Automatic speech recognition (ASR) has been under the scrutiny of researchers for many years. Speech Recognition System is the ability to listen what we speak, interpreter and perform actions according to spoken information. After so many detailed study and optimization of ASR and various techniques of features extraction, accuracy of the system is still a big challenge. The selection of feature extraction techniques is completely based on the area of study. In this paper, a detailed theory about features extraction techniques like LPC and LPCC is examined. The goal of this paper is to study the comparative analysis of features extraction techniques like LPC and LPCC.

LPC and LPCC method of feature extraction in Speech Recognition System

As the most widely used coupling structure in electromechanical systems, bolt coupling is the important part in these systems. The reliability and strength of bolted joint are affected by pretensio...

Bolt loosening detection based on audio classification

Although biometrics is being increasingly used across the world, it also raises concerns over privacy and security of the enrolled identities. This is due to the fact that biometrics are not cancelable and if compromised may give access to the intruder. To address these problems, in this paper, we suggest two simple and powerful techniques called (i) Random Permutation Principal Component Analysis (RP-PCA) and (ii) Random Permutation Two Dimensional Principal Component Analysis (RP-2DPCA). The proposed techniques are based on the idea of cancelable biometric which can be reissued if compromised. The proposed techniques work in a cryptic manner by accepting the cancelable biometric template and a key (called PIN) issued to a user. The identity of a person is recognized only if the combination of template and PIN is valid, otherwise the identity is rejected. The superiority of the proposed techniques is demonstrated on three freely available face (ORL), iris (UBIRIS) and ear (IITD) datasets against state-of-the-art methods. The key advantages of the proposed techniques are (i) classification accuracy remains unaffected due to cancelable biometric templates generated using random permutation (ii) robustness across different biometrics. In addition, no image registration is required for performing recognition.

Random permutation principal component analysis for cancelable biometric recognition

Late fusion framework for Acoustic Scene Classification using LPCC, SCMC, and log-Mel band energies with Deep Neural Networks

Modern automatic speaker verification relies largely on deep neural networks (DNNs) trained on mel-frequency cepstral coefficient (MFCC) features. While there are alternative feature extraction methods based on phase, prosody and long-term temporal operations, they have not been extensively studied with DNN-based methods. We aim to fill this gap by providing extensive re-assessment of 14 feature extractors on VoxCeleb and SITW datasets. Our findings 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. Experimental results demonstrate up to 16.3% (VoxCeleb) and 25.1% (SITW) relative decrease in equal error rate (EER) to the baseline.

/pdf/a-comparative-re-assessment-of-feature-extractors-for-deep-46h4j450bx.pdf

A Comparative Re-Assessment of Feature Extractors for Deep Speaker Embeddings

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.

Jinlong Ma

Papers

Speaker recognition based on principal component analysis of LPCC and MFCC