Speaker Recognition Systems 2016


  • Automated speaker recognition
  • Automatic speaker recognition
  • Intelligent voice system
  • Speaker characterisation (Speaker characterization)
  • Speaker diarisation (Speaker diarization)
  • Speaker identification
  • Speaker recognition module
  • Voice biometrics




See also:

APR (Automatic Personality Recognition) 2016

Migrating i-vectors between speaker recognition systems using regression neural networks
O Glembek, P Mat?jka, O Plchot, J Pešán… – … Annual Conference of …, 2015 – fit.vutbr.cz
Abstract This paper studies the scenario of migrating from one ivector-based speaker recognition system (SRE) to another, ie comparing the i-vectors produced by one system with those produced by another system. System migration would typically be motivated by

Incorporation of Speech Duration Information in Score Fusion of Speaker Recognition Systems
A Khodabakhsh, SS Sarfjoo, U Uludag… – arXiv preprint arXiv …, 2016 – arxiv.org
Abstract: In recent years identity-vector (i-vector) based speaker verification (SV) systems have become very successful. Nevertheless, environmental noise and speech duration variability still have a significant effect on degrading the performance of these systems. In

Corpora for the Evaluation of Robust Speaker Recognition Systems.
DE Sturim, PA Torres-Carrasquillo, JP Campbell – INTERSPEECH, 2016 – ll.mit.edu
Abstract The goal of this paper is to describe significant corpora available to support speaker recognition research and evaluation, along with details about the corpora collection and design. We describe the attributes of high-quality speaker recognition corpora.

The IBM Speaker Recognition System: Recent Advances and Error Analysis
SO Sadjadi, J Pelecanos, S Ganapathy – arXiv preprint arXiv:1605.01635, 2016 – arxiv.org
Abstract: We present the recent advances along with an error analysis of the IBM speaker recognition system for conversational speech. Some of the key advancements that contribute to our system include: a nearest-neighbor discriminant analysis (NDA) approach

I-vector speaker and language recognition system on Android
C Vazquez-Machado… – … (HPEC), 2016 IEEE, 2016 – ieeexplore.ieee.org
… part of the study. Gomar [5] presents the design of a system, with various opti- mization operations and functionality, to achieve the goal of an I-Vector speaker recognition system within a mobile device. The author provides various …

Analysis of Speaker Recognition Systems in Realistic Scenarios of the SITW 2016 Challenge.
O Novotný, P Matejka, O Plchot, O Glembek, L Burget… – Interspeech, 2016 – fit.vutbr.cz
Abstract In this paper, we summarize our efforts for the Speakers In The Wild (SITW) challenge, and we present our findings with this new dataset for speaker recognition. Apart from the standard comparison of different SRE systems, we analyze the use of diarization for

Real time speaker recognition system using MFCC and vector quantization technique
R Bharti, P Bansal – International Journal of Computer …, 2015 – search.proquest.com
Abstract This paper represents a very strong mathematical algorithm for Automatic Speaker Recognition (ASR) system using MFCC and vector quantization technique in the digital world. MFCC and vector quantization techniques are the most preferable and promising

VOCALISE: A forensic automatic speaker recognition system supporting spectral, phonetic, and user-provided features
A Alexander, O Forth, AA Atreya, F Kelly – 2016 – odyssey2016.org
Abstract In this article we present the latest version of VOCALISE (Voice Comparison and Analysis of the Likelihood of Speech Evidence), a forensic automatic system for speaker recognition. VOCALISE, with selectable stateof-the-art and legacy speaker modelling

Text-independent, automatic speaker recognition system evaluation with males speaking both Arabic and English
SS Alamri – 2015 – search.proquest.com
Abstract Automatic speaker recognition is an important key to speaker identification in media forensics and with the increase of cultures mixing, there’s an increase in bilingual speakers all around the world. The purpose of this thesis is to compare text-independent samples of

Improved speaker recognition system for stressed speech using deep neural networks
SH Dumpala, SK Kopparapu – Neural Networks (IJCNN), 2017 …, 2017 – ieeexplore.ieee.org
Good speaker recognition systems should identify the speaker irrespective of what is spoken, including non-speech sounds that are often produced during natural conversations. In this work, the inclusion of breath sounds in the training phase of the speaker recognition is

Formant dynamics and durations of um improve the performance of automatic speaker recognition systems
V Hughes, P Foulkes, S Wood – Proceedings of the 16th …, 2016 – eprints.whiterose.ac.uk
We assess the potential improvement in the performance of MFCC-based automatic speaker recognition (ASR) systems with the inclusion of linguistic-phonetic information. Likelihood ratios were computed using MFCCs and the formant trajectories and durations of the

Robustness of Quality-based Score Calibration of Speaker Recognition Systems with respect to low-SNR and short-duration conditions
A Nautsch, R Saeidi, C Rathgeb… – Proc. Odyssey, Speaker …, 2016 – odyssey2016.org
Abstract Degraded signal quality and incomplete voice probes have severe effects on the performance of a speaker recognition system. Unified audio characteristics (UACs) have been proposed to quantify multi-condition signal degradation effects into posterior

Analysis Of Different Feature Extraction Techniques For Speaker Recognition System: A Review
MY Dawande, M Dhopeshwarkar – IJATER, 2015 – ijater.com
Abstract: This paper gives an overview of various methods and techniques used for feature extraction in speaker recognition. The research in speaker recognition have been evolved starting from short time features reflecting spectral properties of speech (low-level or

Speaker Recognition System using Wavelet Transform under Stress Condition
KT Biswal, J Rout – IJSEAT, 2017 – ijseat.com
Abstract in this paper, we introduced a text-depend speaker recognition by using wavelet transform under stressed conditions. Here we compare different feature such as ARC, LAR, LPCC, MFCC, CEP and after comparison we found that LPCC provides best feature. For

Analysis of compressed speech signals in an Automatic Speaker Recognition system
RA Metzger, JF Doherty… – Information Sciences and …, 2015 – ieeexplore.ieee.org
Abstract: This paper analyzes the effects popular audio compression algorithms have on the performance of a speaker recognition system. Popular audio compression algorithms were used to compress both clean and noisy speech before being passed to a speaker

Feature Extraction and Classification for Automatic Speaker Recognition System-A Review
K Kaur, N Jain – International Journal of Advanced …, 2015 – pdfs.semanticscholar.org
Abstract—Automatic speaker recognition (ASR) has found immense applications in the industries like banking, security, forensics etc. for its advantages such as easy implementation, more secure, more user friendly. To have a good recognition rate is a pre-

Identifying Perceptually Similar Voices with a Speaker Recognition System Using Auto-Phonetic Features.
F Kelly, A Alexander, O Forth, S Kent… – …, 2016 – pdfs.semanticscholar.org
Abstract Assessing the perceptual similarity of voices is necessary for the creation of voice parades, along with media applications such as voice casting. These applications are normally prohibitively expensive to administer, requiring significant amounts of ‘expert

The IBM 2016 speaker recognition system
SO Sadjadi, S Ganapathy, JW Pelecanos – arXiv preprint arXiv …, 2016 – arxiv.org
Abstract: In this paper we describe the recent advancements made in the IBM i-vector speaker recognition system for conversational speech. In particular, we identify key techniques that contribute to significant improvements in performance of our system, and

Amrita sre database: A database for evaluating speaker recognition systems with mimicked speech
KK George, CS Kumar, KT Sreekumar… – 0-COCOSDA 2015 …, 2015 – researchgate.net
Abstract—Evaluating speaker recognition systems under challenging conditions with mimicked voices of target speakers as non-target trials is very important in making decisions of its effectiveness and deployability in critical applications. The lack of a standard database

A Speaker Recognition System for the SITW Challenge.
O Kudashev, S Novoselov, K Simonchik… – …, 2016 – researchgate.net
Abstract This paper presents an ITMO university system submitted to the Speakers in the Wild (SITW) Speaker Recognition Challenge. During evaluation track of the SITW challenge we explored conventional universal background model (UBM) Gaussian mixture model

Modified-prior PLDA and score calibration for duration mismatch compensation in speaker recognition system
QY Hong, L Li, M Li, L Huang, L Wan… – … Annual Conference of …, 2015 – speech.xmu.edu.cn
Abstract To deal with the performance degradation of speaker recognition due to duration mismatch between enrollment and test utterances, a novel strategy to modify the standard normal prior distribution of the i-vector during probabilistic linear discriminant analysis

Using Approximate Entropy as a speech quality measure for a speaker recognition system
RA Metzger, JF Doherty… – Information Science and …, 2016 – ieeexplore.ieee.org
Abstract: In this paper, we will show that Approximate Entropy (ApEn) can be used to detect high-quality speech frames in an otherwise distorted speech signal. By exploiting the property of quasi-periodicity in speech, ApEn is able to detect small aberrations in speech

Comparative study of different classifiers based speaker recognition system using modified MFCC for noisy environment
A Sukhwal, M Kumar – Green Computing and Internet of Things …, 2015 – ieeexplore.ieee.org
Abstract: Speaker recognition has made great progress under the laboratory environment, but in real life the performance of speaker recognition system is affected by various factors including environmental noise. This paper studies the performance of speaker recognition

A Study on Text-Independent Speaker Recognition Systems in Emotional Conditions Using Different Pattern Recognition Models
SV Gangashetty, AK Vuppala – Mining Intelligence and …, 2017 – books.google.com
Abstract. The present study focuses on the text-independent speaker recognition in emotional conditions. In this paper, both system and source features are considered to represent speaker specific information. At the model level, Gaussian Mixture Models

On the Issue of Calibration in DNN-Based Speaker Recognition Systems.
M McLaren, D Castan, L Ferrer… – …, 2016 – pdfs.semanticscholar.org
Abstract This article is concerned with the issue of calibration in the context of Deep Neural Network (DNN) based approaches to speaker recognition. DNNs have provided a new standard in technology when used in place of the traditional universal background model

Short duration voice data speaker recognition system using novel fuzzy vector quantization algorithm
S Singh, MH Assaf, SR Das, SN Biswas… – … (I2MTC), 2016 IEEE …, 2016 – ieeexplore.ieee.org
Abstract: The performance of any speaker recognition system depends on the duration of the speech samples. The higher the number of feature vectors is, the better is the efficiency. A major contribution of this paper is in enhancing the identification accuracy of the speaker

Detect mimicry by enhancing the speaker recognition system
S Kanrar, PK Mandal – Information Systems Design and Intelligent …, 2015 – Springer
Abstract Mimicry voice sample is a potential challenge to the speaker verification system. The system performance is highly depended on the equal error rate. If the false accept to reduce, then the equal error rate decrease. The speaker verification process, verifies the

Dealing with additive noise in speaker recognition systems based on i-vector approach
D Matrouf, WB Kheder, PM Bousquet… – … 2015 23rd European, 2015 – ieeexplore.ieee.org
Abstract: In the last years, the i-vector approach became the state-of-the-art in speaker recognition systems. As in previous approaches, i-vector-based systems suffer greatly in presence of additive noise, especially in low SNR cases. In this paper, we will describe a

Effect of plosives on isolated speaker recognition system performance
Z ?entürk, Ö Salor – Electrical and Electronics Engineering …, 2015 – ieeexplore.ieee.org
Abstract: In this paper, the effect of keyword choice including and excluding plosive sounds on isolated speaker recognition system is investigated. In order to perform this study, a Turkish word database has been created consisting of 48 words including plosives and 7

Digital Speech Watermarking for Authenticity of Speaker in Speaker Recognition System
N Desai, N Tahilramani – Micro-Electronics and …, 2016 – ieeexplore.ieee.org
Abstract: Speaker recognition is a process of speakeridentification and speaker verification refers to specific tasks. Where security is a main concern, speaker Recognitiontechnique is one of the most helpful recognition techniques intoday world. It is very important to identify

Speaker Recognition System using Gaussian Mixture Model
A Aroon, SB Dhonde – methods, 2015 – pdfs.semanticscholar.org
ABSTRACT In this paper, features for text-independent speaker recognition has been evaluated. Speaker identification from a set of templates and analyzing speaker recognition rate by extracting several key features like Mel Frequency Cepstral Coefficients [MFCC] from

The Intelligent Voice 2016 Speaker Recognition System
A Khosravani, C Glackin, N Dugan, G Chollet… – arXiv preprint arXiv …, 2016 – arxiv.org
Abstract: This paper presents the Intelligent Voice (IV) system submitted to the NIST 2016 Speaker Recognition Evaluation (SRE). The primary emphasis of SRE this year was on developing speaker recognition technology which is robust for novel languages that are

Scores Calibration in Speaker Recognition Systems
A Shulipa, S Novoselov, Y Matveev – International Conference on Speech …, 2016 – Springer
Abstract It is well known that variability of speech signal quality affects the performance of speaker recognition systems. Difference in speech quality between enrollment and test utterances leads to shifting of scores and performance degradation. In order to improve the

Mahalanobis Metric Scoring Learned from Weighted Pairwise Constraints in I-Vector Speaker Recognition System.
Z Lei, Y Wan, J Luo, Y Yang – INTERSPEECH, 2016 – pdfs.semanticscholar.org
Abstract The i-vector model is widely used by the state-of-the-art speaker recognition system. We proposed a new Mahalanobis metric scoring learned from weighted pairwise constraints (WPCML), which use the different weights for the empirical error of the similar

Text-Available Speaker Recognition System for Forensic Applications.
C Yu, C Zhang, F Kelly, A Sangwan… – …, 2016 – crss.utdallas.edu
Abstract This paper examines a text-available speaker recognition approach targeting scenarios where the transcripts of test utterances are either available or obtainable through manual transcription. Forensic speaker recognition is one of such applications where the

Performance analysis of text-dependent speaker recognition system based on template model based classifiers
K Kaur, N Jain – Signal Processing, Computing and Control …, 2015 – ieeexplore.ieee.org
Abstract: Speaker recognition technology has found its usage in varied different fields including security systems, banking operations and forensic laboratories etc. due to its easy implementation, flexibility and security. Each of these applications demand high

Reducing computation in an i-vector speaker recognition system using a tree-structured universal background model
R McClanahan, PL De Leon – Speech Communication, 2015 – Elsevier
Abstract The majority of state-of-the-art speaker recognition systems (SR) utilize speaker models that are derived from an adapted universal background model (UBM) in the form of a Gaussian mixture model (GMM). This is true for GMM supervector systems, joint factor

The influence of fundamental frequency on speaker recognition system
Y Zhang, Y Xie, K Wang – Intelligent Control and Automation …, 2016 – ieeexplore.ieee.org
Abstract: The impact of fundamental frequency of MFCC usually is neglected in the application and research of speech signal based on feature MFCC. Analysis shows that the fundamental frequency affects the accurate description of channel characteristics, thus affect

Adoption Speaker Recognition System using Mel-frequency Cepstral Coefficients
R Elbarougy, HA Algrbaa – Journal of Computer Science …, 2017 – jcsa.zu.edu.eg
Abstract The traditional system of speaker recognition depends on extraction some of features within the speech. Many researchers have adopted several ways to extract these features. One of the most famous of these methods is MFCC. The number of extracted

Performance comparison of speaker recognition systems in presence of duration variability
A Poddar, M Sahidullah, G Saha – India Conference (INDICON) …, 2015 – ieeexplore.ieee.org
Abstract: Performance of speaker recognition system is highly dependent on the amount of speech data used in training and testing. In this paper, we compare the performance of two different speaker recognition systems in presence of utterance duration variability. The first

Speaker Recognition System for Limited Speech Data Using High-Level Speaker Specific Features and Support Vector Machines
S Singh, N Agarwal, A Kumar – International Journal of Applied …, 2017 – ripublication.com
Abstract High-level speaker-specific features (HLSSFs), such as the style of pronunciation of words, their use, phonotactics and prosody, form the main subjects of state-of-the-art research on automatic speaker recognition (ASR). In this paper, we experimentally verify

A perfect balance of sparsity and acoustic hole in speech signal and its application in speaker recognition system
S Singh, M Assaf – Middle-East Journal of Scientific Research, 2016 – researchgate.net
Abstract: This paper addresses the issue of balancing the acoustic hole and sparsing the speech signal enrollment for training and testing in Automatic Speaker Recognition (ASR) system. Sparsing techniques involve the representation of a small number of coefficients that

Speaker Recognition System Using Watermark Technology for Anti-Spoofing Attack: A Review
NG Desai, NV Tahilramani – International Journal of Innovative …, 2016 – ijireeice.com
Abstract: This paper is about Speaker recognition using Watermark technology for Anti-Spoofing Attack. Speaker recognition is a process whereas speaker identification and speaker verification refer to definite tasks. For the areas in which security is a foremost

Speakers In The Wild (SITW): The QUT Speaker Recognition System.
H Ghaemmaghami, MH Rahman… – …, 2016 – pdfs.semanticscholar.org
Abstract This paper presents the QUT speaker recognition system, as a competing system in the Speakers In The Wild (SITW) speaker recognition challenge. Our proposed system achieved an overall ranking of second place, in the main core-core condition evaluations of

Modulation Components and Genetic Algorithm for Speaker Recognition System
TA Hassan, RI Ajel, EK Ibrahim – INTERNATIONAL …, 2017 – pdfs.semanticscholar.org
Abstract—In this paper, the aim is to investigate weather or not that changing the filter-bank components (of the speaker recognition system) could improve the system performance in identifying the speaker. The filter is composed of 30 Gamatone filter channels. First, the

Real time implementation of speaker recognition system with MFCC and neural networks on FPGA
B Kari, S Muthulakshmi – Indian Journal of Science and Technology, 2015 – indjst.org
Background: Speaker recognition systems plays a pivotal role in the field of forensics, security and biometric authentication for verifying or identifying the speaker from the group of speakers. Methods: This paper gives a brief introduction about developing a hardware

Designing and Modeling of Speech and Speaker Recognition System to Control the Wheelchair
G Kaur, MS andAmod Kumar – Advances in Computational …, 2017 – ripublication.com
Abstract The proposed work presents the speech operated wheelchair for handicapped person which is controlled with the voice command from handicapped person. Speech user interface is imperative for movement of wheelchair based on the speaker voice. The learning

Effects of clipping distortion on an Automatic Speaker Recognition system
JL Ramirez – 2016 – search.proquest.com
Abstract Clipping distortion is a common problem faced in the audio recording world in which an audio signal is recorded at higher amplitude than the recording system’s limitations, resulting in a portion of the acoustic event not being recorded. Several

Joint MFCC-and-vector quantization based text-independent speaker recognition system
AE Omer – Communication, Control, Computing and Electronics …, 2017 – ieeexplore.ieee.org
Abstract: Signal processing front end for extracting the feature set is an important stage in any speaker recognition system. There are many types of features that are derived differently and have good impact on the recognition rate. This paper uses one of the techniques to

Towards PLDA-RBM based speaker recognition in mobile environment: Designing stacked/deep PLDA-RBM systems
A Nautsch, H Hao, T Stafylakis… – … , Speech and Signal …, 2016 – ieeexplore.ieee.org
… themos.stafylakis@crim.ca ABSTRACT The vast majority of text-independent speaker recognition systems rely on intermediate-sized vectors (i-vectors), which are compared by probabilistic linear discriminant analysis (PLDA) …

Affect-insensitive speaker recognition systems via emotional speech clustering using prosodic features
D Li, Y Yuan, Z Wu, Y Yang – Neural Computing and Applications, 2015 – Springer
Abstract Voice-based biometric security systems involving only neutral speech have achieved promising performance. However, the speakers are very likely to fail the recognition when the test data exhibit multiple emotions. This paper aimed to address the

A Novel Algorithm of Sparse Representations for Speech Compression/Enhancement and Its Application in Speaker Recognition System
S Singh, MH Assaf, A Kumar – International Journal of …, 2016 – ripublication.com
Abstract This paper proposes sparse and redundancy representation spectral domain compression of the speech signal using novel sparsing algorithms to the problem of speech compression (SC)/enhancement (SE). In Automatic Speaker Recognition (ASR)

KU-ISPL Speaker Recognition Systems under Language mismatch condition for NIST 2016 Speaker Recognition Evaluation
S Shon, H Ko – arXiv preprint arXiv:1702.00956, 2017 – arxiv.org
Abstract: Korea University Intelligent Signal Processing Lab.(KU-ISPL) developed speaker recognition system for SRE16 fixed training condition. Data for evaluation trials are collected from outside North America, spoken in Tagalog and Cantonese while training data only is

The non-trusty clown attack on model-based speaker recognition systems.
AF Baroughi, S Craver – Media …, 2015 – proceedings.spiedigitallibrary.org
ABSTRACT Biometric detectors for speaker identification commonly employ a statistical model for a subject’s voice, such as a Gaussian Mixture Model, that combines multiple means to improve detector performance. This allows a malicious insider to amend or

Improved Dynamic Speaker Recognition System using NLMS Adaptive Filter
PH Kumar, V Srinivas, T Madhu – International Journal of …, 2016 – search.proquest.com
Abstract In a controlled environment, we can implement a speaker recognition system using MFCC and Vector Quantization. So, the main objective of this paper is to develop a speaker recognition system using MFCC and Vector Quantization (VQ) in a noisy environment, when

Optimization of feature vectors for art classifier in language independent speaker recognition system for biometric security
AJ Albin – Biomedical Research, 2016 – alliedacademies.org
Automated speaker recognition from speech signals plays a major role in the field of biometrics to authenticate the speaker. Though considerable research is carried out in this area, sensitivity and specificity of the proposed technique are not satisfactory. In this paper,

AUT System for SITW Speaker Recognition Challenge.
A Khosravani, MM Homayounpour – INTERSPEECH, 2016 – researchgate.net
… Taking advantage of the challenge develop- ment data, our experiments indicate that source normalization can help speaker recognition system to better adapt to the eval- uation condition … Sec- tion 2 describes our speaker recognition system …

Speaker recognition system techniques and applications
S Kaur, KS Dhindsa – International Journal of Computer Science and …, 2015 – academia.edu
2015 Revised: Jul/22/2015 Accepted: Aug/20/2015 Published: Aug/30/2015 Abstract-Speaker verification is feasible method of controlling access to computer and communication network. It is an automatic process that uses human voice characteristics

On the Performance Degradation of Speaker Recognition System due to Variation in Speech Characteristics Caused by Physiological Changes
M Usman – 2017 – bspace.uob.edu.bh
Speaker recognition is the process of identifying a person using their speech characteristics (voice biometrics). Speech characteristics of an individual can vary due to physiological changes which may be caused by health changes, physical activity as well as emotional

A synthetic speech countermeasure using pitch pattern statistics derived from image analysis for speaker recognition systems
B Stewart – 2015 – search.proquest.com
Abstract Automatic Speaker Verification (ASV) systems have become one of the more popular biometrics in part due to the abundance of microphones on all phones and nearly all computers. However, due to advances in synthetic speech synthesizers and voice

A Study on Text-Independent Speaker Recognition Systems in Emotional Conditions Using Different Pattern Recognition Models
KR Alluri, S Achanta, R Prasath… – … Conference on Mining …, 2016 – Springer
Abstract The present study focuses on the text-independent speaker recognition in emotional conditions. In this paper, both system and source features are considered to represent speaker specific information. At the model level, Gaussian Mixture Models

Nature-inspired feature subset selection application to arabic speaker recognition system
A Harrag – International Journal of Speech Technology, 2015 – Springer
Abstract Feature selection is an important task which can affect the performance of pattern classification and recognition system. This study uses two nature-inspired algorithms, namely genetic algorithms and particle swarm optimization, for this problem. The algorithms

Program Guardian: screening system with a novel speaker recognition approach for smart TV
YH Chin, TC Tai, JH Zhao, KY Wang, CT Hong… – Multimedia Tools and …, 2017 – Springer
… This system is based on a robust speaker recognition system that uses robust principal component analysis (RPCA) and a sparse representation classifier (SRC) … The results show that the proposed speaker recognition system is feasible and offers advantages over accuracy …

Automatic Speaker Recognition System in Adverse Conditions–Implication of Noise and Reverberation on System Performance
KA Al-Karawi, AH Al-Noori, FF Li… – International Journal of …, 2015 – search.proquest.com
Abstract Speaker recognition has been developed and evolved over the past few decades into a supposedly mature technique. Existing methods typically utilize robust features extracted from clean speech. In real-world applications, especially security and forensics

Inter-Task System Fusion for Speaker Recognition.
M Ferras, SR Madikeri, S Dey, P Motlícek… – …, 2016 – publications.idiap.ch
… Abstract Fusion is a common approach to improving the performance of speaker recognition systems … 1. Introduction In the last decade, speaker recognition system have progres- sively improved their performance under more and more chal- lenging scenarios …

Comparative study between different classifiers based speaker recognition system using MFCC for noisy environment
A Sukhwal, M Kumar – Green Computing and Internet of Things …, 2015 – ieeexplore.ieee.org
Abstract: Speaker recognition has made great progress under the laboratory environment, but in real life the performance of speaker recognition system is affected by various factors including environmental noise. This paper studies the performance of speaker recognition

Analysis of source and system features for speaker recognition in emotional conditions
KR Alluri, VVV Raju, SV Gangashetty… – … TENCON), 2016 IEEE, 2016 – ieeexplore.ieee.org
… emotion. III. ANALYSIS OF FEATURES IN EMOTIONAL CONDITIONS Feature extraction is a vital step in building the speaker recognition system. Speech signal possess A large amount of redundancy in its representation. Feature …

Text dependent and independent speaker recognition using neural responses from the model of the auditory system
S Chowdhury, N Mamun, AAS Khan… – Electrical, Computer …, 2017 – ieeexplore.ieee.org
… systems. I. INTRODUCTION The basic of speaker recognition system is to decode the speech signal in a sequential manner based on the acoustic features of the signal between acoustic features and phonetic symbols. Here …

ART Network Based Text Independent Speaker Recognition System for Dynamically Growing Speech Database
AJ Albin, NM Nandhitha, SE Roslin – Proceedings of the 3rd International …, 2015 – Springer
Abstract Automated recognizing a speaker from the speech signals is the foremost application in forensics. Speaker recognition system involves two phases namely feature extraction and a classifier system. Features extracted from the speech signals are fed to an

A dynamic-threshold approach to text-dependent speaker recognition using principles of immune system
S Dey, K Kashyap – India Conference (INDICON), 2015 Annual …, 2015 – ieeexplore.ieee.org
… Abstract— This paper focuses on implementation of a speaker recognition system, where a user will require to provide a particular word in order to be verified as a particular user … [3] AK Sahoo, and AK Panda, “Study of Speaker Recognition Systems”, NIT Rourkela e-thesis, pp …

UTD-CRSS Systems for 2016 NIST Speaker Recognition Evaluation
C Zhang, F Bahmaninezhad, S Ranjan, C Yu… – arXiv preprint arXiv …, 2016 – arxiv.org
… 0.589 7. COMPUTATIONAL RESOURCES 7.1. CPU cluster The speaker recognition system was implemented on our in- house high-performance Dell computing cluster, running Rocks 6.0 (Mamba) Linux distribution. The cluster …

A New Speaker Recognition System with Combined Feature Extraction Techniques in Continuous Speech
P Jaiswal, P Chouksey, R Miri – Software Engineering and …, 2015 – ciitresearch.org
Abstract Speech knowledge can be conked out down into language mixture, lecturer detection and words detection. mixture refers to the process of repeatedly produce speech using a processor. The other main areas of notice both involve speech as input: whereas the

A new study of GMM-SVM system for text-dependent speaker recognition
H Sun, KA Lee, B Ma – Acoustics, Speech and Signal …, 2015 – ieeexplore.ieee.org
… This paper is organized as follows: we first give an overview of the RSR2015 databases for text-dependent speaker verification in Section 2. Section 3 describes the GMM-SVM-NAP speaker recognition system for the text- dependent evaluation …

An Efficient Speaker Recognition System by Employing BWT and ELM
A Indumathi, E Chandra – BVICAM’s International Journal of …, 2016 – bvicam.ac.in
Abstract–Speaker recognition system has gained substantial research interest, owing to security enforcement in many applications. Mostly, the speaker recognition system is employed for achieving access control. Hence, a speaker recognition system must be

A text-dependent speaker-recognition system
D Ishac, A Abche, E Karam, G Nassar… – … (I2MTC), 2017 IEEE …, 2017 – ieeexplore.ieee.org
In this work, a voice recognition approach is developed and presented. It is a based on acquiring the signal of vocal cords’ vibrations of a person using a piezoelectric transducer element attached on a collar wrapped around the neck. The recognition is then based on the

Research of neural network classifier in speaker recognition module for automated system of critical use
MM Bykov, VV Kovtun, A Smolarz… – … , Industry, and High …, 2017 – spiedigitallibrary.org
… In context of automated speaker recognition systems, this means the creating of a module that would perform speakers recognition procedure with a high probability of correct recognition in the critical systems in condition of high level noise, signal of the person who imitate …

A speaker recognition system using power spectrum density and similarity measurements
AE Maazouzi, N Aqili, M Raji… – … Systems (WCCS), 2015 …, 2015 – ieeexplore.ieee.org
Abstract: Most of speaker identification systems are based on the computation of distance or likelihood between the feature vectors of the unknown speaker and the models in the database. The identification process depends on the number of feature vectors, their

Environment and Speaker Recognition System Using MFCC
KC Nisha – History, 2015 – aetsjournal.com
Abstract—Environment recognition and speaker recognition from digital audio for forensic application is a growing area of interest. A significant amount of research can be found in the area of speech recognition or enhancement speaker recognition and authentication of

Z Hong – 2017 – jultika.oulu.fi
… 25 3.1. Implementation Platform ….. 25 3.2. Implementation of Speaker recognition system ….. 25 3.2.1. Voice Recording ….. 26 …

On the Performance Degradation of Speaker Recognition System due to Variation in Speech Characteristics Caused by Physiological Changes
U Mohammed – International Journal of Computing and Digital …, 2017 – eprints.kku.edu.sa
Speaker recognition is the process of identifying a person using their speech characteristics (voice biometrics). Speech characteristics of an individual can vary due to physiological changes which may be caused by health changes, physical activity as well as emotional

Robust speaker recognition for e-commerce system
H Anwer, S Anjum, NA Saqib – Radar, Antenna, Microwave …, 2015 – ieeexplore.ieee.org
… The design of such robust speaker recognition system can have various problems related to combined optimization of a number of processes like front-end noise removal, auditory parameter extraction and the speech modeling/recognition paradigm …

Comparison between Different Methods used in MFCC for Speaker Recognition System
SG Bagul – Journal of VLSI Design and Signal Processing, 2017 – matjournals.in
Abstract The idea of the Speaker Recognition Project is to implement a recognizer which might determine an individual by process his/her voice. The essential goal of the project is to acknowledge and classify the speeches of various persons. This classification is especially

Text Independent Automatic Speaker Recognition System using fusion of features
E MAJDA-ZDANCEWICZ… – Przegl?d …, 2015 – red.pe.org.pl
Abstract. This paper presents a speaker recognition system, which is independent of the linguistic context. The solved task includes: the preprocessing stage, the segmentation of speech signal leading to the extraction of features based on three techniques, selection of

Speaker recognition access control system
B Arrieta Fernández – 2017 – upcommons.upc.edu
… leading to different solutions that are still under research and development. The following diagram shows what the general Speaker Recognition system looks like … Page 18. 18 Feature extraction is considered the main part of any Speaker Recognition system …

Attacks on Biometric Systems for Speaker and Face Recognition
AF Baroughi – 2016 – search.proquest.com
… 17. 4 A Powerful Insider Attack on Model-based Speaker Recognition Systems 22. 4.1 Introduction . … vii. List of Tables. 3.1 Score of each speaker and speaker plus noise with SNR of 0dB to fool the speaker recognition system, and 1 unsuccessful attack out of 20 attacks …

Theoretical basis of the automated speaker recognition system of critical use identification
?? ????????, ?? ?????? – 2017 – ir.lib.vntu.edu.ua
Introduction Actual classification of critical systems divides them by the reaction to the occurrence of extraordi- nary situations and by the branch of operating. By the reaction to the appearance of extraordinary situations critical systems are divided into critical systems, which have to continue

Experimental result of the automated speaker recognition system of critical use identification
? ??????, ? ?????? – 2017 – ir.lib.vntu.edu.ua
Introduction Critical systems take a special place among the existing classes of automated systems and they oper- ate with high reliability and save its predicted level during the whole life cycle of automated system regard- less of any external conditions [1-3]. At the creation of critical systems

Whispered Speech Speaker Recognition. Listening Tests versus Speaker Recognition System
K Goliasz, M Luczynski – Audio Engineering Society Convention 142, 2017 – aes.org
ABSTRACT In this study, efficiency of different methods of whispered speech speaker recognition have been compared. Whispered speech as one of the voice disguise is causing a lot of difficulties in speaker identification. During examination of both methods authors

Study of speaker recognition system based on Feed Forward Deep Neural Networks exploring text-dependent mode
BJ Makrem, J Imen, O Kaïs – Information and Digital …, 2017 – ieeexplore.ieee.org
We aim by this work to follow the significant progress in speaker recognition systems getting the benefits of the advancement in the artificial intelligence (AI). Indeed, the deep learning algorithms have proved a real performance in the recognition and classification data. In this

Design and Implementation of an Efficient Language Independent Speaker Recognition System
P Sangwan – 2016 – shodhganga.inflibnet.ac.in
In this thesis, an algorithm for noise-robust language-independent speaker recognition system is proposed. The first phase for implementation of the proposed speaker recognition system is speaker database collection. To collect database a framework has been designed

Hybrid Biometric System Using Iris and Speaker Recognition
G Çetinel, L Çerkezi, B Yazar, D Ero?lu – 2016 – dergipark.gov.tr
… Accepted 3rd September 2016 Abstract: In this study, a hybrid security system is proposed. The proposed system is composed of two subsystems namely iris recognition system (IRS) and speaker recognition system (SRS). Pre …

Speaker recognition system using HTK
ME Chougui, G Haciane – 2015 – dlibrary.univ-boumerdes.dz
The technological strives the world is witnessing as we speak made that biometric applications for security measures and authentication are being ubiquitous in every aspect of human life. These applications are turning out to be effective and efficient in other sectors,

N GEETA – 2015 – ir.inflibnet.ac.in
Speaker recognition is the task of establishing identity of an individual based on his her voice. Due to recent advances in the field of speaker recognition, it has become possible to use these systems for authentication and in forensics. It does not require sophisticated or