Study of robust feature extraction techniques for speech recognition system

Sharma, Usha; Maheshkar, Sushila; Mishra, Achyuta Nand

doi:10.1109/ablaze.2015.7154944

Cited by 17 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LPCCs, which are the coefficients of the Fourier transform representation of the log magnitude of the spectrum, are typically used instead of the original predictor coefficients since they are considered more robust for audio classification purposes. 45 The LPCCs, C , for each frame, m , were calculated from the linear predictor coefficients, a , according to equation (4) 46…”

Section: Methodsmentioning

confidence: 99%

An experimental investigation into passive acoustic damage detection for structural health monitoring of wind turbine blades

Solimine

Niezrecki

İnalpolat

2020

Structural Health Monitoring

View full text Add to dashboard Cite

This article details the implementation of a novel passive structural health monitoring approach for damage detection in wind turbine blades using airborne sound. The approach utilizes blade-internal microphones to detect trends, shifts, or spikes in the sound pressure level of the blade cavity using a limited network of internally distributed airborne acoustic sensors, naturally occurring passive system excitation, and periodic measurement windows. A test campaign was performed on a utility-scale wind turbine blade undergoing fatigue testing to demonstrate the ability of the method for structural health monitoring applications. The preliminary audio signal processing steps used in the study, which were heavily influenced by those methods commonly utilized in speech-processing applications, are discussed in detail. Principal component analysis and K-means clustering are applied to the feature-space representation of the data set to identify any outliers (synonymous with deviations from the normal operation of the wind turbine blade) in the measurements. The performance of the system is evaluated based on its ability to detect those structural events in the blade that are identified by making manual observations of the measurements. The signal processing methods proposed within the article are shown to be successful in detecting structural and acoustic aberrations experienced by a full-scale wind turbine blade undergoing fatigue testing. Following the assessment of the data, recommendations are given to address the future development of the approach in terms of physical limitations, signal processing techniques, and machine learning options.

show abstract

Section: Methodsmentioning

confidence: 99%

An experimental investigation into passive acoustic damage detection for structural health monitoring of wind turbine blades

Solimine

Niezrecki

İnalpolat

2020

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…Several works have been conducted to compare ASR features extraction techniques [1][2] [3][4][5] [6]. Most of this research has been focused on the advantages and disadvantages of each extraction method.…”

Section: Related Workmentioning

confidence: 99%

Automatic Speech Recognition Features Extraction Techniques: A Multi-criteria Comparison

Labied¹,

Belangour²

2021

IJACSA

View full text Add to dashboard Cite

Features extraction is an important step in Automatic Speech Recognition, which consists of determining the audio signal components that are useful for identifying linguistic content while removing background noise and irrelevant information. The main objective of features extraction is to identify the discriminative and robust features in the acoustic data. The derived feature vector should possess the characteristics of low dimensionality, long-time stability, nonsensitivity to noise, and no correlation with other features, which makes the application of a robust feature extraction technique a significant challenge for Automatic Speech Recognition. Many comparative studies have been carried out to compare different speech recognition feature extraction techniques, but none of them have evaluated the criteria to be considered when applying a feature extraction technique. The objective of this work is to answer some of the questions that may arise when considering which feature extraction techniques to apply, through a multicriteria comparison of different features extraction techniques using the Weighted Scoring Method.

show abstract

“…Because it relies on auto-correlaton analysis, MFCC shares the trait with LPC that it is not noise robust [13, p. 358]; although there are many MFCC variants, each with their own improvements and compromises [14]. Other feature extraction techniques include Perceptual Linear Predictive Coefficients (PLP), which are often used in conjunction with RASTA for improved performance; Wavelet-based features; and Linear Predictive Cepstral Coefficients (LPCC), an addition to LPC [13][14][15][16]. The work performed in [3, p.83] contrasts LPCC and MFCC, demonstrating that LPCC generally results in lower accuracy but has a faster computation rate while MFCC is slower to compute, but often results in improved recognition accuracy.…”

Section: Feature Extraction Techniques Used In Asr Systemsmentioning

confidence: 99%

A Model for the Application of Automatic Speech Recognition for Generating Lesson Summaries

Blunt¹,

Haskins²

2021

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Automatic Speech Recognition (ASR) technology has the potential to improve the learning experience of students in the classroom. This article addresses some of the key theoretical areas identified in the pursuit of implementing a speech recognition system, capable of lesson summary generation in the educational setting. The article discusses: some of the applications of ASR technology in education; prominent feature extraction and speech enhancement techniques typically applied to digital speech; and established neural network-based machine learning models capable of keyword spotting or continuous speech recognition. Following the theoretical investigation, a model is proposed for the implementation of an automatic speech recognition system in a noisy educational environment to facilitate automated, speech-driven lesson summary generation. A prototype system was developed and improved based on this model, ultimately proving itself capable of generating a lesson summary intended to bolster students' secondary contact with lesson content. This topic-oriented lesson summary provides students with a lesson transcript, but also helps them to monitor educator-defined keyword terms, their prevalence and order as communicated in the lesson, and their associations with educatordefined sections of course content. The prototype was developed using the Python programming language with a modular approach so that its implemented Continuous Speech Recognition system and noise management technique could be chosen at run-time. The prototype contrasts the performance of CMUSphinx and Google Speech Recognition for ASR, both accessed via a cloud-based programming library, and compared the change in accuracy when applying noise injection, noise cancellation or noise reduction to the educator's speech. Proof of concept was established using the Google Speech Recognition System, which prevailed over CMUSphinx and enabled the prototype to achieve 100,00% accuracy in keyword identification and association on noise-free speech, contrasted with a 96,93% accuracy in keyword identification and association on noise-polluted speech using a noise-cancellation technique.

show abstract

Study of robust feature extraction techniques for speech recognition system

Cited by 17 publications

References 11 publications

An experimental investigation into passive acoustic damage detection for structural health monitoring of wind turbine blades

An experimental investigation into passive acoustic damage detection for structural health monitoring of wind turbine blades

Automatic Speech Recognition Features Extraction Techniques: A Multi-criteria Comparison

A Model for the Application of Automatic Speech Recognition for Generating Lesson Summaries

Contact Info

Product

Resources

About