scholarly journals Automated classification of vowel category and speaker type in the high-frequency spectrum

2016 ◽  
Vol 6 (1) ◽  
Author(s):  
Jeremy J. Donai ◽  
Saeid Motiian ◽  
Gianfranco Doretto

The high-frequency region of vowel signals (above the third formant or F3) has received little research attention. Recent evidence, however, has documented the perceptual utility of high-frequency information in the speech signal above the traditional frequency bandwidth known to contain important cues for speech and speaker recognition. The purpose of this study was to determine if high-pass filtered vowels could be separated by vowel category and speaker type in a supervised learning framework. Mel frequency cepstral coefficients (MFCCs) were extracted from productions of six vowel categories produced by two male, two female, and two child speakers. Results revealed that the filtered vowels were well separated by vowel category and speaker type using MFCCs from the high-frequency spectrum. This demonstrates the presence of useful information for automated classification from the high-frequency region and is the first study to report findings of this nature in a supervised learning framework.

2020 ◽  
Vol 5 (5) ◽  
pp. 1347-1355
Author(s):  
Helen A. Boyd-Pratt ◽  
Jeremy J. Donai

Purpose High-frequency speech energy (above approximately 4–5 kHz) is garnering substantial research attention. This review surveys recent evidence surrounding the presence and use of perceptual information in the high-frequency region. Additionally, clinical and research applications relevant to speech, language, and hearing professionals are discussed. Method Five databases were used during the search (Medline, CINAHL, WorldCat, ERIC, and Google Scholar). Criteria for study inclusion included (a) peer review, (b) utilization of high-frequency energy (above approximately 4 kHz) during the experimental tasks, and (c) were published from 2014 to present. Fifty-seven articles were included for review, and after further inspection, 13 met the inclusion criteria and were retained. Results Thirteen peer-reviewed studies provided evidence to support the supposition that important and useable acoustic cues exist in the high-frequency portion of the speech spectrum. Conclusions Considering the evidence discussed in this document, it is apparent that the high-frequency region contains additional perceptual cues than currently assumed. Specifically, acoustic cues regarding segmental information (vowel and consonant identification), individual speaker identity, and speaker sex are available for use by human listeners and automated machine recognition systems. Additionally, the high-frequency speech region may reduce listening effort and improve speech recognition in noisy listening conditions, particularly when the speech and noise are spatially separated. Therefore, clinicians and researchers should be aware of this information, which can inform clinical practice when fitting amplification devices for various clinical populations and experimental research for speech and hearing scientists.


2007 ◽  
Vol 280-283 ◽  
pp. 919-924
Author(s):  
M.S. Jogad ◽  
V.K. Shrikhande ◽  
A.H. Dyama ◽  
L.A. Udachan ◽  
Govind P. Kothiyal

AC and DC conductivities have been measured by using the real (e¢) and imaginary (e¢¢) parts of the dielectric constant data of glass and glass-ceramics (GC) at different temperatures in the rage 297-642K and in the frequency range 100 Hz to 10 MHz. Using Anderson –Stuart model, we have calculated the activation energy, which is observed to be lower than that of the DC conductivity. The analysis for glass/glass-ceramics indicates that the conductivity variation with frequency exhibits an initial linear region followed by nonlinear region with a maximum in the high-frequency region. The observed frequency dependence of ionic conductivity has been analyzed within the extended Anderson–Stuart model considering both the electrostatic and elastic strain terms. In glass/glassceramic the calculations based on the Anderson-Stuart model agree with the experimental observations in the low frequency region but at higher frequencies there is departure from measured data.


2005 ◽  
Vol 20 (2) ◽  
pp. 216-220
Author(s):  
Nirupama Kapoor ◽  
Subhasis Haldar ◽  
Mridula Gupta ◽  
R S Gupta

PEDIATRICS ◽  
1979 ◽  
Vol 63 (1) ◽  
pp. 100-106 ◽  
Author(s):  
Fred H. Bess ◽  
Barbara Finlayson Peek ◽  
Judy J. Chapman

The purpose of this study was to conduct an acoustic analysis of incubator noise under two conditions: when the incubator was associated with different types of life-support equipment; and when impulse noise was created by striking the side of the incubator or by opening and closing the doors of the storage unit. It was found that the life-support equipment increased the overall noise levels of incubators by as much as 15 to 20 dB. Much of this increased energy was in the high frequency region. Impulse signals created by striking the side of the incubator ranged from 130 to 140 dB. A representative impulse for opening the incubator was 92.8 dB, whereas closing the door produced a peak amplitude of 114 dB.


1916 ◽  
Vol 182 (3) ◽  
pp. 403 ◽  
Author(s):  
Albert W. Hull ◽  
Marion Rice

2012 ◽  
Vol 86 (4) ◽  
Author(s):  
Zhen Zhai ◽  
Dian Peng ◽  
Xi Zhao ◽  
Fuming Guo ◽  
Yujun Yang ◽  
...  

Clay Minerals ◽  
1999 ◽  
Vol 34 (4) ◽  
pp. 565-577 ◽  
Author(s):  
M. D. Ruiz Cruz ◽  
F. I. Franco Duro

AbstractThe intercalation complex of kaolinite and potassium acetate (KAc) was studied by HTXRD, IR spectroscopy and DTA-TG. The HTXRD patterns indicate that the 14.06 Å basal spacing of the complex contracts to 11.77 Å and 9.35 Å after heating at 60°C. The DTA-TG data indicate that water is present in these new complexes, the decomposition of which occurs between 290°C and 400°C. Modifications observed in the high-frequency region of the spectra obtained after heating suggest that K ions occupy the ditrigonal holes in the OH surface of the kaolinite layers, whereas water is probably located between the KAc layer and the OH surface of the kaolinite. This structural arrangement would favour the H-bonding between inner-surface OH groups and water and justifies the presence of new bands at lower frequencies. Electrostatic interactions between the keyed K ions and O of the inner OH groups would justify the modifications of the 3619 cm-1 OH-stretching band.


Sign in / Sign up

Export Citation Format

Share Document