Recognition of Speaker Age from Selected Acoustic Features as Perceived by Normal Young and Older Listeners

Jacques, Richard; Rastatter, Michael P.

doi:10.1159/000266055

Cited by 13 publications

(5 citation statements)

References 5 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, some re search aimed at a practical application, e.g. voice synthesis [19] and speaker identifica tion [20,21]. As a model of investigation, most researchers have preferred using the cross-sectional method.…”

mentioning

confidence: 99%

Changes in Spectral Measures and Voice-Onset Time with Age: A Cross-Sectional and a Longitudinal Study

Decoster

Debruyne²

1997

Folia Phoniatr Logop

View full text Add to dashboard Cite

In this study, we searched for changes in spectral features (during the sustained vowels [a] and [i]) and the voice onset time (VOT, of [pa] and [ka]) ofthe ageing voice. A longitudinal study (on 20 participants) and a cross-sectional study (on 265 participants) were conducted. The spectral parameters under consideration were: the difference in amplitude between the first and the second harmonic, the energy difference between the frequency band below 1 kHz and 2–4 kHz, and the energy difference between < 1 kHz and 4–5 kHz. The VOT was also measured. Comparing five age bands of men and women, the cross-sectional study revealed a stronger H₂ relative to H₁ for women above 60 years pronouncing both vowels [a] and [i]. A relatively stronger spectral level was found between 4 and 5 kHz in elderly men and women (60+) for [i] compared to young men and women (20–29 years). Significant differences in the longitudinal study were not identical to those ofthe cross-sectional study. After a time interval of 30 years, 20 men produced a relatively weaker 2- to 4-kHz part ofthe spectrum and the VOT became much longer. It was impossible to attribute the changes purely to the process of ageing. Situations and emotions also play an important role and contribute to the different findings of the two groups of participants under consideration.

show abstract

mentioning

confidence: 99%

Changes in Spectral Measures and Voice-Onset Time with Age: A Cross-Sectional and a Longitudinal Study

Decoster

Debruyne²

1997

Folia Phoniatr Logop

View full text Add to dashboard Cite

show abstract

“…Research has revealed that age-related changes in the supralaryngeal structures provide acoustic cues to adult speaker age [10,13,74]. However, there are relatively few studies of the age-related changes in the vocal tract resonance features.…”

Section: Resonance Measuresmentioning

confidence: 99%

Acoustic Analysis of Adult Speaker Age

Schötz

Lecture Notes in Computer Science

View full text Add to dashboard Cite

“…There are acoustic correlations with age in every phonetic dimension, and their relative importance in age perception has yet to be fully explored (Hollien 1987 [1], Jacques & Rastatter 1990 [2], Linville 1987 [3], Ptacek & Sander 1996 [4], Schots 2003 [5])…”

Section: Introductionmentioning

confidence: 99%

Age and Gender Classification for a Home-Robot Service

Kim

Bae

Yoon

2007

RO-MAN 2007 - The 16th IEEE International Symposium on Robot and Human Interactive Communication

View full text Add to dashboard Cite

This paper describes a method to recognize the age and gender of a user on the basis of human speech. Using voice source characteristics of the Mel Frequency Cepstral coefficients (MFCCs), a Gaussian Mixture Model (GMM) technique is applied in an effort to discover the age, gender, and other information as regards a user. On the basis of this information, service applications for robots can satisfy users by offering services adaptive to the special needs of specific user groups that may include adults and children as well as females and males. The major aim of this paper is to discover the voice source parameters of age and gender and to classify these two characteristics simultaneously. ETRI-VoiceDB2006 was employed to evaluate the proposed method.

show abstract

Recognition of Speaker Age from Selected Acoustic Features as Perceived by Normal Young and Older Listeners

Cited by 13 publications

References 5 publications

Changes in Spectral Measures and Voice-Onset Time with Age: A Cross-Sectional and a Longitudinal Study

Changes in Spectral Measures and Voice-Onset Time with Age: A Cross-Sectional and a Longitudinal Study

Acoustic Analysis of Adult Speaker Age

Age and Gender Classification for a Home-Robot Service

Contact Info

Product

Resources

About