Normalized noise energy as an acoustic measure to evaluate pathologic voice

Abstract

In order to evaluate noise components included in pathologic voice signals, a novel acoustic measure, normalized noise energy (NNE), is proposed and its effectiveness for the detection of laryngeal pathologies is investigated with 250 vowel samples spoken by 64 control (normal) subjects and 186 patients with various laryngeal diseases. The NNE is automatically computed from the voice signals using an adaptive comb filtering method performed in the frequency domain. Experiments with the voice samples show that the NNE is especially effective for detecting glottic cancer, recurrent nerve paralysis, and vocal cord nodules. Specifically, when glottic cancer is represented in terms of the T classification adopted by the UICC (Union Internationale Contre le Cancer), glottic T2-T4 cancer can be perfectly discriminated from normal samples, but 22.6% of patients with glottic T1 cancer are incorrectly classified as normal, with an error rate of 9.4% for normal subjects.

Objective and Subjective Evaluation of Larynx in Smokers and Nonsmokers: A Comparative Study

“…The NNE assesses the relative level of vocal noise to that of harmonics [19]. In present study, raised values of NNE were obtained in smokers as compared to nonsmokers.…”

“…So, increased glottal gap size in smokers as compared to nonsmokers may account for breathy voice resulting in raised NNE. However, despite few published studies used NNE as an outcome measure to distinguish pathological from normal voices, but its clinical usefulness is still unclear [19,21].…”

Dimensões perceptivas das alterações de qualidade vocal e suas correlações aos planos da acústica e da fisiologia

“…Como resultado de tal desenvolvimento, muitas informações sobre a função vocal foram obtidas, com destaque para as investigações por meio de procedimentos acústicos e de técnicas de imagens. Um grande número de estudos investigou a atividade glótica como o principal correlato da qualidade vocal e procurou por índices acústicos em estudos de população, com destaque para o fato de que, em sua maioria, procuraram estabelecer uma relação linear entre determinada qualidade sonora e uma medida ou índice acústico (Kojima et al, 1980;Kitajima, 1981;Yumoto et al, 1982;Hiraoka et al, 1984;Klingholz, Martin, 1985;Kasuya et al, 1986;Hillenbrand, 1987;Cox et al, 1989;Sasaki et al, 1991;Qi, 1992;Deliyski, 1993;Awan, Frenkel, 1994;Kent et al, 1999;Smits et al, 2005;Uloza et al, 2005).…”

Computer Aided Recognition of Vocal Folds Disorders by Means of RASTA-PLP

“…A study like (Kasuya, Ogawa, Mashima & Ebihara, 1986), the authors proposed the NNE parameter for acoustic discrimination of voice disorders obtained an accuracy of 78.6% for NNE and 74.1% for HNR. In (Godino-Llorente, Ruiz, Lechon & Gomez-Vilda, 2008), the authors evaluate the capabilities of the GNE ratio for the screening of voice disorders, reporting an accuracy of 95%.…”

“…It includes signal-to-noise ratio (SNR) (Klingholz, 1997), harmonics-to-noise ratio (HNR) (Qi & Hillman, 1997) and (Kasuya, Ogawa, Mashima & Ebihara, 1986), normalized noise energy (NNE) (Michaelis, Gramss & Strube, 1997), voice turbulence index (VTI) (Qi & Hillman, 1997), soft phonation index (SPI) (Deliyski, 1993) and glottal-to-noise excitation ratio (GNE) (Michaelis, Gramss & Strube, 1997) and (Godino-Llorente, Ruiz, Lechon & Gomez-Vilda, 2008).…”