Feature Extraction Methods Proposed for Speech Recognition Are Effective on Road Condition Monitoring Using Smartphone Inertial Sensors

Abstract

The objective of our project is to develop an automatic survey system for road condition monitoring using smartphone devices. One of the main tasks of our project is the classification of paved and unpaved roads. Assuming recordings will be archived by using various types of vehicle suspension system and speeds in practice, hence, we use the multiple sensors found in smartphones and state-of-the-art machine learning techniques for signal processing. Despite usually not being paid much attention, the results of the classification are dependent on the feature extraction step. Therefore, we have to carefully choose not only the classification method but also the feature extraction method and their parameters. Simple statistics-based features are most commonly used to extract road surface information from acceleration data. In this study, we evaluated the mel-frequency cepstral coefficient (MFCC) and perceptual linear prediction coefficients (PLP) as a feature extraction step to improve the accuracy for paved and unpaved road classification. Although both MFCC and PLP have been developed in the human speech recognition field, we found that modified MFCC and PLP can be used to improve the commonly used statistical method.

Design and Implementation of Machine Tool Life Inspection System Based on Sound Sensing

“…There are many algorithms for feature extraction, and MFCC is a more common method [ 13 , 14 , 15 , 16 ]. It is a speech feature algorithm developed based on human hearing, which can imitate the features obtained by the human ear in different frequency bands.…”

Classification of three pathological voices based on specific features groups using support vector machine

“…A Mel is a unit of measure based on the human ears perceived frequency where human ears are not sensitive enough to detect sounds below 1000 Hz when frequency warping process occurs, the coefficients of each short time Fourier transformed (STFT) are multiplied by the corresponding filter gain. A popular formula to convert f in hertz into 𝑓 𝑚𝑒𝑙 is given in (3) [12]- [14]. The DCT applied to the transformed Mel frequency coefficients produced a set of MFCC campestral coefficients.…”

Classification of Chest X-Ray Images using Wavelet and MFCC Features and Support Vector Machine Classifier

“…The resulting 1-D signal is a non-stationary signal, therefore analysis should always be performed by blocking the signal into possibly overlapping frames, so that the signal is constant [20]. In this step, the continuous 1-D signal is broken into 60 frames of N=2000 samples, with consecutive frames separated by L=512 samples.…”

“…These energies are also known as the Mel spectrum and can be used for calculating the first 13 coefficients using DCT. A popular formula to convert f in hertz into ݂ is given in (2) [20,21]:…”