model is highly efficient, and provides more accurate speaker verification than GE2E. For VCTK dataset, with just less than half the size of GE2E, the proposed model showed significant performance i
Authors
(none)
Tags
Stats
Related papers
- Generalized End-to-end Loss For Speaker Verification (2017)20.58
- An Empirical Study On Text-independent Speaker Verification Based On The GE2E Method (2020)0.00
- Deep Speaker Embedding Learning With Multi-level Pooling For Text-independent Speaker Verification (2019)0.00
- End-to-end Attention Based Text-dependent Speaker Verification (2017)14.87
- Joint Speaker Encoder And Neural Back-end Model For Fully End-to-end Automatic Speaker Verification With Multiple Enrollment Utterances (2022)0.00
- Text-independent Speaker Verification Using Long Short-term Memory Networks (2018)0.00
- Deep Neural Network Embeddings With Gating Mechanisms For Text-independent Speaker Verification (2019)8.82
- Self-attentive Multi-layer Aggregation With Feature Recalibration And Normalization For End-to-end Speaker Verification System (2020)0.00