Intelligibility Test Research Articles

The real-time application and effectiveness assessment of an intelligent physical fitness testing system in physical training

An intelligent physical fitness testing system leverages advanced technologies to monitor and evaluate individuals’ fitness levels accurately. It integrates real-time data acquisition, and analysis, to support personalized physical training and health management. This study aims to evaluate the practical application and effectiveness of an intelligent system for real-time physical fitness testing in the context of physical training. Our suggested model employs portable sensing devices and we proposed a novel Northern Goshawk optimization-driven Gate Customized Long Short-Term Memory (NG-GC-LSTM) for enhancing accuracy in evaluating the individuals’ physical fitness levels. Data acquisition involves gathering bio-sensing data from 25 individuals during diverse physical training activities. The Min-Max Scaling algorithm is utilized to pre-process the obtained sensor data. We employed a Short-Time Fourier Transform (STFT) for extracting crucial features from the processed data. In our proposed framework, the NG optimization algorithm iteratively fine-tunes the GC-LSTM architecture for the accurate evaluation of an established intelligent physical fitness testing system. The recommended model is executed in Python software. During the result analysis phase, we assess the efficacy of our model’s performance across a variety of parameters. Additionally, we conduct comparative analyses with existing methodologies. The obtained outcomes demonstrate the efficacy and superiority of the suggested framework.

SYSAI for System Health Management - a Statistical Framework for the Analysis of Diagnosis Systems

On-board failure diagnosis and health management systems (HMS) are crucial for the operation of complex autonomous aerospace systems. False alarms (false positives, FPs) or false negatives (FNs) can lead to lower system performance or even loss of mission or the autonomous vehicle. Therefore, a careful verification and validation (V&V) is important. Due to the high dimensionality of the system’s state space, however, exhaustive testing of the HMS is usually not possible. In this paper, we present how our SYSAI (System Analysis for Systems with AI components) framework can support intelligent analysis and testing of HMS on the system level. SYSAI’s capabilities to efficiently explore high-dimensional state and parameter spaces and to identify diagnosability regions and their boundaries, makes a comprehensive analysis of the diagnosis system possible and can provide feedback to the designer. We will illustrate our approach using the ADAPT (Advanced Diagnostics and Prognostics Testbed) redundant power storage and distribution system.

Development and cultural adaptation of the Saudi pediatric speech intelligibility test.

To report the development and administration of the Saudi pediatric speech intelligibility (SPSI) test. This study was carried out at King Abdullah Ear Specialist Center, King Saud University, Riyadh, Saudi Arabia, between 2021 and 2023. A pilot study was carried out in 5 regions of Saudi Arabia including 100 normal hearing children aged 7-11 years old, with 20 children from each region. The final test materials were voice-recorded by a native Saudi radio announcer, and a software-based application for administering the SPSI was developed. During the pilot study, minor adjustments were carried out to the test for more clarity. The developed SPSI software is an android-based application that includes features like automatic result calculation, data saving, and individual user accounts for examiners to review results. The SPSI test comprises 4-word cards and 2 sentence cards, each with 5 pictures, and operates in 3 modes: quiet, background noise, and competing sentences. The SPSI test has been developed in an android-based software using the Saudi local dialects. It can facilitate comprehensive and accurate assessment of speech intelligibility, particularly in children with hearing impairments.

Maxillectomy patients' speech and performance of contemporary speaker-independent automatic speech recognition platforms in Japanese.

Automatic speech recognition (ASR) can potentially help older adults and people with disabilities reduce their dependence on others and increase their participation in society. However, maxillectomy patients with reduced speech intelligibility may encounter some problems using such technologies. To investigate the accuracy of three commonly used ASR platforms when used by Japanese maxillectomy patients with and without their obturator placed. Speech samples were obtained from 29 maxillectomy patients with and without their obturator and 17 healthy volunteers. The samples were input into three speaker-independent speech recognition platforms and the transcribed text was compared with the original text to calculate the syllable error rate (SER). All participants also completed a conventional speech intelligibility test to grade their speech using Taguchi's method. A comprehensive articulation assessment of patients without their obturator was also performed. Significant differences in SER were observed between healthy and maxillectomy groups. Maxillectomy patients with an obturator showed a significant negative correlation between speech intelligibility scores and SER. However, for those without an obturator, no significant correlations were observed. Furthermore, for maxillectomy patients without an obturator, significant differences were found between syllables grouped by vowels. Syllables containing /i/, /u/ and /e/ exhibited higher error rates compared to those containing /a/ and /o/. Additionally, significant differences were observed when syllables were grouped by consonant place of articulation and manner of articulation. The three platforms performed well for healthy volunteers and maxillectomy patients with their obturator, but the SER for maxillectomy patients without their obturator was high, rendering the platforms unusable. System improvement is needed to increase accuracy for maxillectomy patients.

How to Efficiently Measure the Intelligibility of People With Parkinson's Disease.

The purpose of this study was to determine the most efficient approaches to measuring the intelligibility of people with Parkinson's disease (PD) when considering the estimation method, listener experience, number of listeners, number of sentences, and the ways these factors may interact. Speech-language pathologists (SLPs) and inexperienced listeners estimated the intelligibility of people with and without PD using orthographic transcription or a visual analog scale (VAS). Intelligibility estimates were based on 11 Speech Intelligibility Test sentences. We simulated all combinations of listeners and sentences to compare intelligibility estimates based on fewer listeners and sentences to a speaker-specific benchmark estimate based on the mean intelligibility across all sentences and listeners. Intelligibility estimates were closer to the benchmark (i.e., more accurate) when more listeners and sentences were included in the estimation process for transcription- and VAS-based estimates and for SLPs and inexperienced listeners. Differences between the benchmark and subset-based intelligibility estimates were, in some cases, smaller than the minimally detectable change in intelligibility for people with PD. The intelligibility of people with PD can be measured more efficiently by reducing the number of listeners and/or sentences, up to a point, while maintaining the ability to detect change in this outcome. Clinicians and researchers may prioritize either fewer listeners or fewer sentences, depending on the specific constraints of their work setting. However, consideration must be given to listener experience and estimation method, as the effect of reducing the number of listeners and sentences varied with these factors.

Toward Intelligent Head Impulse Test: A Goggle-Free Approach Using a Monocular Infrared Camera.

To assess vestibular function, video head impulse test (vHIT) is taken as the gold standard by evaluating the vestibulo-ocular reflex (VOR). However, vHIT requires the patient to wear a specialized head-mounted goggle equipment that needs to be calibrated before each use. For this, we proposed an intelligent head impulse test (iHIT) setting with a monocular infrared camera instead of the head-mounted goggle and contributed correspondingly a video classification approach with deep learning to vestibular function determination. Within the iHIT framework, a monocular infrared camera was set in front of the patient to capture test videos, based on which a dataset DiHIT of HIT video clips was set up. We then proposed a two-stage multi-modal video classification network, trained on the dataset DiHIT, that took as input the eye motion and head motion data extracted from the facial keypoints via HIT clips and outputted the identification of the semicircular canal (SCC) being tested (SCC identification) and determination of VOR abnormality (SCC qualitation). Experiments on this dataset DiHIT showed that it achieved the accuracy of 100% in prediction of SCC identification. Furthermore, it attained predictive accuracies of 84.1% in horizontal and 79.0% in vertical SCC qualitation. Compared with existing video-based HIT, iHIT eliminates goggles, does not require equipment calibration, and achieves complete automation. Furthermore, iHIT will bring more benefits to users due to its low cost and ease of operation. Codes and use case pipeline are available at: https://github.com/dec1st2023/iHIT. 3 Laryngoscope, 2024.

Clinical Outcomes for Adult Single-Sided Deafness Cochlear Implantees Exceeding the 5% Candidacy Criterion.

While single-sided deafness cochlear implants (SSD-CIs) have now received regulatory approval in the United States, candidate-ear candidacy criteria (no better than 5% word-recognition score) are stricter than for traditional CI candidates (50 to 60% speech recognition, best-aided condition). SSD implantation in our center began before regulatory approval, using a criterion derived from traditional candidacy: 50% consonant-nucleus-consonant (CNC) word-identification score in the candidate ear. A retrospective analysis investigated whether SSD patients exceeding the 5% CNC criterion nevertheless benefitted from a CI as assessed by spatial-hearing tests (speech understanding in noise [SIN] and localization) and by a patient-reported outcome measure quality-of-life instrument validated for patients with CIs. A retrospective chart review assessed the clinical experience of a single CI center. Subjects consisted of 27 adult CI recipients with SSD (N = 21) or asymmetric hearing loss (AHL; N = 6) implanted since September 2019 with at least 3 months of postoperative follow-up. Patients with revision surgery or simultaneous labyrinthectomy and CI surgery were excluded from the sample. Subjects were divided into 2 groups based on preoperative CNC scores measured under best-aided conditions with a behind-the-ear hearing aid in the sound field at 0.9 m from a front loudspeaker, and the better ear masked using an insert earphone with 45 dB HL speech-weighted noise. The "MEETS" group had preoperative CNC word scores <5%; the "EXCEEDS" group had scores >5%. The clinical protocol also included intelligibility tests using AzBio sentences in the same test conditions as CNC; binaural spatial testing (broadband-noise sound localization, and matrix-sentence speech-reception thresholds in spatially separated noise) using a custom-built 7-speaker array; and the CI Quality of Life (CIQOL) instrument. To evaluate CI benefit, preoperative unaided performance was compared with postoperative binaural (acoustic ear + CI ear) performance at a clinic visit closest to 6 months postsurgery. Of 27 SSD-CI recipients, 11 subjects exceeded the 5% preoperative CNC candidacy criterion. Both the MEETS and EXCEEDS groups improved significantly on all 5 primary study outcome measures (CI-alone CNC and AzBio, binaural SIN and sound localization, and CIQOL). The only statistically significant differences observed between the MEETS and EXCEEDS groups were that preoperative CNC and AzBio scores were significantly higher for the EXCEEDS group, as expected given that the groups were defined based on preoperative speech-perception scores in quiet. There were no statistically significant differences between the MEETS and EXCEEDS groups in postoperative scores in any test or in the magnitude of the improvement from preoperative to postoperative assessment. SSD- and AHL-CI recipients exceeding the 5% CNC preoperative candidacy criterion significantly improved in CI-alone speech perception, spatial hearing, and subjectively reported CIQOL outcomes and the observed benefits were indistinguishable from SSD- and AHL-CI recipients who met the 5% criterion. A less-restrictive SSD-CI and AHL-CI candidacy criterion should be considered, and larger-scale clinical trials to evaluate CI efficacy using a less-stringent candidate-ear criterion are warranted.

Construction of virtual test scenarios for intelligent car-pedestrian interaction

Aiming at the needs of intelligent car and pedestrian interaction testing under urban conditions, this paper proposes a scenario generation method that comprehensively considers the frequency of scenarios in the real world and the degree of challenge to human-vehicle interaction performance. First, according to the key features of intelligent car and pedestrian interaction, the original scene data of pedestrians crossing the road is extracted from the natural driving dataset; then, according to the needs of accelerated testing, a key scenario extraction method based on importance sampling theory is designed to extract and construct important scenarios for intelligent car-pedestrian interaction testing from the original scenes; finally, by comparing the data distribution of important scenarios with original scenarios, it is shown that this method can effectively screen out scenarios that may challenge safety performance during driving, thereby realizing accelerated testing, while taking into account the statistical characteristics of the test scenarios.

Impact of contextual and lip-sync-related visual cues on speech intelligibility through immersive audio-visual scene recordings in a reverberant conference room

Recent hearing research has benefitted from the latest Virtual Reality systems that allowed the reproduction of immersive Audio-Visual scenarios to achieve more ecological listening tests. Indeed, efforts have been spent to identify the aspects that convey actual ecological validity, particularly investigating the effects of visual cues and self-motion on Speech Intelligibility through tests mainly based on simulated scenes. However, work must still be addressed when sceneries developed through real recordings inside reverberant environments are concerned. This study used 3rd-order ambisonics recordings and stereoscopic 360° videos inside a reverberant conference hall to create three virtual audio-visual scenes where speech intelligibility tests were performed, introducing informational noise from different angles. A 16-speaker spherical array synced with a headmounted display was used to administer the immersive tests to 50 normal-hearing subjects. Firstly, tests only composed of the auditory scenes were compared, based on the achieved scores, with tests also providing contextual and positional source-related visual cues, both with and without self-motion, for a total of four different test configurations. Then, to complete the investigation of the visual cues' impact on speech intelligibility, ten normal-hearing subjects were recruited to performaudio-visual tests incorporating lip-sync-related visual cues for the target speech.

Effect of Modulation Domain Coupled KalmanSpectral Filter on Speech Enhancement over Wireless Voiced Communication System

Noise suppression in speech signal has received great attention in signal processing research community. However, existing methods of noise suppression such as the time-domain Kalman filter suffers from the psychoacoustic and physiological characteristic feature while the spectral subtraction technique performed in the modulation domain is associated with remnant noise in the enhanced speech signal. Therefore, in this paper, a Modulation-Domain coupled Kalman-Spectral Filtering (MD-KSF) in a single channel system is proposed to address the aforementioned shortcomings in the two existing techniques. The simulation of the proposed coupled MD-KSF was performed in MATLAB software environment. The evaluation of the proposed coupled MD-KSF technique in terms of Spectral waveform, Mean Square Error (MSE) and Log Spectral Distance (LSD) was performed. Furthermore, Perceptual Evaluation of Speech Quality (PESQ) and Short-Time Objective Intelligibility (STOI) tests were employed to validate the quality and intelligibility of the proposed coupled MD- KSF using the NOIZEUS corpus data set. The proposed technique shows significant noise suppression over the existing techniques.

Development of Intelligent Testing and Evaluation System for Fracturing Pump

Abstract Fracturing truck is the key technical equipment for oil and gas production stimulation. Fracturing pump of fracturing truck is subjected to high pressure load for a long time during use. Due to the influence of many factors such as transportation and equipment aging, the performance of fracturing pump in field use is reduced and the output power is insufficient. In order to realize the on-site inspection of fracturing pump, a set of intelligent inspection and evaluation system of fracturing pump is developed. Through the establishment of the hardware test platform and the development of the software system, the intelligent inspection and evaluation system of fracturing pump with the features of one-click automatic detection, automatic analysis of performance indicators, intelligent prediction and maintenance of health status is realized. The system can support the static pressure test, water power test and overpressure protection test of 140MPa ultra-high pressure fracturing pump. Experimental tests show that the test accuracy of the equipment can effectively meet the detection and evaluation needs of the field fracturing truck, ensure the normal function through static pressure and water power detection, and determine the safety of the equipment through overpressure protection detection, which greatly improves the effect and efficiency of fracturing operations.

Tipping the Scales: Indiscriminate Use of Interval Scales to Rate Diverse Dysarthric Features.

Error related to incorrect use of rating scales is problematic in the assessment and treatment of dysarthria. The main purpose of this project was to determine scale fit for cardinal speech features of hypokinetic dysarthria. A secondary aim was to determine rater reliability for the two different scales explored. Forty-three speakers with Parkinson's disease (PD) and 25 neurologically healthy control talkers were recorded reading sentences from the Speech Intelligibility Test. Twenty-two healthy female listeners used both an equal appearing interval (EAI) scale and a direct magnitude estimation (DME) scale to rate five perceptual speech features (i.e., overall speech severity, articulatory imprecision, reduced loudness, short rushes of speech, and monotony) from these recordings. Regression analyses were used to determine the linearity of the relationship between the means of the EAI and DME ratings. Inter- and intrarater reliability was calculated using intraclass correlation coefficients and Spearman's correlation coefficients, respectively, for both EAI and DME ratings. There was a linear relationship between EAI and DME means for monotony, indicating it is a metathetic dimension. Curvilinear relationships were observed between the EAI and DME means for the other four features, indicating prothetic dimensions. Intra- and interrater reliability values were similar for EAI and DME ratings. Overall, results of this work suggest that DME is the best fit for scaling several hypokinetic dysarthria features, and not the conventionally used EAI scale. Prothetic dimensions best scaled by DME include overall speech severity, articulatory imprecision, reduced loudness, and short rushes of speech. Monotony was the only feature found to be a metathetic dimension and would be best scaled using EAI or DME. Findings call for rethinking the widespread use of EAI scales for rating perceptual features as part of the assessment and treatment of motor speech disorders.

Patient-related outcome measures (PROM) in adult cochlear implant patients

Cochlear implants (CI) provide individuals with severe sensorineural hearing loss the opportunity for artificial auditory perception. The standardized documentation of speech intelligibility tests is widespread, while the systematic capture of patient-related outcome measures (PROMs) remains inconsistent. Relevant PROM instruments were evaluated and selected based on the criteria of dissemination, clarity, and relevance, integrated into routine clinical practice, and tested at longitudinal time points. A total of three PROM instruments were selected and successfully integrated into the clinical routine. The comparison of 2measurement points from 25individuals showed improvements in subjective speech comprehension and tinnitus perception. This study demonstrates the clinical implementation and integration of PROMs in adult CI candidates and patients. The PROMs are apromising tool to support various phases of treatment, both as adecision aid for potential CI candidates and for monitoring after implantation.

Experimental study of mechanical properties of deep-sea hydrate-bearing sediments under multi-field coupling conditions

To ensure the long-term safety of hydrate-bearing sediments (HBSs) in the deep sea, it is necessary to conduct a comprehensive study of the mechanical properties of HBSs, which is closely related to the safe extraction of natural gas hydrates (NGH). In this study, a HBSs preparation method was proposed preparing HBSs artificially to meet the test requirement. A series of triaxial shear tests were carried out by the self-developed HBSs multi-field coupling intelligent triaxial test device to analyze the effects of different hydrate saturation and NaCl concentration on the mechanical properties of HBSs. The results show that HBSs have elastic-plastic properties under multi-field coupling conditions, and the stress-strain curves show a strain-hardening trend. Hydrate saturation affects the shear strength of hydrate-bearing sediment critically. When the hydrate saturation is Sh>35 %, the cohesion and internal friction angle is directly proportional to the hydrate saturation. When the NaCl concentration is low, the cohesion of HBSs is more affected by the NaCl concentration, and the shear strength and yield strength are proportional to NaCl concentration. When NaCl concentration is high, the internal friction angle of HBSs is more affected by NaCl concentration and the shear strength is inversely proportional to NaCl concentration. Under the condition of multi-field coupling, the influence of each factor on the mechanical properties of HBSs has an upper limit, which is not a purely linear relationship.

In situ testing of micro-ecological elements in offshore engineering

With the increasing human development and utilization of the ocean, the impact of offshore engineering on the ocean ecological environment is becoming more and more serious. In this article, a technique for in situ monitoring of marine micro-ecological elements based on laser-induced fluorescence is proposed. Combining laser-induced fluorescence with different types, contents, and proportions of micro-ecological elements, we establish the relationships between the concentration of marine micro-ecological elements, their diversity, and the fluorescence intensity of different wavelengths in order to detect the abundance and dominant species of micro-ecological elements in the ocean in situ. The experimental results show that this technique has the advantages of in situ, rapid, convenient, and continuous measurement, which provides a technical basis for accurate and rapid intelligent testing of marine micro-ecological elements for the development and maintenance of offshore engineering.

Future Prospects of the Assembly Model for MEP Systems in Chinese Buildings: A Whole Life Cycle Perspective

The assembly building M&amp;E (Monitoring and Evaluation) system is a vital part of the transformation of China’s construction industry, featuring intelligent control, high efficiency, and high safety. The article provides a comprehensive review of research related to assembly M&amp;E systems from the perspective of the whole life cycle of assembly, containing 125 journal articles from 1993 to 2024. The article analyzes some policies with updated iterations in the United States, Japan, Germany, Denmark, France, and the European Union. The literature review and semi-structured interviews with experts identified significant constraints limiting the various stages of the entire life cycle of assembled MEP (mechanical, electrical, and plumbing) systems. The absence of uniform design standards, personnel collaboration, prefabricated component testing, transportation, information utilization, intelligent testing, and recycling of disassemblability that can occur in the entire life cycle of assembled MEP systems are summarized. Finally, the article suggests that assembly M&amp;E systems can be shared and marketed to improve the economic viability of assembly M&amp;E systems and their wide application in the areas of technology, platform, and demand.

Research on the Construction Technology of INS Digital Prototype Based on Digital Twin

In response to the continuous advancement of digitalization and intelligence in equipment as mandated by the state, a digital twin-based inertial navigation digital prototype construction scheme has been designed. This scheme supports the realization of intelligent manufacturing, testing, evaluation, and operational assurance throughout the lifecycle of inertial navigation products. This paper decomposes the physical entities of the " three-autonomy " SINS and integrates component-level inertial navigation digital prototypes based on the principles of inertial navigation. The prototypes were integrated using heterogeneous models in simulation software. Pure navigation functionality verification was conducted on the prototypes. The results show that the errors in pure simulation of the inertial navigation digital prototypes constructed in this study are consistent with the physical navigation results of inertial navigation systems, providing a reference for the development of inertial navigation digital twin systems.

Speech recognition and speech audiometry parameters in evaluation of aural rehabilitation progress in cochlear implant patients. Review paper.

&lt;b&gt;Introduction:&lt;/b&gt; Speech audiometry is well established and frequently used test in audiology as well as in cochlear implant recipient's performance evaluation. Expanding indications for cochlear implantation forces use of more refined methods of both assessment and prognosis of outcome of aural rehabilitation. Variability of speech intelligibility tests and materials require standardized protocol facilitating outcome comparison.&lt;b&gt;Aim:&lt;/b&gt; Aim of this review paper is analysis of usage of speech audiometry and other speech intelligibility tests and its results reporting in patients with cochlear implant in Poland and in the World.&lt;b&gt;Materials and methods:&lt;/b&gt; Protocols of many different domestic and foreign health centers where compared, showing many methodological differences. Selection of literature for analysis was made according to PRISMA algorithm recommendations. Twenty research papers were chosen for review process.&lt;b&gt;Discussion:&lt;/b&gt; In many papers we found lack of data regarding methodology of performed tests. Many authors indicate difficulties in comparing results, especially if publication lacks basic technical information. Despite that if right method is applied, results can be compared. In literature only one level of material presentation in test is prevalent. Speech audiometry is significant in exploring connections between multiple pre-op and post-op prognostic aspects of cochlear implantation.&lt;b&gt;Conclusions:&lt;/b&gt; Because of variability in presentation and reporting of CI patients outcomes, consensus is needed in area of system facilitating comparison of research results. This may provide simple solution for accurate analysis and choosing right set of data. Schematic of presentation of audiological data in authors health center was proposed as example.

Organosilane-assisted synthesis of EU-1 nanozeolite aggregates with improved activity in catalytic cracking of n-hexane

One-dimensional microporous zeolite, EU-1, exhibits more favorable selectivity of propylene in cracking of petroleum components. However, it faced the problem of low catalytic activity for the poor utilization of active sites. In this work, dimethyloctadecyl[3-(trimethoxysilyl)propyl]ammonium chloride (TPOAC) was used to functionalize protozeolitic units and inhibit the excessive growth of crystals by the long hydrophobic alkyl chain. The introduction of TPOAC decreased the crystal sizes into nanoscale, enhanced the mesoporous volume of EU-1 zeolite, and exposed more external acid sites. Moreover, TPOAC could interact with Al species, and in this case, fewer Al atoms were incorporated into the zeolite framework, reducing the acid strength and amount. Intelligent gravitation analyzer test indicated that the zeolite prepared with the presence of 0.30 g TPOAC exhibited the largest accessible volumes in n-hexane adsorption, and the highest accessibility of acid sites, which synergistically promoted cracking of n-hexane for the production of light olefins.

Design and experiment of an intelligent testing bench for air-suction seed metering devices for small vegetable seeds

In order to realise the real-time monitoring of seeding quality of small vegetable seeds, and solve the problem of inconvenience caused by the small particle sizes of vegetable seeds, an intelligent testing bench for air-suction seed metering device for small vegetable seeds with a particle diameter of 0.5–3 mm was designed, and a complementary quality monitoring and controlling system was developed. The photoelectric sensing technology and image recognition technology were used together in the system. Photoelectric sensing technology was used for real-time monitoring of seed counting, while the image recognition technology can dynamically monitor the missed seeding, repeated seeding and the falling trajectory of seed deposition in real time. The system was installed on the air-suction intelligent testing bench to test the monitoring accuracy of the monitoring system. The experimental results demonstrated that the monitoring accuracy of drilling quality monitoring system was over 97%, the monitoring accuracy of miss seeding was over 95%, and the monitoring accuracy of repeated seeding was over 93%. Furthermore, the monitoring system was less affected by the seed particle size, shape, and plant spacing, etc., and the system was stable, which effectively realised the real-time monitoring of the operation of air-suction metering device.