43,853 Hits in 3.3 sec

Frame Selection for Text-independent Speaker Recognition

Abedenebi Rouigueb, Malek Nadil, Abderrahmane Tikourt
2017 Proceedings of the 14th International Joint Conference on e-Business and Telecommunications  
In this paper, we propose a set of criteria for the selection of the most relevant frames in order to improve text-independent speaker automatic recognition (TISAR) task.  ...  Experiments are conducted on the MOBIO database and show that the selection allows an improvement in complexity (time and space) and in speaker identification rate, which is appropriate for real-time TISAR  ...  INTRODUCTION Text-independent automatic speaker recognition (TIASR) task consists in verifying or in identifying the speaker identity using a segment of his speech where the utterance content is free  ... 
doi:10.5220/0006392100510057 dblp:conf/sigmap/RouiguebNT17 fatcat:paisdgooynde3pzxolvrowavf4

Text Independent Speaker Recognition Using Mixed MFCC and WOCOR Methods in Persian Language

Hassan Farsi, Saber Amjadi
2011 International Journal of Computer and Electrical Engineering  
Therefore it is enough for text-independent speaker recognition, to find and use these letters.  ...   Abstract-Voiced speech is usually used for speaker recognition. But in text-independent speaker recognition it would be better to use special voiced letters which are appeared in all words.  ...  Speaker recognition can also be divided into text-dependent and text-independent recognitions.  ... 
doi:10.7763/ijcee.2011.v3.350 fatcat:js2olnp6onco7dq33ajuwal2f4

Automatic Speaker Recognition: An Application of Machine Learning [chapter]

Brett Squires, Claude Sammut
1995 Machine Learning Proceedings 1995  
In a population of 30 speakers, the method described has a recognition rate of 100% for both text dependent and text independent utterances. Training times scale linearly with the population size.  ...  Speaker recognition is the identification of a speaker from features of his or her speech.  ...  Acknowledgments We thank Donald Michie for suggesting this project and Ross Quinlan for making C4.5 available.  ... 
doi:10.1016/b978-1-55860-377-6.50070-0 dblp:conf/icml/SquiresS95 fatcat:lh5wiokrsbeldkrqwshbm26gmq

Wavelet Feature Selection Using Fuzzy Approach to Text Independent Speaker Recognition

2005 IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences  
Shung-Yung LUNG †a) , Nonmember SUMMARY A wavelet feature selection derived by using fuzzy evaluation index for speaker identification is described.  ...  Our results have shown that this feature selection introduced better performance than the wavelet features with respect to the percentages of recognition. key words: speaker recognition, wavelet transform  ...  To achieve this, a novel approach for speaker identification is applied for text-independent speaker identification systems [1] .  ... 
doi:10.1093/ietfec/e88-a.3.779 fatcat:mxrbepo3nfgirclmr34qtuvahq

Assamese Speaker Recognition Using Artificial Neural Network
IJARCCE - Computer and Communication Engineering

Bhargab Medhi, Prof. P.H. Talukdar
2015 IJARCCE  
Speaker recognition is the process of Identification of the person who is speaking depending on the characteristics of his/her voices.  ...  The system contains the training phase, testing phase and recognition phase.  ...  ACKNOWLEDGMENT We are very much grateful to the different speakers for whom the record is possible to create the whole database.  ... 
doi:10.17148/ijarcce.2015.4377 fatcat:4ttznqa7kbfghmrapqekcthj4e

Speaker Identification Using Evolutionary Algorithm

Jane J. Stephan
2016 Research Journal of Applied Sciences Engineering and Technology  
Speaker recognition is the process of automatically recognizing who is speaking on the basis of individual information included in speech waves.  ...  This study provides an efficient approach for speaker identification using Discrete Wavelet Transform (DWT) and the Energy in feature extraction stage and Genetic Algorithm used in classification stage  ...  Speaker recognition methods can also be divided into text-independent and text dependent methods.  ... 
doi:10.19026/rjaset.13.3345 fatcat:gdyxeyqvbbfprcuclycxwoa47y

Deep Speaker: an End-to-End Neural Speaker Embedding System [article]

Chao Li, Xiaokong Ma, Bing Jiang, Xiangang Li, Xuewei Zhang, Xiao Liu, Ying Cao, Ajay Kannan, Zhenyao Zhu
2017 arXiv   pre-print
For example, Deep Speaker reduces the verification equal error rate by 50% (relatively) and improves the identification accuracy by 60% (relatively) on a text-independent dataset.  ...  We also present results that suggest adapting from a model trained with Mandarin can improve accuracy for English speaker recognition.  ...  Acknowledgments We would like to thank Liang Gao and Yuanqing Lin for their supports and great insights on speaker recognition.  ... 
arXiv:1705.02304v1 fatcat:iitrgu7mere7xixqm5vmfkhjxu

Combining dynamic features with MFCC for text-independent speaker identification

Amol Chaudhari, Amol Rahulkar, S. B. Dhonde
2015 2015 International Conference on Information Processing (ICIP)  
In this gives an overview of automatic speaker recognition technology, with an emphasis on textindependent recognition. Speaker recognition has been studied actively for several decades.  ...  In a text-independent system there are no constraints on the words or phrases used during verification system.  ...  Speaker recognition systems, on the other hand, can be divided into text-dependent and text-independent ones.  Text-dependent systems suited for cooperative users, the recognition phrases are fixed, or  ... 
doi:10.1109/infop.2015.7489370 fatcat:w2uqfyafm5a6netwm3dk7bt2p4

Combination of Subtractive Clustering and Radial Basis Function in Speaker Identification [article]

Ibrahim A. Albidewi, Yap Teck Ann
2010 arXiv   pre-print
Besides that, RBF neural network model using subtractive clustering algorithm for selecting the hidden node centers, which can achieve faster training speed.  ...  Speaker identification required to make a claim on the identity of speaker from the Ns trained speaker in its user database.  ...  Text-dependent and Text Independent Speaker recognition methods can be divided into two methods. There are text-dependent and text-independent.  ... 
arXiv:1004.4457v1 fatcat:doqj37ejqjaotmihdpync4jfxe

Comparison of text-independent speaker recognition methods using VQ-distortion and discrete/continuous HMM's

T. Matsui, S. Furui
1994 IEEE Transactions on Speech and Audio Processing  
We also show that the information on transitions between different states is ineffective for text-independent speaker recognition.  ...  It is also found that, for continuous ergodic HMMbased speaker recognition, the Distortion-Intersection Measure (DIM), which was introduced as a VQ-distortion measure to increase the robustness against  ...  ACKNOWLEDGMENT The authors wish to acknowledge the members of the Furui Research Laboratory of NTT Human Interface L a b oratories for their valuable and stimulating discussions.  ... 
doi:10.1109/89.294363 fatcat:eaiv3gaslfea5lxz3w6tjjpqjq

Short utterance-based video aided speaker recognition

Anthony Larcher, Jean-Francois Bonastre, John S.D. Mason
2008 2008 IEEE 10th Workshop on Multimedia Signal Processing  
Embedded speaker recognition in mobile devices could involve several ergonomic constraints and a limited amount of computing resources.  ...  It uses the GMM/UBM paradigm for the general acoustic space modelling and its text-independent speaker recognition capabilities.  ...  The log-likelihood for an input frame is only computed for each Gaussian component of the text-independent model.  ... 
doi:10.1109/mmsp.2008.4665201 dblp:conf/mmsp/LarcherBM08 fatcat:pskpyy2gtbdjvbrq5uqnrb624y

Text-independent speaker recognition based on adaptive course learning loss and deep residual network

Qinghua Zhong, Ruining Dai, Han Zhang, Yongsheng Zhu, Guofu Zhou
2021 EURASIP Journal on Advances in Signal Processing  
The proposed method was applied to a large-scale VoxCeleb2 dataset for extensive text-independent speaker recognition experiments, and average equal error rate (EER) could achieve 1.76% on VoxCeleb1 test  ...  In order to improve the recognition ability of log filter bank feature vectors, a method of text-independent speaker recognition based on deep residual networks model was proposed in this paper.  ...  Finally, text-independent speaker recognition was performed by the ACLL. Res-CASP parameters selection The Res-CASP model was trained by text-independent speaker recognition framework.  ... 
doi:10.1186/s13634-021-00762-2 fatcat:ztlnk7ahrfg4bp666nmug2u23m

From Gmm To Hmm For Embeddded Password-Based Speaker Recognition

J.F. Bonastre, Anthony Larcher, John S. Mason
2008 Zenodo  
It uses the GMM/UBM paradigm for the general acoustic space modelling and the text-independent speaker recognition abilities.  ...  The first and the second layers of this architecture present the same structure as a classical text-independent speaker recognition system.  ... 
doi:10.5281/zenodo.40922 fatcat:dhhp7adaabbn7daknccmlfz2aa

Performance Evaluation of Text-Independent Speaker Identification and Verification Using MFCC and GMM

Palivela Hema
2012 IOSR Journal of Engineering  
This paper presents the performance of a text independent speaker identification and verification system using Gaussian Mixture Model(GMM).In this paper, we adapted Mel-Frequency Cepstral Coefficients(  ...  MFCC) as speaker speech feature parameters and the concept of Gaussian Mixture Model for classification with log-likelihood estimation.  ...  GMM [1, 2] has been being the most classical method for text-independent speaker recognition.  ... 
doi:10.9790/3021-02861822 fatcat:ipdby35whfhuvk7yyrbxcx3jsu

Emotion Recognition Based On Audio Speech

Showkat Ahmad Dar Showkat Ahmad Dar
2013 IOSR Journal of Computer Engineering  
This paper presents automatic text independent speaker emotion recognition system using the pattern classification methods such as the support vector mechanics (SVM) .Acoustic features are derived from  ...  SVMs are used to construct the optimal separating hyper plane for speech features .SVMs are used to build the models for each speaker and to compare with the test speaker's feature vectors.  ...  Speaker recognition systems can be classified into text dependent and text independent systems.  ... 
doi:10.9790/0661-1164650 fatcat:adjpwzuvqngpzmhguvgxer3gbq
« Previous Showing results 1 — 15 out of 43,853 results