End-to-End Trainable Self-Attentive Shallow Network for Text-Independent Speaker Verification

by   Hyeonmook Park, et al.

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 improvement over GE2E of about 63 (Detection cost function), and AUC (Area under the curve), respectively. Notably, when the input length becomes longer, the DCF score improvement of the proposed model is about 17 times greater than that of GE2E.



page 1

page 2

page 3

page 4


Text-Independent Speaker Verification Using Long Short-Term Memory Networks

In this paper, an architecture based on Long Short-Term Memory Networks ...

End-to-end DNN Based Speaker Recognition Inspired by i-vector and PLDA

Recently several end-to-end speaker verification systems based on deep n...

Deep Speaker Embedding Learning with Multi-Level Pooling for Text-Independent Speaker Verification

This paper aims to improve the widely used deep speaker embedding x-vect...

Utterance-level end-to-end language identification using attention-based CNN-BLSTM

In this paper, we present an end-to-end language identification framewor...

Speaker diarisation using 2D self-attentive combination of embeddings

Speaker diarisation systems often cluster audio segments using speaker e...

Clickbait Detection in Tweets Using Self-attentive Network

Clickbait detection in tweets remains an elusive challenge. In this pape...

EmotionX-DLC: Self-Attentive BiLSTM for Detecting Sequential Emotions in Dialogue

In this paper, we propose a self-attentive bidirectional long short-term...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.