Proceedings ArticleDOI
Speaker recognition based on principal component analysis of LPCC and MFCC
Xinxing Jing,Jinlong Ma,Jing Zhao,Haiyan Yang +3 more
- pp 403-408
Reads0
Chats0
TLDR
A new method of extracting mixed characteristic parameters using the principal component analysis (PCA) based on widely use of the PCA and K-means clustering in image and speech signal processing is introduced.Abstract:
This paper introduces a new method of extracting mixed characteristic parameters using the principal component analysis (PCA), this method proposed is based on widely use of the PCA and K-means clustering in image and speech signal processing. The first work is systematic study of extracting algorithm and theory for speaker recognition system, which is on the most commonly used LPCC (Linear Prediction Cepstrum Coefficient), MFCC (Mel Frequency Cepstrum Coefficient) and differential parameter. Therefore, we select combination of the LPCC, MFCC and the first-order differential parameter as the characteristic parameter. After calculating by means of PCA, the characteristic parameter reduce the orders of each frame of speech signal, and then reduce the frame numbers through the K-means clustering , finally recognizing speaker by VQ. The experimental results show that, this method not only reduces the computational complexity, but also increases correct recognition rate.read more
Citations
More filters
Proceedings ArticleDOI
LPC and LPCC method of feature extraction in Speech Recognition System
Harshita Gupta,Divya Gupta +1 more
TL;DR: The goal of this paper is to study the comparative analysis of features extraction techniques like LPC and LPCC.
Journal ArticleDOI
Bolt loosening detection based on audio classification
TL;DR: A bolt loosening detection method based on audio classification that has high recognition accuracy and strong noise immunity and can effectively reduce the occurrence of disasters is presented.
Journal ArticleDOI
Random permutation principal component analysis for cancelable biometric recognition
TL;DR: Two simple and powerful techniques called Random Permutation Principal Component Analysis (RP-PCA and RP-2DPCA) are suggested which provide classification accuracy remains unaffected due to cancelable biometric templates generated using random permutation and robustness across different biometrics.
Journal ArticleDOI
Late fusion framework for Acoustic Scene Classification using LPCC, SCMC, and log-Mel band energies with Deep Neural Networks
TL;DR: This study has experimented on Detection and Classification of Acoustic Scenes and Events (DCASE) 2018 development dataset and DCASE 2017 dataset, and carried out experiments with individual feature sets, and also performed decision level DNN score fusions for improving the performance.
Proceedings ArticleDOI
A Comparative Re-Assessment of Feature Extractors for Deep Speaker Embeddings
TL;DR: This work provides extensive re-assessment of 14 feature extractors on VoxCeleb and SITW datasets to reveal that features equipped with techniques such as spectral centroids, group delay function, and integrated noise suppression provide promising alternatives to MFCCs for deep speaker embeddings extraction.
References
More filters
Proceedings ArticleDOI
Speaker Recognition and Speech Emotion Recognition Based on GMM
Shupeng Xu,Yan Liu,Xiping Liu +2 more
TL;DR: This paper put forward a method for speaker recognition and speech emotion recognition based on GMM that extracted the Mel Frequency Cepstral Coefficients from each frame of the speech signal as speech features, and applied Gaussian mixture model as a statistical classifier.
Journal Article
Speaker recognition method using MFCC and LPCC features
TL;DR: The result shown that this method can efficiently accelerate the recognition capacity of the system and it proves that the robustness of MFCC parameter is prior to that of LPCC parameter.
Journal Article
The Study of Several Speech Recognition Feature Parameters
TL;DR: The results show that the recognition rate of MFCC+△MFCC is highest,LPCC is lowest and the recognition method of DTW is studied.
Journal Article
Discuss and research of face recognition based on PCA algorithm
TL;DR: The test of face image database with PCA is presented and the projection result is classified using the 2-norm distance classifier to achieve the goal of recognition.
Journal Article
Chinese dialects identification based on mixed characteristic parameters and BP_Adaboost
TL;DR: A kind of model combining the BP neural network with the Adaboost is proposed to identify isolated words of Hunan dialect speaker-independently and the experimental results show that this hybrid model has stronger robustness and higher recognition rate than the pure BP neuralnetwork under relatively low signal to noise ratio.