4 Hits in 5.0 sec

Cochannel speaker count labelling based on the use of cepstral and pitch prediction derived features

Michael A. Lewis, Ravi P. Ramachandran
2001 Pattern Recognition  
For the feature extraction step, we propose a new pitch prediction feature (PPF) which is compared with the linear Predictive cepstral coe$cients (LPCC) and the mel frequency cepstral coe$cients (MFCC)  ...  The superiority of the PFF comes with the added bene"ts of using a scalar feature as opposed to the 12-dimensional vectorial LPCC and MFCC features and a lower VQ codebook size.  ...  We develop a new feature called the pitch prediction feature (PPF) based on the concept of pitch prediction that is used in speech coding.  ... 
doi:10.1016/s0031-3203(00)00004-2 fatcat:da4d7v5ovzh6pcvhxg5veakpga

An Overview of Speaker Identification: Accuracy and Robustness Issues

Roberto Togneri, Daniel Pullella
2011 IEEE Circuits and Systems Magazine  
The results showed that recognition performance using both the filterbank based (MFCC, LFCC) and linear predictive based cepstral features (LPCC, PLPCC) degraded significantly in the presence of mismatched  ...  Linear predictive (LP) analysis features are based on an all-pole model which captures vocal tract information in the magnitude spectrum of the LP filter response, and pitch information within the LP residual  ... 
doi:10.1109/mcas.2011.941079 fatcat:jnp75b7tjvaq5f3jfyoroolmuy

Performance Evaluation of Different Data Mining Classification Algorithm and Predictive Analysis

Syeda Farha Shazmeen Syeda Farha Shazmeen
2013 IOSR Journal of Computer Engineering  
and improve the performance by applying data preprocessing techniques and feature selection and also prediction of new class labels.  ...  Based on the combination of the four features, Fisher developed a linear discriminant model to distinguish the species from each other classification method to identify the class of Iris flower as Irissetosa  ...  For this we designed our SNS in php which has the primary features of any Social Networking Site like Facebook. Then we implemented few of the proposed policies on it.  ... 
doi:10.9790/0661-1060106 fatcat:ffw6zxhlajaljmhstlrz6tbqhe

Welcome Messages

2019 2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)  
The developed H-BTC database comprises of 30K images comprising of the five types of H-BTC images in which three categories are constructed based on digital halftoning and two types are based on digital  ...  The application of the H-BTC images range from image compression and retrieval, indexing, reconstruction, classification and so on.  ...  Based on the work of Guo and Li [2] , Lin used the wavelet transform to extract sub-band energy and pitch frequency [4] as features of voices.  ... 
doi:10.1109/ispacs48206.2019.8986291 fatcat:gu4zaxsqkncp5n2ebj5fybk7ce