Speech Intelligibility and Speaker Recognition

During the time the European Economic Community (EC), through the Comite Europeen de Normalisation (CEN) was developing standards for Laser Processing Machines (by a mandate of the 89/392/EEC, “Machine Directive”), it became apparent to the Laser Products Group of the Association for Manufacturing Technology (AMT) that a similar standard would be useful for products made and used in the United States.AMT, among other activities, acts as the American National Standards Institute (ANSI) Secretariat for developing Machine Tool Standards, known as the ANSI B11 series. The B11.21 standard, like others in the B11 series, covers both manufacturers’ and users’ requirements for safety, as it spans the topics of Design, Construction, Care and Use. Since radiation and associated hazard information is covered primarily by existing laws and standards, such as 21 CFR and ANSI Z 136.1, the ANSI B11.21 acts as an information resource and as a comprehensive collection of these criteria.While it would be incorrect to term this standard a “spin-off” or copy of the EC efforts (e.g. ISO 11553 (EN 11553)), it has been an important element of B11.21’s creation that it contain recognition of the European work and harmonization with it. Two key elements of the standard make it especially useful for US manufacturers who wish to produce laser processing machines for both US delivery and the EC. The format of the B11.21, like other B11 standards contains a “normative” or requirement statement on the left side of each page, while the right hand column contains “informative” or explanatory information. In this standard, comparison to the EC requirements are listed to the right hand side for selected segments of the US standard. Additionally, throughout the B11.21 document, the concept of “Risk Assessment” and risk reduction, as a design element, is promoted, in accord with European standards which must comply with the Machine Directive.During the time the European Economic Community (EC), through the Comite Europeen de Normalisation (CEN) was developing standards for Laser Processing Machines (by a mandate of the 89/392/EEC, “Machine Directive”), it became apparent to the Laser Products Group of the Association for Manufacturing Technology (AMT) that a similar standard would be useful for products made and used in the United States.AMT, among other activities, acts as the American National Standards Institute (ANSI) Secretariat for developing Machine Tool Standards, known as the ANSI B11 series. The B11.21 standard, like others in the B11 series, covers both manufacturers’ and users’ requirements for safety, as it spans the topics of Design, Construction, Care and Use. Since radiation and associated hazard information is covered primarily by existing laws and standards, such as 21 CFR and ANSI Z 136.1, the ANSI B11.21 acts as an information resource and as a comprehensive collection of these criteria.While it would be incorrect to term ...

: The Thales Avionics Topowl(trade mark) Helmet Mounted Sight and Display System (HMSD) with and without the Communications Earplug (CEP) was tested for sound attenuation using American National Standards Institute (ANSI) standard S12.6-1984 and S12.6-1997 (R2002). Insertion loss measurements were made for the HMSD without the CEP in accordance with ANSI S12.42-1995 (R1999). The Thales Avionics Topowl(trade name) HMSD worn without the CEP does not meet the Navy/Marine Corps sound attenuation requirement but exceeds the requirement when worn with the CEP. When worn without the additional hearing protection afforded by the Communications Earplug or other passive earplugs, aircrew wearing the Thales Avionics Topowl(trade name) HMSD would be at risk due to higher noise exposure and reduced speech intelligibility, hence reduced operational capabilities. Expandable-forin or preformed earplugs could be employed with the Thales Avionics Topowl(trade name) HMSD to meet the Navy/Marine Corps hearing protection requirements. However, these types of earplugs will compromise speech intelligibility and, thus, negatively impact crew performance. The U.S. Army Aeromedical Research Laboratory recommends that Thales Avionics Topowl(trade name) HMSD not be used without the additional hearing protection and enhanced communications afforded by insert hearing protection and communication devices such as the CEP.

With the rapidly increasing number of electronic ballast manufacturers and ballast products entering the market recently, the compatibility of fluorescent lamps with electronic ballasts has become one of the major concerns among specifiers and users. In 1993, the American National Standards Institute (ANSI) published ANSI C82.11-1993, which describes recommendations for high-frequency operation of fluorescent lamp ballasts. To address compatibility issues for lamp starting, ANSI C82.11 limits the average value of the RMS glow current to a maximum of 25 mA and lamp preheat time to a minimum of 500 ms. ANSI's definitions of glow current and preheat time are made on an ideal lamp starting curve. In reality, some electronic ballasts produce lamp starting curves very different from ANSI's definition, creating difficulties in practical measurements of glow current and preheat time. This research work tested lamp starting characteristics of 17 different electronic ballasts on 2-F40T12 lamps. The results showed that the starting performance of electronic ballasts varied; some met ANSI's requirements, but some did not. The results also showed that using electrode voltage can better define preheat time and glow current, which can better characterize the starting performance of electronic ballasts and ensure reliable testing procedures.

Speech intelligibility and prosody production in children with cochlear implants

<div class="section abstract"> <div class="htmlview paragraph">This standard is to delineate the symbols used to identify controls, indicators, and tell-tales for automotive vehicles, trucks, off-the-road vehicles, construction equipment, industrial and recreational transportation and is for reference purposes only. The symbol application is to be found within the appropriate standards listed.</div> <div class="htmlview paragraph">Approved by AMERICAN NATIONAL STANDARDS INSTITUTE February 22, 1983</div> <div class="htmlview paragraph">An American National Standard implies a consensus of those substantially concerned with its scope and provisions. An American National Standard is intended as a guide to aid the manufacturer, the consumer, and the general public. The existence of an American National Standard does not in any respect preclude anyone, whether he has approved the standard or not, from manufacturing, marketing, purchasing, or using products, processes, or procedures not conforming to the standard. American National Standards are subject to periodic review and users are cautioned to obtain the latest editions.</div> <div class="htmlview paragraph">The American National Standards Institute does not develop standards and will in no circumstances give an interpretation of any American National Standard. Moreover, no person shall have the right or authority to issue an interpretation of an American National Standard in the name of the American National Standards Institute.</div> <div class="htmlview paragraph">CAUTION NOTICE: This American National Standard may be revised or withdrawn at any time. The procedures of the American National Standards Institute require that action be taken to reaffirm, revise, or withdraw this standard no later than five years from the date of approval. Purchasers of American National Standards may receive current information on all standards by calling or writing the American National Standards Institute.</div></div>

The purpose of this study was twofold: (a) to determine the extent to which 4-channel, slow-acting wide dynamic range amplitude compression (WDRC) can counteract the perceptual effects of reduced auditory dynamic range and (b) to examine the relation between objective measures of speech intelligibility and categorical ratings of speech quality for sentences processed with slow-acting WDRC. Multiband expansion was used to simulate the effects of elevated thresholds and loudness recruitment in normal hearing listeners. While some previous studies have shown that WDRC can improve both speech intelligibility and quality, others have found no benefit. The current experiment shows that moderate amounts of compression can provide a small but significant improvement in speech intelligibility, relative to linear amplification, for simulated-loss listeners with small dynamic ranges (i.e., flat, moderate hearing loss). This benefit was found for speech at conversational levels, both in quiet and in a background of babble. Simulated-loss listeners with large dynamic ranges (i.e., sloping, mild-to-moderate hearing loss) did not show any improvement. Comparison of speech intelligibility scores and subjective ratings of intelligibility showed that listeners with simulated hearing loss could accurately judge the overall intelligibility of speech. However, in all listeners, ratings of pleasantness decreased as the compression ratio increased. These findings suggest that subjective measures of speech quality should be used in conjunction with either objective or subjective measures of speech intelligibility to ensure that participant-selected hearing aid parameters optimize both comfort and intelligibility.

The American National Standards Institute (ANSI) standard for respiratory protection (ANSI Z88.2 1992) lists assigned protection factors (APFs) for various respirators. The committee that developed the APFs based its decisions on a review of available studies of respirator performance. If workplace studies were available, these formed the basis for the number assigned. If no such studies were available, then laboratory studies, design analogies, and other information were used to decide what value to assign. For half-mask air purifying respirators, four workplace protection factor studies were consulted to arrive at an APF. For loose-fitting facepiece powered air purifying respirators (PAPRs), five workplace studies and two laboratory studies were reviewed. For full-face air purifying, helmet/hooded PAPRs, and most supplied air respirators no workplace studies were available. The APF was based on laboratory studies or decided by analogy to other equipment. For the remaining respirators only single workplace protection factor studies were available, and these were used by the committee to assign an APF. The database available to the ANSI committee was limited. Most of the studies available for review were not published. The committee in a sense was required to perform peer review on the information to use the data. Studies completed after the ANSI committee finished its deliberations, when added to the data used, continue to support the APFs assigned by ANSI.

Competitive state-of-the-art automatic pathological speech intelligibility measures typically rely on regression training on a large number of features, require a large amount of healthy speech training data, or are applicable only to phonetically balanced scenarios where healthy and pathological speakers utter the same utterances. As a result, their performance in unseen data is unsatisfactory, and they cannot be used in low-resource languages or in phonetically unbalanced scenarios. To overcome these drawbacks, we propose a subspace-based intelligibility (SBI) measure. The SBI measure operates based on the hypothesis that dominant spectral patterns of pathological speech differ from intelligible speech (where the pathological and intelligible speech signals do not need to match in phonetic content), with the difference increasing as pathological speech intelligibility decreases. The SBI measure uses a minimal number of speech recordings to compute dominant spectral basis vectors spanning intelligible and pathological speech. The subspaces spanned by the intelligible and pathological spectral basis vectors are compared to each other through a subspace distance measure, which is directly used (i.e., without any training) as the pathological speech intelligibility estimate. Exploiting psychoacoustic evidence on the importance of spectral modulation cues to the perceived speech intelligibility and clinical evidence on the degradation of these cues in pathological speech, we show that the power of the proposed SBI measure lies in capturing the effect of spectral modulation degradation. To be able to additionally track possible degradations in the temporal structure of the pathological speech signal, we also propose two extensions of the SBI measure by incorporating short-time temporal information. Experimental results for different languages and speech pathologies show that the proposed intelligibility measures yield high and significant correlations with subjective intelligibility ratings, while not requiring any regression training or a large number of healthy speech recordings and being applicable to phonetically unbalanced scenarios.

Abstract: Significance: Ultraviolet (UV)-blocking contact lenses (CLs) may limit the exposure to UV radiation and prevent UV-associated adverse effects. However, the effectiveness of daily disposable CLs (DDCLs) and monthly disposable CLs (MDCLs) in blocking UV radiation and how well they conform to the American National Standard Institute (ANSI) Z80.20 standard are not fully understood. Aim: This study aimed to determine the UV-blocking effectiveness of DDCLs and MDCLs available in Jordan and examine their compliance with the criteria specified by the ANSI. Approach: Visible and UV light transmittances of the CLs (DDCLs: 1-DAY ACUVUE® MOISTTM, Bausch + Lomb Biotrue®ONEday, ACUVUE® OASYSTM; MDCLs: Avaira VitalityTM, CooperVision® Biomedics® 55 sphere, Clear 58TM) were evaluated using a spectrophotometer. The data were analyzed using a one-way analysis of variance ANOVA followed by Tukey’s pairwise comparison test. Results: One-way ANOVA showed a significant difference between UV transmission from three DDCLs of different brands in the UVA, UVB, and UVC regions (P < 0.001). In the case of MDCLs, a significant difference was also observed in the UV transmission characteristics. Most importantly, all three DDCLs met the class 2 criteria of ANSI for UV-blocking CLs. Among the MDCLs, however, only one met these criteria. Conclusion: These findings suggest that the Acuvue OASYS is the best daily contact lens for blocking UV radiation. Among MDCLs, Avaira and Biomedics Sphere 55 are recommended for UV protection. All DDCLs met ANSI class 2 criteria for UV blockage.

It is important that hearing assistance devices/systems (HADS) be evaluated electroacoustically to verify performance relative to published results and to compare performance across similar devices. The guidelines for verification prepared by professional organizations address the comparison of the HADS to personal amplification systems. The current document by the American Academy of Audiology includes guidelines for wireless systems integrated with hearing aids, classroom audio distribution systems, and induction loop systems. A new standard by the American National Standards Institute (ANSI) is now available, which provides specifications for systematic electroacoustic measurements that can be compared across manufacturers. Although many of the measurements are similar to those in the ANSI Standard for the Electroacoustic Evaluation of Hearing Aids, there are recommendations regarding position of wireless microphones and receivers that are specific to procedures for the evaluation of HADS. The ANSI standard for Electroacoustic Evaluation of HADS will be reviewed with particular application to systems with wireless transmitters and receivers.

Standardization of the virtual device metafile and the virtual device interface

Oxygen permeability (Dk) was determined for 37 available rigid contact lens materials in a masked fashion. The results were compared with those of an earlier study that included different lots of 14 test materials assessed in the current study. Six lenses of different thicknesses in each test and reference material were obtained. Test materials were arranged in sets of six to eight materials per set. Each set of materials, with inclusion of at least two reference materials for the purpose of simultaneous calibration, was measured to obtain preliminary amperages. Four preliminary measures were performed per thickness, resulting in 24 per material, in a schedule designed to spread the potential effects of machine drift and other factors. The mean preliminary amperages were used to derive corrected Dk values according to American National Standards Institute (ANSI) Z80.20-1998, and the values were linearly calibrated using the measured and established Dk values of the reference materials. The resistance (t/Dk) vs. thickness (t) plots for the 37 test and seven reference materials were approximated linearly. In 54 of 57 linear regressions, the coefficients of determination (R2) were >0.96, and in 48 instances were >0.98. Fourteen Dk values from the current study and an earlier study were linearly correlated (R2 = 0.9846), with a slope close to unity (+1.056) and intercept close to zero (-0.292). Ten of the current values fell within 10% of their corresponding earlier values. Only three current Dk values fell outside of the ANSI Z80.20-1998 tolerance for Dk (+/-20%). Two of these Dk values met the product tolerance when an obvious outlying point was graphically identified and omitted from the linear resistance (t/Dk) vs. thickness (t) regression. Omission of a single outlying point from a linear resistance vs. thickness regression can help provide a more valid Dk value. The ANSI Z80.20-1998 tolerance of +/-20% on Dk and the measurement reproducibility of +/-10% were achieved for the overwhelming majority of rigid contact lens materials up to at least 160 Dk units. The corrected, calibrated Dk values for the 37 test materials, in ANSI units, ranged from 13.8 to 175.1, having an overall mean of 43.2, median of 31.9, and standard error of 6.57 (N = 37).

In this paper, we present a novel system for joint speaker identification and speech separation. For speaker identification a single-channel speaker identification algorithm is proposed which provides an estimate of signal-to-signal ratio (SSR) as a by-product. For speech separation, we propose a sinusoidal model-based algorithm. The speech separation algorithm consists of a double-talk/single-talk detector followed by a minimum mean square error estimator of sinusoidal parameters for finding optimal codevectors from pre-trained speaker codebooks. In evaluating the proposed system, we start from a situation where we have prior information of codebook indices, speaker identities and SSR-level, and then, by relaxing these assumptions one by one, we demonstrate the efficiency of the proposed fully blind system. In contrast to previous studies that mostly focus on automatic speech recognition (ASR) accuracy, here, we report the objective and subjective results as well. The results show that the proposed system performs as well as the best of the state-of-the-art in terms of perceived quality while its performance in terms of speaker identification and automatic speech recognition results are generally lower. It outperforms the state-of-the-art in terms of intelligibility showing that the ASR results are not conclusive. The proposed method achieves on average, 52.3% ASR accuracy, 41.2 points in MUSHRA and 85.9% in speech intelligibility.

American national standards for evaluations of educational programs have been developed by the joint committee on Standards for Educational Evaluation. These standards have been approved by the American National Standards Institute (ANSI). In the article, the standard-setting process developed by the joint committee and approved by ANSI is described. The process involves the following steps: (a) initiation of projects, (b) development of the first draft, (c) national and international reviews, (d) field tests, (e) national public hearings, (f) finalization of standards, (g) consideration of views and objections, (h) appeals, and (i) validation. The process is public, participatory, open, and consensual.

The Association for the Advancement of Medical Instrumentation develops voluntary standards for medical devices so that manufacturers might provide information on their product and basic safety and performance criteria that should be considered in qualifying the instrument for clinical use. American national standards are generated through a consensus process by committees consisting of experts in research, development, and design from user, industry, and government communities. Draft standards are made available for public review and may become American national standards after review by the American National Standards Institute. The first American national standard for electronic and automated sphygmomanometers was published in monograph form in 1987. The objective of the revised 1992 standard for electronic and automated sphygmomanometers is to provide updated labeling, safety, and performance requirements that help ensure that consumers and health care professionals are supplied with safe, accurate devices for the indirect measurement of blood pressure, including ambulatory blood pressure recorders. This standard permits validation of the automatic or electronic device by comparison with either direct, intra-arterial blood pressure measurements or the noninvasive cuff/stethoscope technique, based on Korotkoff sounds identified by individuals trained in auscultation. This summary report of the 1992 American national standard for automatic sphygmomanometers provides recommendations for the methods of comparison, statistical analysis of the data, presentation of the results, and criteria for acceptability. Users, researchers, and instrument designers should refer to the American national standard monograph for detailed requirements.