711 Hits in 4.7 sec

Speaker identification features extraction methods: A systematic review

Sreenivas Sremath Tirumala, Seyed Reza Shahamiri, Abhimanyu Singh Garhwal, Ruili Wang
2017 Expert systems with applications  
Speaker Identification (SI) is the process of identifying the speaker from a given utterance by comparing the voice biometrics of the utterance with those utterance models stored beforehand.  ...  , and noise robustness.  ...  Kernel Principal Component Analysis) and KMDA (Kernel Multimodal Component Analysis) ICA (Independent Component Analysis) Principal Component Transformation Reducing the features dimension by using DKLT  ... 
doi:10.1016/j.eswa.2017.08.015 fatcat:stdgc7wnvzcldir3ipogzi43te

Investigations into the Robustness of Audio-Visual Gender Classification to Background Noise and Illumination Effects

Darryl Stewart, Hongbin Wang, Jiali Shen, Paul Miller
2009 2009 Digital Image Computing: Techniques and Applications  
In other work, Buchala et al [4] analyzed the importance of principal component analysis (PCA) order in classifying faces with respect to gender, ethnicity, age and identity.  ...  with respect to the first M principal nal decomposition of the tually exclusive and principal subspace l components, and its .  ... 
doi:10.1109/dicta.2009.34 dblp:conf/dicta/StewartWSM09 fatcat:oie5xdbhfnhvpn6xenjnw5ulo4

A Novel Minimum Divergence Approach to Robust Speaker Identification [article]

Ayanendranath Basu, Smarajit Bose, Amita Pal, Anish Mukherjee, Debasmita Das
2015 arXiv   pre-print
This approach is made more robust to the presence of outliers, through the use of suitably modified versions of the standard divergence measures.  ...  Moreover, the ubiquitous principal component transformation, by itself and in conjunction with the principle of classifier combination, is found to further enhance the performance.  ...  Acknowledgement The authors gratefully acknowledge the contribution of Ms Disha Chakrabarti and Ms Enakshi Saha to this work.  ... 
arXiv:1512.05073v1 fatcat:tgbsbfp2mfd3vashbkqgiepnqq

Multiple views of the response of an ensemble of spectro-temporal features support concurrent classification of utterance, prosody, sex and speaker identity

M. Coath, J. M. Brader, S. Fusi, S. L. Denham
2005 Network  
of the speaker.  ...  We have also shown that this is robust with respect to the exact choice of feature set, moderate time compression in the stimulus and speaker variation.  ...  PCA analysis of network weights In order to investigate the contribution of each feature to the classification of each of the letters, we performed a principal components analysis of the neural network  ... 
doi:10.1080/09548980500290120 pmid:16411500 fatcat:yhfuxebuhjbpbi4henhrrpyb5q

Facial gender recognition using multiple sources of visual information

Federico Matta, Usman Saeed, Caroline Mallauran, Jean-Luc Dugelay
2008 2008 IEEE 10th Workshop on Multimedia Signal Processing  
In the end, we implement an integration step to combine the similarity scores of the two parallel subsystems, using a suitable opinion fusion (or score fusion) strategy.  ...  on a probabilistic extension of the eigenface approach.  ...  More precisely, each vectorised image The optimal projection matrix W is computed using the principal component analysis (PCA) (also called the Karhunen-Loeve transform (KLT)), which has the property of  ... 
doi:10.1109/mmsp.2008.4665181 dblp:conf/mmsp/MattaSMD08 fatcat:oiciygpyofghdbqxv6w3yvxzeq

On the development of an automatic voice pleasantness classification and intensity estimation system

Luis Pinto-Coelho, Daniela Braga, Miguel Sales-Dias, Carmen Garcia-Mateo
2013 Computer Speech and Language  
Abstract In the last few years, the number of systems and devices that use voice based interaction has grown significantly.  ...  For a continued use of these systems, the interface must be reliable and pleasant in order to provide an optimal user experience.  ...  In the first category we can find linear methods, such as Principal Components Analysis or Multidimensional Scaling (Borg and Groenen, 2005) , and non-linear methods, like Self Organizing Maps (Kohonen  ... 
doi:10.1016/j.csl.2012.01.006 fatcat:ivvp3qpxijg4rnqingsppx6mb4

Time-Frequency Bibliography [chapter]

2003 Time Frequency Analysis  
"Application of time-frequency principal component analysis to text-independent speaker identification". IEEE Trans. on Speech & Audio Processing, 10(6):371-378, September 2002. [295] S. G.  ...  using time-lag kernel, 665 -discrete, 240, 241, 271 -for component extraction, 361 -for component separation, 366 -of EEG signals, 664, 665, 667-669 backscattering, see scattering band-limited  ... 
doi:10.1016/b978-008044335-5/50038-3 fatcat:tfc7wkllejcdvcbtqalinh5t3y

Face Recognition: Issues, Methods and Alternative Applications [chapter]

Waldemar Wójcik, Konrad Gromaszek, Muhtar Junisbekov
2016 Face Recognition - Semisupervised Classification, Subspace Projection and Evaluation Methods  
Face recognition, as one of the most successful applications of image analysis, has recently gained significant attention.  ...  The final part of the chapter describes chosen face recognition methods and applications and their potential use in areas not related to face recognition.  ...  Many applications have shown good results of the linear projection appearance-based methods such as principal component analysis (PCA) [5] , independent component analysis (ICA) [6] , linear discriminate  ... 
doi:10.5772/62950 fatcat:ucj2xyk2ovflfd74nouozqlrmy

Machine Learning Methods in the Application of Speech Emotion Recognition [chapter]

Ling Cen, Minghui Dong, Haizhou Li Zhu Liang Yu, Paul Ch
2010 Application of Machine Learning  
Principal Component Analysis (PCA) was applied to further reduce the dimension of the features selected using the FS method.  ...  In order to reduce computational cost in classification, Principal Component Analysis (PCA) is employed for reducing feature dimensionality.  ...  The wide scope of the book provides them with a good introduction to many application researches of machine learning, and it is also the source of useful bibliographical information.  ... 
doi:10.5772/8613 fatcat:2mau3sve45ep5dk3vd5vyvnlyq

Assessing Effectiveness of Exercised Variants of Machine Learning Techniques

Currently, the research field of machine learning is receiving more attention due to the automatic visual inspection of different tasks.  ...  Also, this study evaluates the performance of various machine learning methods and their applications in different fields and also their limitations.  ...  statistics, principal components analysis, and ANN.  ... 
doi:10.35940/ijitee.d1781.029420 fatcat:3dig3j6ja5hovmazntsm3ldt3m

Face Recognition: A Survey

Shailaja A Patil1 And Dr. P. J. Deore2
2013 Zenodo  
The methods which are used to extract features are robust to low-resolution images. The method is a trainable system for selecting face features.  ...  Firstly, they tried to extract the face image features by principal component analysis, Independent component analysis and linear discriminant analysis methods.  ...  and corresponds to template matching.The statistical tools such as Support Vector Machines (SVM) (E.Osuna, 1997), (Vladimir N, 1995) Independent component Analysis, Principal Component Analysis (PCA)  ... 
doi:10.5281/zenodo.1438611 fatcat:gmznwbriuvccrnyj4pgbbzxuci

Unit commitment considering multiple charging and discharging scenarios of plug-in electric vehicles

Zhile Yang, Kang Li, Qun Niu, Aoife Foley
2015 2015 International Joint Conference on Neural Networks (IJCNN)  
Principe P131 Non-negative Matrix Factorization based on Gamma-Divergence [#15559] Kohei Machida and Takashi Takenouchi P132 Independent Component Analysis with an Inverse Problem Motivated Penalty  ...  Ensembles of Neural Networks [#15429] Mashud Rana, Irena Koprinska and Vassilios Agelidis 9:30AM Towards robust flood forecasts using neural networks [#15464] Seyyed Adel Alavi Fazel, Hamid Mirfenderesk  ... 
doi:10.1109/ijcnn.2015.7280446 dblp:conf/ijcnn/YangLNF15 fatcat:6xlakikcfzfyhhm2spooe2j7ra

Analysis of the IJCNN 2011 UTL challenge

Isabelle Guyon, Gideon Dror, Vincent Lemaire, Daniel L. Silver, Graham Taylor, David W. Aha
2012 Neural Networks  
The goal was to learn data representations that capture regularities of an input space for re-use across tasks.  ...  The analysis indicates that learned data representations yield significantly better results than those obtained with original data or data preprocessed with standard normalizations and functional transforms  ...  This project is part of the DARPA Deep Learning program and is an activity of the Causality Workbench supported by the Pascal network of excellence funded by the European Commission and by the U.S.  ... 
doi:10.1016/j.neunet.2012.02.010 pmid:22374109 fatcat:gaoeexsksfaehaf5xaoirg773y

SIFT-Bag kernel for video event analysis

Xi Zhou, Xiaodan Zhuang, Shuicheng Yan, Shih-Fu Chang, Mark Hasegawa-Johnson, Thomas S. Huang
2008 Proceeding of the 16th ACM international conference on Multimedia - MM '08  
components with high-variability for video clips of the same event.  ...  On the other hand, the SIFT-Bag Kernel is used in a Support Vector Machine for margin-based video event classification.  ...  Government VACE Program, National Science Foundation Grant IIS-0534106, and AcRF Tier 1 Grant of R-263-000-464-112, Singapore. We thank Prof.  ... 
doi:10.1145/1459359.1459391 dblp:conf/mm/ZhouZYCHH08 fatcat:w6vlrvl3tjhjpm7ravblvtueom

Speech synthesis from neural decoding of spoken sentences

Gopala K. Anumanchipalli, Josh Chartier, Edward F. Chang
2019 Nature  
Decoded articulatory representations were highly conserved across speakers, enabling a component of the decoder to be transferrable across participants.  ...  These findings advance the clinical viability of using speech neuroprosthetic technology to restore spoken communication.  ...  Using principal components analyses, the 32 spectral features were projected onto the first four principal components before fitting the Gaussian kernel density estimate (KDE) model.  ... 
doi:10.1038/s41586-019-1119-1 pmid:31019317 fatcat:7taeckhko5fhnbk4gwio4y2ogy
« Previous Showing results 1 — 15 out of 711 results