scholarly journals Text-Independent Speaker Verification Based on Deep Neural Networks and Segmental Dynamic Time Warping

2018 ◽  
Author(s):  
Mohamed Adel ◽  
Mohamed Afify ◽  
Akram Gaballah ◽  
Magda Fayek
Keyword(s):  
Neural Networks ◽  
Dynamic Time Warping ◽  
Deep Neural Networks ◽  
Speaker Verification ◽  
Time Warping ◽  
Segmental Dynamic ◽  
Dynamic Time ◽  
Text Independent Speaker Verification

Mean-Delta Features for Telephone Speech Endpoint Detection

2014 ◽  
Vol 12 (3-4) ◽  
pp. 36-44
Author(s):  
A. Ouzounov
Keyword(s):  
Dynamic Time Warping ◽  
Group Delay ◽  
Speaker Verification ◽  
Verification Task ◽  
Endpoint Detection ◽  
Time Warping ◽  
The Mean ◽  
Telephone Speech ◽  
Dynamic Time ◽  
Speech Endpoint Detection

Abstract In this paper, a brief summary of the author’s research in the field of the contour-based telephone speech Endpoint Detection (ED) is presented. This research includes: development of new robust features for ED – the Mean-Delta feature and the Group Delay Mean-Delta feature and estimation of the effect of the analyzed ED features and two additional features in the Dynamic Time Warping fixed-text speaker verification task with short noisy telephone phrases in Bulgarian language.

scholarly journals BIOMETRIC HUMAN AUTHENTICATION SYSTEM THROUGH SPEECH USING DEEP NEURAL NETWORKS (DNN)

THE BULLETIN ◽  
2020 ◽  
Vol 5 (387) ◽  
pp. 6-15
Author(s):  
O. Mamyrbayev ◽  
◽  
A. Akhmediyarova ◽  
A. Kydyrbekova ◽  
N. O. Mekebayev ◽  
...  
Keyword(s):  
Neural Networks ◽  
Teaching Methods ◽  
Deep Neural Networks ◽  
Speaker Verification ◽  
Noisy Data ◽  
Gaussian Mixture ◽  
Modern Method ◽  
Background Modeling ◽  
Authentication System ◽  
Text Independent Speaker Verification

Biometrics offers more security and convenience than traditional methods of identification. Recently, DNN has become a means of a more reliable and efficient authentication scheme. In this work, we compare two modern teaching methods: these two methods are methods based on the Gaussian mixture model (GMM) (denoted by the GMM i-vector) and methods based on deep neural networks (DNN) (denoted as the i-vector DNN). The results show that the DNN system with an i-vector is superior to the GMM system with an i-vector for various durations (from full length to 5s). DNNs have proven to be the most effective features for text-independent speaker verification in recent studies. In this paper, a new scheme is proposed that allows using DNN when checking text using hints in a simple and effective way. Experiments show that the proposed scheme reduces EER by 24.32% compared with the modern method and is evaluated for its reliability using noisy data, as well as data collected in real conditions. In addition, it is shown that the use of DNN instead of GMM for universal background modeling leads to a decrease in EER by 15.7%.

scholarly journals Telephone Speech Endpoint Detection using Mean-Delta Feature

2014 ◽  
Vol 14 (2) ◽  
pp. 127-139 ◽  
Author(s):  
Atanas Ouzounov
Keyword(s):  
Dynamic Time Warping ◽  
Speaker Verification ◽  
Verification Task ◽  
Endpoint Detection ◽  
Time Warping ◽  
Energy Entropy ◽  
Telephone Speech ◽  
Dynamic Time ◽  
Teager Energy ◽  
Speech Endpoint Detection

Abstract In the study the efficiency of three features for trajectory-based endpoint detection is experimentally evaluated in the fixed-text Dynamic Time Warping (DTW) - a based speaker verification task with short phrases of telephone speech. The employed features are Modified Teager Energy (MTE), Energy-Entropy (EE) feature and Mean-Delta (MD) feature. The utterance boundaries in the endpoint detector are provided by means of state automaton and a set of thresholds based only on trajectory characteristics. The training and testing have been done with noisy telephone speech (short phrases in Bulgarian language with length of about 2 s) selected from BG-SRDat corpus. The results of the experiments have shown that the MD feature demonstrates the best performance in the endpoint detection tests in terms of the verification rate.

scholarly journals Addressing Text-Dependent Speaker Verification Using Singing Speech

2019 ◽  
Vol 9 (13) ◽  
pp. 2636 ◽  
Author(s):  
Yan Shi ◽  
Juanjuan Zhou ◽  
Yanhua Long ◽  
Yijie Li ◽  
Hongwei Mao
Keyword(s):  
Dynamic Time Warping ◽  
State Of The Art ◽  
Speaker Verification ◽  
Gaussian Mixture ◽  
Time Warping ◽  
Normal Reading ◽  
Feature Spaces ◽  
Dynamic Time ◽  
The One ◽  
Normal Speech

The automatic speaker verification (ASV) has achieved significant progress in recent years. However, it is still very challenging to generalize the ASV technologies to new, unknown and spoofing conditions. Most previous studies focused on extracting the speaker information from natural speech. This paper attempts to address the speaker verification from another perspective. The speaker identity information was exploited from singing speech. We first designed and released a new corpus for speaker verification based on singing and normal reading speech. Then, the speaker discrimination was compared and analyzed between natural and singing speech in different feature spaces. Furthermore, the conventional Gaussian mixture model, the dynamic time warping and the state-of-the-art deep neural network were investigated. They were used to build text-dependent ASV systems with different training-test conditions. Experimental results show that the voiceprint information in the singing speech was more distinguishable than the one in the normal speech. More than relative 20% reduction of equal error rate was obtained on both the gender-dependent and independent 1 s-1 s evaluation tasks.

Building Sequence Kernels for Speaker Verification and Word Recognition

2011 ◽  
pp. 575-589
Author(s):  
Vincent Wan
Keyword(s):  
Speech Recognition ◽  
Speech Processing ◽  
Kernel Methods ◽  
Speaker Recognition ◽  
Dynamic Time Warping ◽  
Speaker Verification ◽  
Dimensional Space ◽  
Time Warping ◽  
Recognition Systems ◽  
Dynamic Time

This chapter describes the adaptation and application of kernel methods for speech processing. It is divided into two sections dealing with speaker verification and isolated-word speech recognition applications. Significant advances in kernel methods have been realised in the field of speaker verification, particularly relating to the direct scoring of variable-length speech utterances by sequence kernel SVMs. The improvements are so substantial that most state-of-the-art speaker recognition systems now incorporate SVMs. We describe the architecture of some of these sequence kernels. Speech recognition presents additional challenges to kernel methods and their application in this area is not as straightforward as for speaker verification. We describe a sequence kernel that uses dynamic time warping to capture temporal information within the kernel directly. The formulation also extends the standard dynamic time-warping algorithm by enabling the dynamic alignment to be computed in a high-dimensional space induced by a kernel function. This kernel is shown to work well in an application for recognising low-intelligibility speech of severely dysarthric individuals.

Building Sequence Kernels for Speaker Verification and Word Recognition

2011 ◽  
pp. 246-262
Author(s):  
Vincent Wan
Keyword(s):  
Speech Recognition ◽  
Speech Processing ◽  
Kernel Methods ◽  
Speaker Recognition ◽  
Dynamic Time Warping ◽  
Speaker Verification ◽  
Dimensional Space ◽  
Time Warping ◽  
Recognition Systems ◽  
Dynamic Time

This chapter describes the adaptation and application of kernel methods for speech processing. It is divided into two sections dealing with speaker verification and isolated-word speech recognition applications. Significant advances in kernel methods have been realised in the field of speaker verification, particularly relating to the direct scoring of variable-length speech utterances by sequence kernel SVMs. The improvements are so substantial that most state-of-the-art speaker recognition systems now incorporate SVMs. We describe the architecture of some of these sequence kernels. Speech recognition presents additional challenges to kernel methods and their application in this area is not as straightforward as for speaker verification. We describe a sequence kernel that uses dynamic time warping to capture temporal information within the kernel directly. The formulation also extends the standard dynamic time-warping algorithm by enabling the dynamic alignment to be computed in a high-dimensional space induced by a kernel function. This kernel is shown to work well in an application for recognising low-intelligibility speech of severely dysarthric individuals.

scholarly journals Surgical data processing for smart intraoperative assistance systems

2017 ◽  
Vol 2 (3) ◽  
pp. 145-152 ◽  
Author(s):  
Ralf Stauder ◽  
Daniel Ostler ◽  
Thomas Vogel ◽  
Dirk Wilhelm ◽  
Sebastian Koller ◽  
...  
Keyword(s):  
Neural Networks ◽  
Dynamic Time Warping ◽  
Data Science ◽  
Markov Models ◽  
Context Aware ◽  
Time Warping ◽  
Surgical Assistance ◽  
Surgical Data ◽  
Assistance Systems ◽  
Dynamic Time

AbstractDifferent components of the newly defined field of surgical data science have been under research at our groups for more than a decade now. In this paper, we describe our sensor-driven approaches to workflow recognition without the need for explicit models, and our current aim is to apply this knowledge to enable context-aware surgical assistance systems, such as a unified surgical display and robotic assistance systems. The methods we evaluated over time include dynamic time warping, hidden Markov models, random forests, and recently deep neural networks, specifically convolutional neural networks.

HUMAN-LIKE DYNAMIC PROGRAMMING NEURAL NETWORKS FOR DYNAMIC TIME WARPING SPEECH RECOGNITION

1995 ◽  
Vol 06 (01) ◽  
pp. 79-89 ◽  
Author(s):  
CHINCHUAN CHIU ◽  
MICHAEL A. SHANBLATT
Keyword(s):  
Neural Networks ◽  
Dynamic Programming ◽  
Speech Recognition ◽  
Dynamic Time Warping ◽  
Hardware Implementation ◽  
Time Warping ◽  
Network Method ◽  
The Neural Networks ◽  
Dynamic Time ◽  
Better Than

This paper presents a human-like dynamic programming neural network method for speech recognition using dynamic time warping. The networks are configured, much like human’s, such that the minimum states of the network’s energy function represent the near-best correlation between test and reference patterns. The dynamics and properties of the neural networks are analytically explained. Simulations for classifying speaker-dependent isolated words, consisting of 0 to 9 and A to Z, show that the method is better than conventional methods. The hardware implementation of this method is also presented.

Sign in / Sign up

Export Citation Format

Share Document