Deep multi-metric learning for text-independent speaker verification (2020-07-17T00:00:00.000000Z)

TL;DR

Deep multi-metric learning is used to address the purpose of text-independent speaker verification and introduces three different losses for this problem, i.e., triplet loss, n-pair loss and angular loss, which work in a cooperative way to train a feature extraction network equipped with Residual connections and squeeze-and-excitation attention.

Authors

Xinggang Wang

22 papers

Wenyu Liu

13 papers

Bin Feng

3 papers

Jiwei Xu

1 papers

TL;DR

Authors

References52 items

Classification of breast cancer histopathological images using interleaved DenseNet with SENet (IDSNet)

PyTorch: An Imperative Style, High-Performance Deep Learning Library

CNN with Phonetic Attention for Text-Independent Speaker Verification

Sparse High-Level Attention Networks for Person Re-Identification

DPGAN: PReLU Used in Deep Convolutional Generative Adversarial Networks

Combining Speaker Recognition and Metric Learning for Speaker-Dependent Representation Learning

Deep Speaker Recognition: Modular or Monolithic?

Towards Discriminative Representations and Unbiased Predictions: Class-Specific Angular Softmax for Speech Emotion Recognition

Deep embedding learning with adaptive large margin N-pair loss for image retrieval and clustering

A modified contrastive loss method for face recognition

A Fourier Perspective on Model Robustness in Computer Vision

3D Instance Segmentation via Multi-Task Metric Learning

Transfer Learning in Natural Language Processing

Improving person re-identification by multi-task learning

Seq2Seq Attentional Siamese Neural Networks for Text-dependent Speaker Verification

A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning

Computer vision analysis captures atypical attention in toddlers with autism

Probabilistic Linear Discriminant Analysis With Vectorial Representation for Tensor Data

Speech Recognition Using Deep Neural Networks: A Systematic Review

Streaming End-to-end Speech Recognition for Mobile Devices

Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-Identification

Angular Softmax for Short-Duration Text-independent Speaker Verification

Learning Discriminative Features for Speaker Identification and Verification

Deep Discriminative Embeddings for Duration Robust Speaker Verification

Text-Independent Speaker Verification Based on Triplet Convolutional Neural Network Embeddings

An Experimental Evaluation of Covariates Effects on Unconstrained Face Verification

Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing

VoxCeleb2: Deep Speaker Recognition

Angular Softmax Loss for End-to-end Speaker Verification

Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System

Attentive Statistics Pooling for Deep Speaker Embedding

Attention-Based Models for Text-Dependent Speaker Verification

Multi-task network embedding

Deep Speaker Embeddings for Short-Duration Speaker Verification

Deep Metric Learning with Angular Loss

VoxCeleb: A Large-Scale Speaker Identification Dataset

End-to-End attention based text-dependent speaker verification

A Discriminative Feature Learning Approach for Deep Face Recognition

CNN architectures for large-scale audio classification

Speaker identification and clustering using convolutional neural networks

Deep Residual Learning for Image Recognition

Speaker Recognition by Machines and Humans: A tutorial review

FaceNet: A unified embedding for face recognition and clustering

Deep neural networks for small footprint text-dependent speaker verification

Text-dependent speaker verification: Classifiers, databases and RSR2015

A Study of Interspeaker Variability in Speaker Verification

High performance digit recognition in real car environments

Deep Residual SENet for Foliage Recognition

librosa: Audio and Music Signal Analysis in Python

Text-dependent speaker recognition using PLDA with uncertainty propagation

Eurospeech 2001-Scandinavia Robust Speech Recognition in Noise : An Evaluation using the SPINE Corpus †

Speaker Verification Using Adapted Gaussian Mixture Models

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL