Intelligibility Test Research Articles

Intelligent liver function testing (iLFT): A trial of automated diagnosis and staging of liver disease in primary care

Liver function tests (LFTs) are frequently requested blood tests which may indicate liver disease. LFTs are commonly abnormal, the causes of which can be complex and are frequently under investigated. This can lead to missed opportunities to diagnose and treat liver disease at an early stage. We developed an automated investigation algorithm, intelligent liver function testing (iLFT), with the aim of increasing the early diagnosis of liver disease in a cost-effective manner. We developed an automated system that further investigated abnormal LFTs on initial testing samples to generate a probable diagnosis and management plan. We integrated this automated investigation algorithm into the laboratory management system, based on minimal diagnostic criteria, liver fibrosis estimation, and reflex testing for causes of liver disease. This algorithm then generated a diagnosis and/or management plan. A stepped-wedged trial design was utilised to compare LFT outcomes in general practices in the 6 months before and after introduction of the iLFT system. Diagnostic outcomes were collated and compared. Of eligible patients with abnormal LFTs, 490 were recruited to the control group and 64 were recruited to the intervention group. The primary diagnostic outcome was based on the general practitioner diagnosis, which agreed with the iLFT diagnosis in 67% of cases. In the iLFT group, the diagnosis of liver disease was increased by 43%. Additionally, there were significant increases in the rates of GP visits after diagnosis and the number of referrals to secondary care in the iLFT group. iLFT was cost-effective with a low initial incremental cost-effectiveness ratio of £284 per correct diagnosis, and a saving to the NHS of £3,216 per patient lifetime. iLFT increases liver disease diagnoses, improves quality of care, and is highly cost-effective. This can be achieved with minor changes to working practices and exploitation of functionality existing within modern laboratory diagnostics systems. There is a growing epidemic of advanced liver disease, this could be offset by early detection and management. Checking liver blood tests (LFTs) should be an opportunity to diagnose liver problems, but abnormal results are often incompletely investigated. In this study we were able to substantially increase the diagnostic yield of the abnormal LFTs using the automated intelligent LFT system. With the addition of referral recommendations and management plans, this strategy provides optimum investigation and management of LFTs and is cost saving to the NHS.

Design and Implementation of Intelligent Measurement Testing and Calibration Management Information System based on Big Data

In recent years most testing and calibration laboratories in developed and developing countries have generally enhanced the awareness of information construction by adopting laboratory information management system to strengthen the information construction. This paper designs an intelligent measurement testing and calibration management information system based on large data, aiming at the problems of data connection and transfer, sample flow management, weak quality management and customer’s informed inspection status in testing and calibration laboratory.The system adopts B/S and C/S mixed development mode, uses the current popular information technologies and utilize reasonably SQL Server database resources.Based on the network topology and architecture of the system, the system realizes function modules. In addition, this paper makes innovations in measurement equipment, sample testing, operation record, certificate life cycle management, multi-channel notification to customers, intelligent early warning.Therefore, the intelligent measurement and calibration management information system provides guarantee for improving refined management level of measuring and testing Institutes and third-party detection institutions, standardizing business processes, improving work efficiency and quality management, and providing better service to customers.

Research on Construction of Intelligent Operational Simulation Test Environment

With the development of simulation technologies, simulation test has become an important means of weapon equipment demonstration, finalization and operational test and evaluation, but the simulation test system built for the performance evaluation cannot meet the requirements of system of systems (SoS) operational test and evaluation. This paper analyzes the requirements of the operational simulation test for the intelligent simulation test system and puts forward an intelligent simulation framework of the complex simulation test system and its main elements, which realizes the simulation of the operational activities with uncertain confrontation process and can support the demonstration, construction and evaluation of the weapon equipment system. The research results have been applied to the construction of a certain simulation system and provided support for the test and evaluation of equipment SoS tests.

Adaptive deep brain stimulation as advanced Parkinson’s disease treatment (ADAPT study): protocol for a pseudo-randomised clinical study

IntroductionAdaptive deep brain stimulation (aDBS), based on the detection of increased beta oscillations in the subthalamic nucleus (STN), has been assessed in patients with Parkinson’s disease (PD) during the immediate...

Benefits of a contralateral routing of signal device for unilateral Naída CI cochlear implant recipients.

Many bilaterally deaf adults are only able to receive one cochlear implant (CI), resulting in suboptimal listening performance, especially in challenging listening environments. Adding a contralateral routing of signal (CROS) device to a unilateral CI is one possibility to alleviate these challenges. This study examined the benefit of such a CROS device. Thirteen adult subjects with at least 6months of CI use, and no or limited benefit of a hearing instrument in the contralateral ear were included in the study. The perceived benefit of a CROS device in everyday listening environments was evaluated up to 1 year after initial fitting using several questionnaires. Speech intelligibility performance was determined using the French matrix sentence test in quiet and in two speech-in-noise setups and was followed for 3 months after CROS fitting. Subjects indicated high satisfaction with the practical usability of the CROS device and long-term device retention was high. Perceived benefits in everyday listening environments were reported. Formal speech intelligibility tests revealed statistically significant median improvements of 6.93dB SPL (Wilcoxon Z = 2.380, p = 0.017) in quiet and up to 8.00dB SNR (Wilcoxon Z = 2.366, p = 0.018) in noise. These benefits were accessible immediately without a need for prolonged acclimatization. Subjective satisfaction and device retention as well as speech intelligibility benefits in quiet and in noise prove the CROS device to be a valuable addition to a unilateral CI in cases of bilateral deafness where bilateral implantation is not an option.

Enhanced patient care, reduced costs and measurable better healthcare performance through implementation of intelligent liver function testing (ILFT)

Triterpene saponins include bioactive compounds with structures consisting of triterpene aglycones (sapogenins) and one or more sugar moieties linked through acetal or ester glycosidic linkages at one or more sites. Centella asiatica (L.) Urban is a medicinal plant that contains bioactive ursane-type saponins, such as madecassoside and asiaticoside. In this work, glucosylation of triterpenoids in C. asiatica was investigated starting with plant extracts. An enzyme capable of glucosylating asiatic and madecassic acids was partially purified. Proteomics methods and cDNA sequence data were employed as tools to obtain a full-length cDNA clone encoding a glucosyltransferase. The recombinant gene product, UGT73AD1, was functionally expressed in Escherichia coli and purified by immobilized metal-affinity chromatography. Purified recombinant UGT73AD1 was found to have a narrow specificity, glucosylating asiatic and madecassic acids at the C28 carboxyl. mRNA accumulated in all tissues tested (leaves, stems, roots and flowers), with highest expression in leaves. Thus, UGT73AD1 was identified as a triterpenoid carboxylic acid: UDP-glucose 28-O-glucosyltransferase that appears to be involved in saponin biosynthesis in C. asiatica.

Simulation modeling and interface parameter design of the semi‐physical braking intelligent test system

AbstractIn order to adapt to the improvement of freight train braking technology, it is a good method to establish a semi‐physical braking intelligent test system, and the core technology of modeling and interface that supports the system is especially critical. Based on the above background, this paper is focus on the simulation modeling that reflects the braking performance characteristics of freight trains and designs the interface system that can be connected with the test equipment. Based on the analysis of the state equations of pressure gas during the braking process and the characteristics of fluid changes, this paper deduces a modular digital model of the braking machine that reflects the structural factors and the influencing factors of the process of fluid transfer. Then it combines the specific braking tests to verify the significance of the model and the effect of parameter changes on braking performance. The experimental results show the accuracy and feasibility of the modeling process, which provides a reference model establishing method and a research idea for the establishment of a more completed set of freight train braking system mathematical model. The design and implementation of this part of the technology also provide an important basis for the control part of the entire semi‐physical braking intelligent test system.

Adversarial Training for Speech Super-Resolution

Speech super-resolution or speech bandwidth expansion aims to upsample a given speech signal by generating the missing high-frequency content. In this paper, we propose a deep neural network approach exploiting the adversarial training ideas that have been shown effective in image super-resolution. Specifically, our proposed network follows the generative adversarial networks setup, where the generator network uses a convolutional autoencoder architecture with one-dimensional convolution kernels to generate high-frequency log-power spectra from the low-frequency log-power spectra of the input speech. We propose to use both the reconstruction loss and the adversarial loss for training, and we employ a recent regularization method that penalizes the gradient norms of the discriminator to stabilize the training. We compare our proposed approach with two state-of-the-art neural network baselines and evaluate these methods with both objective speech quality measures and subjective perceptual and intelligibility tests. Results show that our proposed method outperforms both baselines in terms of both objective and subjective evaluations. To gain insights of the network architecture, we analyze key parameters of the proposed network including the number of layers, the number of convolution kernels, and the relative weight of the reconstruction and adversarial losses. Besides, we analyze the computational complexity of our method and the baselines and discuss ways for phase estimation. We further develop a noise-resilient version of the proposed approach by training the network with noisy speech inputs. Objective evaluation validates the noise-resilient property on unseen noise types.

Personalized signal-independent beamforming for binaural hearing aids.

The effect of personalized microphone array calibration on the performance of hearing aid beamformers under noisy reverberant conditions is studied. The study makes use of a new, publicly available, database containing acoustic transfer function measurements from 29 loudspeakers arranged on a sphere to a pair of behind-the-ear hearing aids in a listening room when worn by 27 males, 14 females, and 4 mannequins. Bilateral and binaural beamformers are designed using each participant's hearing aid head-related impulse responses (HAHRIRs). The performance of these personalized beamformers is compared to that of mismatched beamformers, where the HAHRIR used for the design does not belong to the individual for whom performance is measured. The case where the mismatched HAHRIR is that of a mannequin is of particular interest since it represents current practice in commercially available hearing aids. The benefit of personalized beamforming is assessed using an intrusive binaural speech intelligibility metric and in a matrix speech intelligibility test. For binaural beamforming, both measures demonstrate a statistically signficant (p < 0.05) benefit of personalization. The benefit varies substantially between individuals with some predicted to benefit by as much as 1.5 dB.

Non-native speech recognition sentences: A new materials set for non-native speech perception research

Research into non-native (L2) speech perception has increased the need for specialized experimental materials. The Non-Native Speech Recognition (NNSR) sentences are a new large-scale set of speech recognition materials for research with L2 speakers of English at CEFR level B1 (North, Ortega, & Sheehan, 2010) and above. The set comprises 439 triplets of sentences in three related conditions: semantically predictable, neutral, and anomalous. The sentences were created by combining a strongly or weakly contextually constrained sentence frame with a congruent or anomalous final keyword, and they were matched on a number of factors during development, to maintain consistency across conditions. This article describes the development process of the NNSR sentences, along with results of speech-in-noise intelligibility testing for L2 and native English speakers. Suggestions for the sentences’ application in a range of investigations and experimental designs are also discussed.

Normal-to-Lombard adaptation of speech synthesis using long short-term memory recurrent neural networks

In this article, three adaptation methods are compared based on how well they change the speaking style of a neural network based text-to-speech (TTS) voice. The speaking style conversion adopted here is from normal to Lombard speech. The selected adaptation methods are: auxiliary features (AF), learning hidden unit contribution (LHUC), and fine-tuning (FT). Furthermore, four state-of-the-art TTS vocoders are compared in the same context. The evaluated vocoders are: GlottHMM, GlottDNN, STRAIGHT, and pulse model in log-domain (PML). Objective and subjective evaluations were conducted to study the performance of both the adaptation methods and the vocoders. In the subjective evaluations, speaking style similarity and speech intelligibility were assessed. In addition to acoustic model adaptation, phoneme durations were also adapted from normal to Lombard with the FT adaptation method. In objective evaluations and speaking style similarity tests, we found that the FT method outperformed the other two adaptation methods. In speech intelligibility tests, we found that there were no significant differences between vocoders although the PML vocoder showed slightly better performance compared to the three other vocoders.

An Intelligent Test Paper Generation Method to Solve Semantic Similarity Problem

In order to solve the problem of semantic duplication in the Intelligent Test Paper Generation Method, Genetic Particle Swarm Optimization Algorithm was used to search multi groups of test papers that conform to the constraints of the test. Then the idea of density entropy was used to screen the test papers, so that test papers will cover more questions uniformly. After that, analyze the semantic similarity of the test papers that use the TextRank algorithm to extract the key words of test questions, and use knowledge-keywords weighted VSM model to calculate the semantic similarity of test questions. Eliminate the high repetition rate of the test papers and avoid the repetition of the inspection points. The experimental results show that the algorithm can solve the semantic similarity problem in intelligent test paper generation of mass item bank.

다중지능 기반 이야기 활용 영어 수업이 초등 학습부진학생의 읽기 및 학습태도에 미치는 효과

The study aims to examine whether teaching English through multiple intelligences can suggest one of the solutions for underachievers to facilitate their English learning and restore their learning attitudes. To explore this, the study investigated two research questions: (a) What are the effects of English instruction using multiple intelligences and stories on underachievers’ reading abilities? and (b) How English instruction using multiple intelligences and stories influences on their learning attitudes? The participants of the study were seven fifth-grade underachievers in one elementary school in Seoul. They were first tested what their strong intelligences are and engaged in customized activities based on their multiple intelligences test results during the experiment English classes. The data collected include the read-aloud test, the reading comprehension test, the affective test, students’ learning log and the interview of students and teachers, and these were analyzed both quantitatively and qualitatively. The results of the study showed that English instruction using multiple intelligences and stories had statistical significance in increasing underachievers’ reading abilities and changing their learning attitudes positively. This study is valuable in that it strongly calls for the need to consider multiple intelligences and provide customized activities for underachievers to facilitate their English learning and restore their learning attitudes.

Application of Artificial Intelligence in Autonomous English Learning among College Students

To improve the English proficiency of college students, this paper attempts to promote autonomous English learning among these students using artificial intel-ligence technology. Specifically, the principles, features and application fields of artificial intelligence were introduced in details, and the requirements, structure, database and processes of autonomous English learning systems were discussed at length. On this basis, the backpropagation (BP) neural network, a typical artifi-cial intelligence technique, was selected to design the modules of the autonomous English learning system for college students. The proposed system was then im-plemented in integrated open environment of Visual Studio, the architecture of the browser/server system and the SQL Server database on the Windows platform. The results show that the proposed system provides college students with intelli-gent and open self-evaluation tests and effective learning feedbacks. The research findings shed new light on improving the English learning of college students and reliving the pressure on college English teachers.

An Investigation of the Clinical Use of a Single-Word Procedure to Assess Intelligibility (Swedish Test of Intelligibility for Children) and an Evaluation of the Validity and Reliability of the Intelligibility in Context Scale.

Purpose Intelligibility is a core concept of speech-language pathology, central both to the assessment of speech disorders and to intervention in such disorders. One purpose of this study was to investigate the reliability and usability of a single-word assessment procedure, the Swedish Test of Intelligibility for Children (STI-CH), in a clinical setting. Another purpose was to investigate the validity and reliability of an assessment method designed to assess functional intelligibility: the Intelligibility in Context Scale (ICS). Method Thirty children aged 4;1-10;1 years;months were recruited from speech-language pathology clinics in Western Sweden. Each child's treating speech-language pathologist served as listener in the STI-CH assessment while the ICS was completed by each child's parents. External listeners (2 last-year speech-language pathology students) were used to assess the validity of the speech-language pathology. Results The mean duration of the test procedure for the STI-CH was about 19 min, and 57% of the test sessions were reported as difficult. There was a weak but statistically significant correlation between the results from the STI-CH and the ICS ( r = .40, p < .05), and both methods showed high reliability in terms of interlistener reliability (intraclass correlation exceeding .97) and internal consistency, respectively. Conclusions The STI-CH had high reliability and was time efficient but had some procedural problems. The ICS had moderate validity but high reliability. The STI-CH is promising for clinical use but needs to be developed further. The validity of the ICS can be discussed and needs to be further investigated.

Perceptual analysis of the speech intelligibility and soundscape of multilingual environments

This paper examines the perceived speech intelligibility of English, Polish, Arabic, and Mandarin and, more generally, the soundscape associated to multilingual environments. Listening tests were used to evaluate three acoustic environments (an airport, a hospital, and a café) under three room acoustic conditions defined by a different speech transmission index (STI) (STI = 0.4, 0.5 and 0.6). In the tests, participants rated eleven semantic attributes representative of speech perception and the overall soundscape (speech intelligibility, speech level, speech pleasantness, noisiness, annoyance, relaxation, comfort, environment pleasantness, eventfulness, excitement, and familiarity). Results obtained indicate that inter-language comparisons based on perceived speech intelligibility are different from those obtained from objective speech intelligibility tests. Noticeably, English participants were found to be most sensitive to changes in room acoustic conditions and to meaningful and distractive noise sources, whilst Arab participants were least sensitive to changes in room acoustic conditions and more tolerant to noise. Perceived speech intelligibility correlated significantly with non-acoustical factors (speech pleasantness, comfort and environment pleasantness), and ‘emotional factors’ (annoyance, relaxation, comfort and environment pleasantness) explained a large portion of the variance in soundscape assessment. Results also showed that language affected the perceived speech intelligibility marginally (p = 0.051) and noisiness significantly (p = 0.047), the latter being the best indicator of cultural variations amongst the attributes tested. Overall, the study shows that designing for speech intelligibility cannot be solely based on room acoustic parameters, especially in the case of multi-lingual environments.

Synthesis of Hydroxyapatite with Antibacterial Properties Using a Microwave-Assisted Combustion Method

The prevention of implant-associated infections has been increasing clinically in orthopedic surgery. Hydroxyapatite with antibacterial properties was synthesized using a microwave-assisted combustion method. High crystallinity at low temperature can be achieved using this method. The synthesized hydroxyapatite exhibited a superior clear zone for both Gram-positive and Gram-negative bacteria. Electron spin resonance (ESR) and X-ray photoelectron spectroscopy (XPS) were used for the radical investigation. The application of intelligent ink testing and an antioxidant assay using DPPH reduction were also used to confirm the existence of radicals. These techniques provided data confirming that radicals are responsible for the antibacterial properties. The synthesized antibacterial hydroxyapatite would be a good candidate for the prevention any infection with medical implants and injection materials causing failure in bone repair.

Research on Control of Intelligent Vehicle Human-Simulated Steering System Based on HSIC

The experienced drivers with good driving skills are used as objects of learning, and road steering test data of skilled drivers are collected in this article. First, a nonlinear fitting was made to the driving trajectory of skilled driver in order to achieve human-simulated control. The segmental polynomial expression was solved for two typical steering conditions of normal right-steering and U-turn, and the hp adaptive pseudo-spectral method was used to solve the connection problem of the vehicle segmental driving trajectory. Second, a new Electric Power Steering (EPS) system was proposed, and the intelligent vehicle human-simulated steering system control model based on human simulated intelligent control (HSIC) was established in Simulink/Carsim joint simulation environment to simulate and analyze. Finally, in order to further verify the effectiveness of the proposed algorithm in this article, an intelligent vehicle steering system test bench with a steering resistance torque simulation device was built, and the dSPACE rapid prototype controller was used to realize human-simulated intelligent control law. The results show that the human-simulated steering control algorithm is superior to the traditional proportion integration differentiation (PID) control in the tracking effect of the steering characteristic parameters and passenger comfort. The steering wheel angle and torque can better track the angle and torque variation curve of real vehicle steering experiment of the skilled driver, and the effectiveness of the intelligent vehicle human-simulated steering control algorithm based on HSIC proposed in this article is verified.

3122 Longitudinal Recovery of Speech Motor Function Following Facial Transplantation

OBJECTIVES/SPECIFIC AIMS: Using a novel biomechanical-based motor speech assessment alongside commonly used clinically-based motor speech assessments, the goal of this study was to describe longitudinal recovery in speech movements and functional speech in a cohort of 5 patients following facial transplantation. METHODS/STUDY POPULATION: Five participants who had received either full or partial face transplantation were included in this study. Each participant received a unique facial graft from their donor, which included varied amounts of soft tissue, facial musculature, nerve, and bone. Two participants were early in the recovery period and were assessed from zero to 24 months post-transplantation. Three participants were late in the recovery period and were assessed from 36 to 60 months post-transplantation. Each participant completed two data collection sessions and the average time between sessions was 20.4 months. At each session, orofacial movements were recorded using a 3D motion capture system. A 4-sensor head marker was used to subtract head movement (translation and rotation) from the facial markers. The analyses in this study were restricted to two markers: midline lower lip and a virtually calculated midline jaw marker. A marker at the top of the nose bridge was used as the origin point. The following kinematic variables were obtained from each lip-jaw movement time-series: peak movement speed (mm/s), and displacement (mm). Each patient was instructed to perform 10 repetitions of the phrase “buy bobby a puppy” at his or her typical speaking rate and volume. Sentence-level intelligibility was obtained using the Sentence Intelligibility Test (SIT) and word-level intelligibility was obtained using the Word Intelligibility Test, using standard procedures. Intelligibility, measured in percentage of words correctly transcribed, and speaking rate, measured in words per minute (wpm), was derived from the SIT sentences for each patient. Intelligibility, measured in percentage of words correctly chosen via multiple choice was derived from the Word Intelligibility Test. RESULTS/ANTICIPATED RESULTS: Effect sizes (Cohen’s d) across the 10 trials of “buy bobby a puppy” were computed to assess the effects of recovery time on range of motion and speed of the lower lip alone, the jaw alone, and the lower lip and jaw together for both range of motion and for speed. The largest effect sizes were observed for increased range of motion and increased speed of the articulators for participants within 24 months of surgery. Smaller effect sizes were observed for these parameters for the participants in the later stages of recovery, with some participants showing declines in range of motion and speed of some but not all articulators. Descriptive statistics indicate that both speech and word intelligibility improvements are most notable in the first two years following transplantation and appear to plateau during the later stages of recovery. Only two out of five of our participants achieved “normal” speech intelligibility (i.e., &gt;97%) at five years post-transplantation. DISCUSSION/SIGNIFICANCE OF IMPACT: Biomechanical assessment revealed that kinematic recovery of articulator range of motion and speed appears most significant in the first two years following surgery, but that improvement continues to some degree as far as five-years post-transplant. Clinically-based assessments suggest that gains in intelligibility appear to plateau by 3-years post-surgery.

Information Loss in the Human Auditory System

From the eardrum to the auditory cortex, where acoustic stimuli are decoded, there are several stages of auditory processing and transmission where information may potentially be lost. In this paper, we aim at quantifying the total information loss in the human auditory system by using information theoretic tools. To do so, we consider a speech communication model, where words are uttered and sent through a noisy channel, and then received and processed by a human listener. We define a notion of information loss that is related to the human word recognition rate. To assess the word recognition rate of humans, we conduct a closed-vocabulary intelligibility test. We derive upper and lower bounds on the information loss. Simulations reveal that the bounds are tight and we observe that the information loss in the human auditory system increases as the signal to noise ratio (SNR) decreases. Our framework also allows us to study whether humans are optimal in terms of speech perception in a noisy environment. Toward that end, we derive optimal classifiers and compare the human and machine performance in terms of information loss and word recognition rate. We observe a higher information loss and lower word recognition rate for humans compared to the optimal classifiers. In fact, depending on the SNR, the machine classifier may outperform humans by as much as 8 dB. This implies that for the speech-in-stationary-noise setup considered here, the human auditory system is suboptimal for recognizing noisy words.