Using Jitter and Shimmer in speaker verification

Farrús, Mireia; Hernando, Javier

doi:10.1049/iet-spr.2008.0147

Cited by 58 publications

(31 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Both magnitudes can be measured according to different criteria resulting in a set of jitter and shimmer measures providing different results at every pitch cycle. In this contribution we have chosen to include a subset of these (see Table 3) that have been successfully used in speaker verification [34]. We will test their ability to discriminate between our two classes and to analyze whether an abnormal condition of the vocal folds could be induced by OSA (e.g., inflammation caused by frequent snoring).…”

Section: Identifiable Deviations Of the Vocal Tract From An Idealmentioning

confidence: 99%

Improving Automatic Detection of Obstructive Sleep Apnea Through Nonlinear Analysis of Sustained Speech

et al. 2012

View full text Add to dashboard Cite

We present a novel approach for the detection of severe obstructive sleep apnea (OSA) based on patients' voices introducing nonlinear measures to describe sustained speech dynamics. Nonlinear features were combined with state-of-the-art speech recognition systems using statistical modeling techniques (Gaussian mixture models, GMMs) over cepstral parameterization (MFCC) for both continuous and sustained speech. Tests were performed on a database including speech records from both severe OSA and control speakers. A 10 % relative reduction in classification error was obtained for sustained speech when combining MFCC-GMM and nonlinear features, and 33 % when fusing nonlinear features with both sustained and continuous MFCC-GMM. Accuracy reached 88.5 % allowing the system to be used in OSA early detection. Tests showed that nonlinear features and MFCCs are lightly correlated on sustained speech, but uncorrected on continuous speech. Results also suggest the existence of nonlinear effects in OSA patients' voices, which should be found in continuous speech.

show abstract

Section: Identifiable Deviations Of the Vocal Tract From An Idealmentioning

confidence: 99%

Improving Automatic Detection of Obstructive Sleep Apnea Through Nonlinear Analysis of Sustained Speech

et al. 2012

View full text Add to dashboard Cite

show abstract

“…However, both magnitudes can be measured according to different criteria resulting in a set of jitter and shimmer measurements. In the present contribution we have chosen to include a subset of those (see Table 1) which have been successfully used for speaker verification [16] in order to test their discriminative power. Table 1.…”

Section: Measures On Sustained Speech Dynamicsmentioning

confidence: 99%

Introducing Non-linear Analysis into Sustained Speech Characterization to Improve Sleep Apnea Detection

Blanco

Hernández

Fernández

et al. 2011

Advances in Nonlinear Speech Processing

View full text Add to dashboard Cite

Esta es la versión de autor de la comunicación de congreso publicada en: This is an author produced version of a paper published in: Abstract. We present a novel approach for detecting severe obstructive sleep apnea (OSA) cases by introducing non-linear analysis into sustained speech characterization. The proposed scheme was designed for providing additional information into our baseline system, built on top of state-of-the-art cepstral domain modeling techniques, aiming to improve accuracy rates. This new information is lightly correlated with our previous MFCC modeling of sustained speech and uncorrelated with the information in our continuous speech modeling scheme. Tests have been performed to evaluate the improvement for our detection task, based on sustained speech as well as combined with a continuous speech classifier, resulting in a 10% relative reduction in classification for the first and a 33% relative reduction for the fused scheme. Results encourage us to consider the existence of non-linear effects on OSA patients' voices, and to think about tools which could be used to improve short-time analysis.

show abstract

“…The amplitude of vibration called the Shimmer depends on the tension of vocal folds and subglotic pressure of the air column. [7,10,[15][16][17] This imbalanced movement of the vocal fold results in excessive breathiness (turbulent noise), which can be measured by Harmonics to Noise Ratio (HNR) and Noise to Harmonics Ratio (NHR). [18] A free shareware program "PRAAT" was used to quantify these time domain features.…”

Section: Time Domain Featuresmentioning

confidence: 99%

“…[2,5] The voice changes may include changes in the pitch, cycleto-cycle variations; jitter, decrease in amplitude; shimmer, loss of power, addition of noises; harmonic to noise ratios, constriction of voice range; i.e., displacement towards lower frequency. [2,3,6,7] The normal acoustic features lie in the frequency range 20 Hz -4,000 Hz, but the pathological voice features are spread over 20 Hz -20 kHz. The changes in the acoustic features may not be noticeable by normal hearing.…”

Section: Introductionmentioning

confidence: 99%

A hybrid model for neurological disordered voice classification using time and frequency domain features

K¹,

Holi

2015

AIR

View full text Add to dashboard Cite

Different neurological disorders may lead to speech related problems, due to paralysis in vocal fold or weakness of the related muscles. This may modify the acoustic characteristics of the subject's voice which may provide important information for detecting certain neurological diseases. The vowel phonation which is acoustically informative and uttered by the patient with not much difficulty is collected and various acoustic features are extracted by time domain and frequency domain techniques. The use of all these features for classification may lead to a large feature space, which may lead to complexity. Hence to avoid this, in the present work experimentation is done by fusing different classifiers which are fed with features extracted from different domains. The time domain and frequency domain features are given to Support Vector Machine (SVM) and Gaussian Mixture Model (GMM) respectively, and the intermediate decision of these classifiers is given to another SVM to identify the voice signal as normal or diseased. It is observed that this hybrid classifier model has shown some improvement with a classification accuracy of 91.43% compared to single GMM classifier with an accuracy of classification of 90% with frequency domain features as input.

show abstract

Using Jitter and Shimmer in speaker verification

Cited by 58 publications

References 41 publications

Improving Automatic Detection of Obstructive Sleep Apnea Through Nonlinear Analysis of Sustained Speech

Improving Automatic Detection of Obstructive Sleep Apnea Through Nonlinear Analysis of Sustained Speech

Introducing Non-linear Analysis into Sustained Speech Characterization to Improve Sleep Apnea Detection

A hybrid model for neurological disordered voice classification using time and frequency domain features

Contact Info

Product

Resources

About