A multiple bandwidth objective speech intelligibility estimator based on articulation index band correlations and attention

Author(s):  
Stephen D. Voran
2021 ◽  
Vol 69 (2) ◽  
pp. 173-179
Author(s):  
Nilolina Samardzic ◽  
Brian C.J. Moore

Traditional methods for predicting the intelligibility of speech in the presence of noise inside a vehicle, such as the Articulation Index (AI), the Speech Intelligibility Index (SII), and the Speech Transmission Index (STI), are not accurate, probably because they do not take binaural listening into account; the signals reaching the two ears can differ markedly depending on the positions of the talker and listener. We propose a new method for predicting the intelligibility of speech in a vehicle, based on the ratio of the binaural loudness of the speech to the binaural loudness of the noise, each calculated using the method specified in ISO 532-2 (2017). The method was found to give accurate predictions of the speech reception threshold (SRT) measured under a variety of conditions and for different positions of the talker and listener in a car. The typical error in the predicted SRT was 1.3 dB, which is markedly smaller than estimated using the SII and STI (2.0 dB and 2.1 dB, respectively).


1990 ◽  
Vol 33 (4) ◽  
pp. 676-689 ◽  
Author(s):  
David A. Fabry ◽  
Dianne J. Van Tasell

The Articulation Index (AI) was used to evaluate an “adaptive frequency response” (AFR) hearing aid with amplification characteristics that automatically change to become more high-pass with increasing levels of background noise. Speech intelligibility ratings of connected discourse by normal-hearing subjects were predicted well by an empirically derived AI transfer function. That transfer function was used to predict aided speech intelligibility ratings by 12 hearing-impaired subjects wearing a master hearing aid with the Argosy Manhattan Circuit enabled (AFR-on) or disabled (AFR-off). For all subjects, the AI predicted no improvements in speech intelligibility for the AFR-on versus AFR-off condition, and no significant improvements in rated intelligibility were observed. The ability of the AI to predict aided speech intelligibility varied across subjects. However, ratings from every hearing-impaired subject were related monotonically to AI. Therefore, AI calculations may be used to predict relative—but not absolute—levels of speech intelligibility produced under different amplification conditions.


Author(s):  
Suzanne E. Lee ◽  
Gary S. Robinson ◽  
John G. Casali

The Federal Highway Administration (FHWA) currently has a hearing requirement for individuals seeking a commercial driver's license for interstate commerce. The existence of such a requirement implies that truck driving is a hearing-critical job, perhaps including speech communication tasks. Indeed, a task analysis performed in an earlier phase of this research confirmed that there are many hearing critical truck driving tasks, including several speech communication tasks. However, previous studies have shown that the truck cab environment can be quite noisy, perhaps noisy enough to impair speech communication. In this study, an analytical method known as the Articulation Index (AI) was used to predict the level of intelligibility in truck cabs for live and CB speech given certain measured truck-cab noise levels. Results showed that except in the quietest noise conditions, speech communication is severely degraded in the truck cab, a finding with potential safety implications. The AI method described herein can be used as a standardized analytical technique to evaluate speech intelligibility in various truck cab environments for design and comparison purposes.


Doklady BGUIR ◽  
2020 ◽  
pp. 67-73
Author(s):  
Y. N. Seitkulov ◽  
S. N. Boranbayev ◽  
H. V. Davydau ◽  
A. V. Patapovich

The article is devoted to assessing the intelligibility of the Kazakh speech when it's masked by combined signals, including «white» noise and speech-like signals. The phonetics features of the Kazakh language have been considered taking into account the law of syngarmonism and the spectrum differences of speech in the Kazakh language and speech in the Russian language. A technique for assessing the intelligibility of the Kazakh speech when it's masked by «white» noise and speech-like signals is proposed. The aim of the work is to analyze well-known methods for speech intelligibility assessing and applying these methods to assess speech intelligibility in the Kazakh language, taking into account masking by its combined signals. Due to the fact that the use of the articulation method of assessing intelligibility for the Kazakh speech requires a dependence of intelligibility on the articulation index for this particular language (the application for the Kazakh language has not been experimentally tested), the use of the formant approach to speech intelligibility assessing will be examined in more detail. The curried out experimental studies of the spectral density of speech in the Kazakh language made it possible to obtain it's approximate dependence on the frequency and take into account the phonetic features of the Kazakh speech when assessing the security of the speech information using the formant method.


1996 ◽  
Vol 5 (1) ◽  
pp. 23-32 ◽  
Author(s):  
Chris Halpin ◽  
Barbara Herrmann ◽  
Margaret Whearty

The family described in this article provides an unusual opportunity to relate findings from genetic, histological, electrophysiological, psychophysical, and rehabilitative investigation. Although the total number evaluated is large (49), the known, living affected population is smaller (14), and these are spread from age 20 to age 59. As a result, the findings described above are those of a large-scale case study. Clearly, more data will be available through longitudinal study of the individuals documented in the course of this investigation but, given the slow nature of the progression in this disease, such studies will be undertaken after an interval of several years. The general picture presented to the audiologist who must rehabilitate these cases is that of a progressive cochlear degeneration that affects only thresholds at first, and then rapidly diminishes speech intelligibility. The expected result is that, after normal language development, the patient may accept hearing aids well, encouraged by the support of the family. Performance and satisfaction with the hearing aids is good, until the onset of the speech intelligibility loss, at which time the patient will encounter serious difficulties and may reject hearing aids as unhelpful. As the histological and electrophysiological results indicate, however, the eighth nerve remains viable, especially in the younger affected members, and success with cochlear implantation may be expected. Audiologic counseling efforts are aided by the presence of role models and support from the other affected members of the family. Speech-language pathology services were not considered important by the members of this family since their speech production developed normally and has remained very good. Self-correction of speech was supported by hearing aids and cochlear implants (Case 5’s speech production was documented in Perkell, Lane, Svirsky, & Webster, 1992). These patients received genetic counseling and, due to the high penetrance of the disease, exhibited serious concerns regarding future generations and the hope of a cure.


Sign in / Sign up

Export Citation Format

Share Document