Recently deep learning has been successfully used in speech recognition, however it has not been carefully explored and widely accepted for speaker verification. To incorporate deep learning into speaker verification, this paper proposes novel approaches of extracting and using features from deep learning models for text-dependent speaker verification. In contrast to the traditional short-term spectral feature, such as MFCC or PLP, in this paper, outputs from hidden layer of various deep models are employed as deep features for text-dependent speaker verification. Fours types of deep models are investigated: deep Restricted Boltzmann Machines, speech-discriminant Deep Neural Network (DNN), speaker-discriminant DNN, and multi-task joint-learned DNN. Once deep features are extracted, they may be used within either the GMM-UBM framework or the identity vector (i-vector) framework. Joint linear discriminant analysis and probabilistic linear discriminant analysis are proposed as effective back-end classifiers for identity vector based deep features. These approaches were evaluated on the RSR2015 data corpus. Experiments showed that deep feature based methods can obtain significant performance improvements compared to the traditional baselines, no matter if they are directly applied in the GMM-UBM system or utilized as identity vectors. The EER of the best system using the proposed identity vector is 0.10%, only one fifteenth of that in the GMM-UBM baseline.

Yuan Liu

Yanmin Qian

Nanxin Chen

Tianfan Fu

Ya Zhang

Kai Yu

Speech Communication

SPEECH COMMUNICATION 是一本跨学科期刊，其主要目标是满足快速传播和深入讨论基础和应用研究成果的需求。该期刊的主要目标是：• 为人类和人机技术的进步提供一个论坛语音通信科学；• 促进该领域不同领域之间的交流；• 促进该领域科学合理贡献的快速和广泛传播。

Speech Communication is an interdisciplinary journal aimed at meeting the needs for rapid dissemination and in-depth discussion of fundamental and applied research findings. The main objectives of the journal are: to provide a forum for the advancement of speech communication science for both humans and human-machine technologies; to facilitate communication across different disciplines within the field; and to promote the rapid and widespread dissemination of scientifically sound contributions in the field.

《Speech Communication》是一本跨学科的期刊，旨在满足基础和应用研究成果的快速传播与深入讨论的需求。该期刊的主要目标包括：为人类与人机技术的进步提供一个语音通信科学的论坛；促进该领域不同学科之间的交流；加速和广泛传播该领域的科学合理贡献。

Deep feature for text-dependent speaker verification

Experiments showed that deep feature based methods can obtain significant performance improvements compared to the traditional baselines, no matter if they are directly applied in the GMM-UBM system or utilized as identity vectors.

Category	Quartile
计算机科学	3
计算机科学, 声学	2
计算机科学, 计算机跨学科应用	3

Deep feature for text-dependent speaker verification

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS	3