I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification

2018-04-01 · Jiacen Zhang, Nakamasa Inoue, Koichi Shinoda

I-vector based text-independent speaker verification (SV) systems often have poor performance with short utterances, as the biased phonetic distribution in a short utterance makes the extracted i-vector unreliable. This paper proposes an i-vector compensation method using a generative adversarial network (GAN), where its generator network is trained to generate a compensated i-vector from a short-utterance i-vector and its discriminator network is trained to determine whether an i-vector is generated by the generator or the one extracted from a long utterance. Additionally, we assign two other learning tasks to the GAN to stabilize its training and to make the generated ivector more speaker-specific. Speaker verification experiments on the NIST SRE 2008 "10sec-10sec" condition show that our method reduced the equal error rate by 11.3% from the conventional i-vector and PLDA system.

📄 PDF Abstract BibTeX arXiv:1804.00290

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial NetworkSpeaker VerificationText-Independent Speaker Verification

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Age Progression/Regression by Conditional Adversarial Autoencoder

2017-02-27 · CVPR 2017 7 · Zhifei Zhang, Yang song, Hairong Qi

"If I provide you a face image of mine (without telling you the actual age when I took the picture) and a large amount of face images that I crawled (containing labeled faces of different ages but not necessarily paired)…

Attribute regression

Towards Recovery of Conditional Vectors from Conditional Generative Adversarial Networks

2017-12-06 · Sihao Ding, Andreas Wallin

A conditional Generative Adversarial Network allows for generating samples conditioned on certain external information. Being able to recover latent and conditional vectors from a condi- tional GAN can be potentially val…

Generative Adversarial Network Image Manipulation

Face Aging with Contextual Generative Adversarial Nets

2018-02-01 · Si Liu, Yao Sun, Defa Zhu, Renda Bao 외

Face aging, which renders aging faces for an input face, has attracted extensive attention in the multimedia research. Recently, several conditional Generative Adversarial Nets (GANs) based methods have achieved great su…

Face Verification

Class-Conditional Defense GAN Against End-to-End Speech Attacks

2020-10-22 · Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich

In this paper we propose a novel defense approach against end-to-end adversarial attacks developed to fool advanced speech-to-text systems such as DeepSpeech and Lingvo. Unlike conventional defense approaches, the propos…

Generative Adversarial Network Sentence Speech-to-Text

Aligning and Projecting Images to Class-conditional Generative Networks

2020-08-01 · ECCV 2020 8 · Minyoung Huh, Richard Zhang, Jun-Yan Zhu, Sylvain Paris 외

We present a method for projecting an input image into the space of a class-conditional generative neural network. We propose a method that optimizes for transformation to counteract the model biases in generative neural…

Generative Adversarial Network Translation