An efficient approach using HOS-based parameters in the LPC residual domain to classify breathy and rough voices

Lee, Ji-Yeoun; Jeong, Sangbae; Hahn, Minsoo; Sprecher, Alicia J.; Jiang, Jack J.

doi:10.1016/j.bspc.2010.09.003

Cited by 5 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some papers have utilized Higher-Order Statistics (HOS) for pitch estimation. Many studies have applied HOS to disordered voices, since, Alonso et al (2001) published on the automatic detection of voice pathologies by HOS-based parameters (Lee et al, 2008a, b;Lee et al, 2011;Lee, 2012). Furthermore, the combination of HOS analysis and the Linear Predictive Coding (LPC) residual may help to effectively construct important information to distinguish the signal types of disordered voices Lee et al, 2011;Lee and Choi, 2012).…”

Section: Introductionmentioning

confidence: 99%

Comparison of Voice Analysis Programs for Fundamental Frequency Measurement in Elderly Voice Signals Through Gender Analysis

Seo¹,

Lee²

2019

J. Eng. Appl. Sci.

View full text Add to dashboard Cite

Changes in the vocal folds due to aging may change the pitch of the voice. An elderly signal can be automatically distinguished from a normal signal through various analyses. With most smart biomedical devices, elderly voices have been neglected due to optimization that does not take the elderly into account. The objective of this study was to use a symmetric higher-order differential energy function to analyze the elderly signal and extract the fundamental frequency. This study suggests a symmetric higher-order differential energy function based on gender analysis. The elderly voices of 40 Korean subjects (20 females and 20 males) ranging in age from 70-80 years were used. Symmetrical instantaneous frequency estimators with orders 5 and 4 were selected for female and male voices, respectively in this study through gender analysis. The experiments were compared to the F0 extracted by various methods such as manual extraction, WaveSurfer, TF32, Praat and an instantaneous frequency estimator based on before-and-after gender analysis. The F0 value obtained through the instantaneous frequency estimator after gender analysis is the most similar to the results from manual extraction, exhibiting an accuracy of 80%. The results will help to provide ease of access for the elderly by means of speech. Future investigations will incorporate multiple analytical methods to implement more reliable detectors for automated medical diagnostic systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison of Voice Analysis Programs for Fundamental Frequency Measurement in Elderly Voice Signals Through Gender Analysis

Seo¹,

Lee²

2019

J. Eng. Appl. Sci.

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…Many studies have applied HOS to disordered voices since Alonso et al's publication on automatic detection of voice pathologies by HOS-based parameters [13]- [18]. Further, the combination of HOS analysis and the linear predictive coding (LPC) residual may help to effectively construct important information to distinguish the signal types of disordered voices [17]- [18]. Although HOS analysis holds promise as one possible method of distinguishing between normal/pathological voices and signal type classification [14]- [16], no studies have applied HOS analysis to analyze elderly voices.…”

Section: Introductionmentioning

confidence: 99%

Feature Extraction of Elderly Signals based on Bicoherence Estimation for Automated Medical Diagnosis System

Lee¹

2017

IJCA

View full text Add to dashboard Cite

show abstract

Identification of oestrus cows based on vocalisation characteristics and machine learning technique using a dual-channel-equipped acoustic tag

Wang¹,

Chen²,

Wang³

et al. 2023

animal

View full text Add to dashboard Cite

An efficient approach using HOS-based parameters in the LPC residual domain to classify breathy and rough voices

Cited by 5 publications

References 24 publications

Comparison of Voice Analysis Programs for Fundamental Frequency Measurement in Elderly Voice Signals Through Gender Analysis

Comparison of Voice Analysis Programs for Fundamental Frequency Measurement in Elderly Voice Signals Through Gender Analysis

Feature Extraction of Elderly Signals based on Bicoherence Estimation for Automated Medical Diagnosis System

Identification of oestrus cows based on vocalisation characteristics and machine learning technique using a dual-channel-equipped acoustic tag

Contact Info

Product

Resources

About