Intelligent Measurement Research Articles

Speech Intelligibility Level Determinants and Measurement Methods

With the ever-increasing population of non-native speakers (NNSs) of English around the globe to the extent of exceeding the population of native speakers, encountering foreign-accented speech (FAS) has become frequent and inevitable. In this paper, the author highlights English in its new position, and its impact on speech intelligibility. The concept of speech intelligibility is discussed as it correlates with accentedness. It is viewed as an indicator for successful oral communication. A review of the different factors that impact speech intelligibility, in relation to the speakers and others related to the listeners. Moreover, speech intelligibility is modulated in relation to the different factors. Finally, numerous measurement methods that have been used regarding assisting the speech intelligibility of English in general and the intelligibility of English variety are discussed in particular.

Impact of Startling Acoustic Stimuli on Word Repetition in Individuals With Aphasia and Apraxia of Speech Following Stroke.

The StartReact effect, whereby movements are elicited by loud, startling acoustic stimuli (SAS), allows the evaluation of movements when initiated through involuntary circuitry, before auditory feedback. When StartReact is applied during poststroke upper extremity movements, individuals exhibit increased muscle recruitment, reaction times, and reaching distances. StartReact releases unimpaired speech with similar increases in muscle recruitment and reaction time. However, as poststroke communication disorders have divergent neural circuitry from upper extremity tasks, it is unclear if StartReact will enhance speech poststroke. Our objective is to determine if (a) StartReact is present in individuals with poststroke aphasia and apraxia and (b) SAS exposure enhances speech intelligibility. We remotely delivered startling, 105-dB white noise bursts (SAS) and quiet, non-SAS cues to 15 individuals with poststroke aphasia and apraxia during repetition of six words. We evaluated average word intensity, pitch, pitch trajectories, vowel formants F1 and F2 (first and second formants), phonemic error rate, and percent incidence of each SAS versus non-SAS-elicited phoneme produced under each cue type. For SAS trials compared to non-SAS, speech intensity increased (∆ + 0.6 dB), speech pitch increased (∆ + 22.7 Hz), and formants (F1 and F2) changed, resulting in a smaller vowel space after SAS. SAS affected pitch trajectories for some, but not all, words. Non-SAS trials had more stops (∆ + 4.7 utterances) while SAS trials had more sustained phonemes (fricatives, glides, affricates, liquids; ∆ + 5.4 utterances). SAS trials had fewer distortion errors but no change in substitution errors or overall error rate compared to non-SAS trials. We show that stroke-impaired speech is susceptible to StartReact, evidenced by decreased intelligibility due to altered formants, pitch trajectories, and articulation, including increased incidence of sounds that could not be produced without SAS. Future studies should examine the impact of SAS on voluntary speech intelligibility and clinical measures of aphasia and apraxia.

Speech treatment for Hebrew-speaking adolescents and young adults with developmental dysarthria: A comparison of mSIT and Beatalk.

Individuals with developmental dysarthria typically demonstrate reduced functioning of one or more of the speech subsystems, which negatively impacts speech intelligibility and communication within social contexts. A few treatment approaches are available for improving speech production and intelligibility among individuals with developmental dysarthria. However, these approaches have only limited application and research findings among adolescents and young adults. To determine and compare the effectiveness of two treatment approaches, the modified Speech Intelligibility Treatment (mSIT) and the Beatalk technique, on speech production and intelligibility among Hebrew-speaking adolescents and young adults with developmental dysarthria. Two matched groups of adolescents and young adults with developmental dysarthria participated in the study. Each received one of the two treatments, mSIT or Beatalk, over the course of 9 weeks. Measures of speech intelligibility, articulatory accuracy, voice and vowel acoustics were assessed both pre- and post-treatment. Both the mSIT and Beatalk groups demonstrated gains in at least some of the outcome measures. Participants in the mSIT group exhibited improvement in speech intelligibility and voice measures, while participants in the Beatalk group demonstrated increased articulatory accuracy and gains in voice measures from pre- to post-treatment. Significant increases were noted post-treatment for first formant values for select vowels. Results of this preliminary study are promising for both treatment approaches. The differentiated results indicate their distinct application to speech intelligibility deficits. The current findings also hold clinical significance for treatment among adolescents and young adults with motor speech disorders and application for a language other than English. What is already known on the subject Developmental dysarthria (e.g., secondary to cerebral palsy) is a motor speech disorder that negatively impacts speech intelligibility, and thus communication participation. Select treatment approaches are available with the aim of improving speech intelligibility in individuals with developmental dysarthria; however, these approaches are limited in number and have only seldomly been applied specifically to adolescents and young adults. What this paper adds to existing knowledge The current study presents preliminary data regarding two treatment approaches, the mSIT and Beatalk technique, administered to Hebrew-speaking adolescents and young adults with developmental dysarthria in a group setting. Results demonstrate the initial effectiveness of the treatment approaches, with different gains noted for each approach across speech and voice domains. What are the potential or actual clinical implications of this work? The findings add to the existing literature on potential treatment approaches aiming to improve speech production and intelligibility among individuals with developmental dysarthria. The presented approaches also show promise for group-based treatments as well as the potential for improvement among adolescents and young adults with motor speech disorders.

The Experience and Enlightenment of Asian Smart City Development—A Comparative Study of China and Japan

With the urbanization level advancing in cities, increasingly significant urban ecological environment problems must be solved. The construction of a smart city with the overall development of information technology also regards environmental friendliness as the primary goal. The “smart” idea of urban environment innovation and governance has become a new model. In this paper, we first expound on the development process of low-carbon cities, eco-cities, and smart cities in Japan and China. Then, we analyze the coordinated development of intelligent environmental protection measures in government policies, transportation, energy utilization, resource recovery, and community management. Finally, we compare Japan and China’s smart city development characteristics. We discuss the improvement measures for energy utilization, urban transportation, and urban operation, including developing renewable energy systems, efficient energy use, and citizen participation policy. These experiences can provide feasible measures for constructing Asian smart cities and have great significance for the city’s sustainable applications and practice.

Comparison of discrete transforms for deep‐neural‐networks‐based speech enhancement

In recent studies of speech enhancement, a deep-learning model is trained to predict clean speech spectra from the known noisy spectra of speech. Rather than using the traditional discrete Fourier transform (DFT), this paper considers other well-known transforms to generate the speech spectra for deep-learning-based speech enhancement. In addition to the DFT, seven different transforms were tested: discrete Cosine transform, discrete Sine transform, discrete Haar transform, discrete Hadamard transform, discrete Tchebichef transform, discrete Krawtchouk transform, and discrete Tchebichef-Krawtchouk transform. Two deep-learning architectures were tested: convolutional neural networks (CNN) and fully connected neural networks. Experiments were performed for the NOIZEUS database, and various speech quality and intelligibility measures were adopted for performance evaluation. The quality and intelligibility scores of the enhanced speech demonstrate that discrete Sine transformation is better suited for the front-end processing with a CNN as it outperformed the DFT in this kind of application. The achieved results demonstrate that combining two or more existing transforms could improve the performance in specific conditions. The tested models suggest that we should not assume that the DFT is optimal in front-end processing with deep neural networks (DNNs). On this basis, other discrete transformations should be taken into account when designing robust DNN-based speech processing applications.

Calculation model for ventilation friction resistance coefficient by surrounding rock roughness distribution characteristics of mine tunnel

Real-time mine ventilation network solution is the core way to realize the actual intelligent ventilation, and ventilation friction resistance coefficient is a significant parameter of network solution. With the help of fractal theory to characterize the three-dimensional roughness characteristics of tunnel surrounding rock. A method to describe the roughness by fractal dimension and fractal intercept. We put the fractal dimension and fractal intercept into Matlab to randomly generate three-dimensional laser scanning data of tunnels. The fusion of the two fractal parameters made the three-dimensional roughness surface information more comprehensive. It has been applied to field practice accurately. Compared to the simulation results show that the relative error of the new prediction results is 3%. Comprehensive evaluation analysis shows that the new friction wind resistance formula can fully reflect the influence of three-dimensional rough surfaces on airflow friction resistance. With the help of three-dimensional laser scanning technology, we can calculate the airflow friction resistance of the tunnel quickly and accurately, which provides a reference for the development of key technology and the theory of intelligent ventilation parameter measurement.

The Relationship Between Single-Word Speech Severity and Intelligibility in Childhood Apraxia of Speech.

The purpose of this study was to investigate the association between perceived single-word speech severity and intelligibility in children with childhood apraxia of speech (CAS), with and without comorbid language impairment (LI), and to investigate the contribution of different CAS signs to perceived single-word speech severity and single-word intelligibility. Thirty children with CAS, 18 with comorbid LI, completed the Goldman-Fristoe Test of Articulation-Second Edition (GFTA-2). Trained judges coded children's responses for signs of CAS and percent phonemes correct. Nine listeners, blind to diagnoses, rated speech severity using a visual analog scale. Intelligibility was assessed by comparing listeners' orthographic transcriptions of children's responses to target responses. Measures of speech severity (GFTA-2 standard score, number of unique CAS signs, total CAS signs, and mean severity rating) were significantly correlated with measures of intelligibility (GFTA-2 raw score, percent phonemes correct, and mean intelligibility score). Speech severity and intelligibility did not differ significantly between children with and without LI. Only consonant errors contributed significant variability to speech severity. Consonant errors and stress errors contributed significant variability to intelligibility. Findings suggest that visual analog scale ratings are a valid and convenient measure of single-word speech severity and that GFTA-2 raw score is an equally convenient measure of single-word intelligibility. The result that consonant errors were by far the major contributor to single-word speech severity and intelligibility in children with CAS, with stress errors also making a small contribution to intelligibility, suggests that consonant accuracy and appropriate lexical stress should be prime therapeutic targets for these children in the context of treatment addressing motor planning/programming, self-monitoring, and self-correcting. https://doi.org/10.23641/asha.19119350.

Research on intelligent measurement and driving mechanism of influencing factors of building energy saving

From project conception, planning and design, construction to operation and maintenance, construction project covers multiple aspects (including policy, resources, materials, environment, economy, and the public) and have the characteristics of complexity, long-term, and multi-factor. Based on literature research, the relationship between the main bodies of energy conservation in construction projects is established, research hypotheses are proposed, and a theoretical model of energy conservation-driven construction projects throughout the life cycle is designed in this paper. Besides, variable measurement is developed through surveys and expert interviews, and data are obtained from questionnaire surveys. Statistical analysis software such as SPSS 19 is employed to perform descriptive statistics, reliability tests, and validity analysis on sample data. Afterward, sample data is extracted through exploratory factor analysis to obtain five factors of government policy, energy-saving technology, energy-saving awareness, facility management, and energy-saving motivation. The initial structural equation model is built using AMOS 21. Additionally, the external quality and internal fit of the initial model are evaluated, and the optimized structural equation model is obtained. Finally, the theoretical model and optimization model are adopted to test the research hypothesis, clarify the relationship and path between various influencing factors, and explore the energy-saving driving mechanism of the whole life cycle of the construction project.

A framework to evaluate the accessibility, visibility, and intelligibility of green-blue spaces (GBSs) related to pedestrian movement

The planning of green-blue spaces (GBSs) requires considering the pedestrian needs in their walking routes for improving the walking experience. Incorporating the quantitative spatial characteristics of pedestrian movement is essential for pedestrian-friendly urban planning, which however received insufficient attention. Based on the space syntax theory, this study provided three indicators – accessibility, visibility, and intelligibility – to demonstrate the needs of physical access, visual access, and spatial cognition, respectively, in pedestrian movement. Measuring these three indicators, this study exemplified the planning of pedestrian-friendly GBSs using Guangzhou, China as a case study. Spatial design network analysis was used to quantify heterogeneous values of accessibility, visibility, and intelligibility of each GBS throughout the city. Moreover, we used principal component analysis to identify the leading indicators based on their weightings and then to calculate the scores to compare these three aspects of GBSs. The measurements of accessibility, visibility, and intelligibility of each GBS were then averaged across urban administrative districts for evaluating city-scale GBSs. The findings showed that GBSs in central districts were most accessible and visible but least intelligible. In contrast, the overall intelligibility of GBSs throughout the city was the greatest but the visibility was the least. Furthermore, intelligibility, as a more important factor than accessibility and visibility, should be particularly emphasized in future planning of pedestrian-friendly GBSs. Pedestrians from the central districts of Guangzhou city were most satisfied with the walking experience, in terms of accessing to, viewing, and cognizing the GBSs. ‘Yuexiu’, ‘Huadu’, and ‘Nansha’ districts were found as the key places where improved accessibility, visibility, and intelligibility were particularly needed to improve the GBS pedestrian-friendliness throughout the city. In summary, this study not only demonstrated a human-scale GBS evaluation framework for improving the human walking experience but also provided empirical evidence for building pedestrian-friendly green-blue spaces at the city scale.

Perceptual consequences of native and non-native clear speech.

Native talkers are able to enhance acoustic characteristics of their speech in a speaking style known as "clear speech," which is better understood by listeners than "plain speech." However, despite substantial research in the area of clear speech, it is less clear whether non-native talkers of various proficiency levels are able to adopt a clear speaking style and if so, whether this style has perceptual benefits for native listeners. In the present study, native English listeners evaluated plain and clear speech produced by three groups: native English talkers, non-native talkers with lower proficiency, and non-native talkers with higher proficiency. Listeners completed a transcription task (i.e., an objective measure of the speech intelligibility). We investigated intelligibility as a function of language background and proficiency and also investigated the acoustic modifications that are associated with these perceptual benefits. The results of the study suggest that both native and non-native talkers modulate their speech when asked to adopt a clear speaking style, but that the size of the acoustic modifications, as well as consequences of this speaking style for perception differ as a function of language background and language proficiency.

Preface

Due to recent pandemic, the 2021 International Conference on Smart Transportation, Energy and Power (STEP 2021) which was planned to be held in Sanya, China, was held virtually online during December 03-05, 2021. The decision to hold the virtual conference was made in compliance with many restrictions and regulations that were imposed by countries around the globe. Such restrictions were made to minimize the risk of people contracting or spreading the COVID-19 through physical contact. There were 110 individuals who attended this online conference, represented many countries including Singapore, Australia, United States, Germany, and China.The conference aimed to provide a platform for experts and scholars, engineers and technicians, R&D personnel engaged in intelligent transportation, environmental engineering, mechanical engineering, measurement and control technology and instrumentation science to share scientific research results and cutting-edge technologies, to understand academic development trends, to broaden research ideas, to strengthen academic research and discussion, and to promote cooperation in industrialization of academic achievements. We have invited experts, scholars, business people and other related personnel from domestic and foreign universities and research institutions to participate in the conference.List of Committee are available in the pdf.

Performance analysis of low complexity fully connected neural networks for monaural speech enhancement

We compare the run-time complexity of recent deep neural network (DNN) and non-DNN based monaural speech enhancement algorithms. Specifically, we consider fully connected, convolutional, and genetic-algorithm based DNNs and compare their performance to the image analysis technique, which is non-DNN based. It is demonstrated that for the same speech enhancement performance, a simple fully connected DNN has the lowest run-time computational complexity in terms of floating-point operations and execution time on a standard laptop. The objective indices used for the evaluation of the speech enhancement performance are the perceptual evaluation of speech quality and short-time objective intelligibility measures. In addition, the subjective intelligibility measures involved in the experiment are the modified rhyme test and the mean opinion score. Both stationary and non-stationary noise in addition to interfering speech is considered.

Study on Intelligent Construction Optimization Measures of Building Electrical Engineering

Study on Intelligent Construction Optimization Measures of Building Electrical Engineering

Ultrasonic Doppler Based Silent Speech Interface Using Perceptual Distance

Moderate performance in terms of intelligibility and naturalness can be obtained using previously established silent speech interface (SSI) methods. Nevertheless, a common problem associated with SSI has involved deficiencies in estimating the spectrum details, which results in synthesized speech signals that are rough, harsh, and unclear. In this study, harmonic enhancement (HE), was used during postprocessing to alleviate this problem by emphasizing the spectral fine structure of speech signals. To improve the subjective quality of synthesized speech, the difference between synthesized and actual speech was established by calculating the distance in the perceptual domains instead of using the conventional mean square error (MSE). Two deep neural networks (DNNs) were employed to separately estimate the speech spectra and the filter coefficients of HE, connected in a cascading manner. The DNNs were trained to incrementally and iteratively minimize both the MSE and the perceptual distance (PD). A feasibility test showed that the perceptual evaluation of speech quality (PESQ) and the short-time objective intelligibility measure (STOI) were improved by 17.8 and 2.9%, respectively, compared with previous methods. Subjective listening tests revealed that the proposed method yielded perceptually preferred results compared with that of the conventional MSE-based method.

Picture Description in the Assessment of Connected Speech Intelligibility in Parkinson’s Disease: A Pilot Study

Introduction: Assessment of intelligibility in dysarthria tends to rely on oral reading of sentences or words. However, self-generated utterances are closer to a client's natural speech. This study investigated how transcription of utterances elicited by picture description can be used in the assessment of intelligibility in speakers with Parkinson’s disease. Methods: Speech samples from eleven speakers with Parkinson’s disease and six neurologically healthy persons were audio-recorded. Forty-two naive listeners completed transcriptions of self-generated sentences from a picture description task and orally read sentences from the Swedish Test of Intelligibility, as well as scaled ratings of narrative speech samples. Results: Intelligibility was higher in orally read than self-generated sentences and higher for content words than for the whole sentence in self-generated sentences for most of the speakers, although these within-group differences were not statistically significant at the group level. Adding contextual leads for the listeners increased intelligibility in self-generated utterances significantly but with individual variation. Although correlations between the intelligibility measures were at least moderate or strong, there was a considerable inter- and intra-speaker variability in intelligibility scores between tasks for the speakers with Parkinson’s disease, indicating individual variation of factors that impact intelligibility. Intelligibility scores from neurologically healthy speakers were generally high across tasks with no significant differences between the conditions. Conclusion: Within-speaker variability supports literature recommendations to use multiple methods and tasks when assessing intelligibility. The inclusion of transcription of self-generated utterances elicited by picture description to the intelligibility assessment has the potential to provide additional information to assessment methods based on oral reading of pre-scripted sentences and to inform the planning of interventions.

Intelligent Measurement and Monitoring of Carbon Emissions for 5G Shared Smart Logistics

With the upgrading of logistics demand and the innovation of modern information technology, the smart logistics platform integrates advanced concepts, technologies, and management methods, maximizes the integration of logistics resources and circulation channels, and effectively improves the efficiency of logistics transactions, but its energy consumption problem is particularly prominent. The study of intelligent measurement and monitoring of carbon emissions in smart logistics is of great value to reduce energy consumption, reduce carbon emissions in buildings, and improve the environment. In this paper, by comparing and analyzing the accounting standards of carbon emissions and their calculation methods, the carbon emission factor method is selected as the method to study the carbon emissions of the smart logistics process in this paper. The working principle of each key storage technology in the smart logistics process is analyzed to find out the equipment factors affecting the carbon emission of each storage technology in the smart logistics process, and the carbon emission calculation model of each key storage technology is established separately by using the carbon emission factor method. Meanwhile, according to the development history of energy consumption assessment, the assessment process of different stages from logistics storage energy consumption assessment to smart logistics energy consumption assessment is analyzed, and based on this, a carbon emission energy consumption assessment framework based on 5G shared smart logistics is constructed. This paper applies the supply chain idea to define the smart logistics supply chain, constructs a conceptual model of the smart logistics supply chain considering carbon emissions, and at the same time combines the characteristics of the smart logistics supply chain to analyze the correlation between the carbon emissions of the smart logistics supply chain and the related social, environmental, and economic systems.

An intelligent measurement method of the resonant frequency of ultrasonic scalpel transducers based on PSO-BP neural network

In the laboratory, using traditional methods to measure the resonant frequency of transducers is inefficient and costly. For this, in this study, the feature variables determining the resonant frequency of transducer was firstly analyzed with the equivalent circuit method. Based on the input–output mapping function of back propagation (BP) neural network, the nonlinear relationship model between feature variables and the resonant frequency was established. Then, particle swarm optimization (PSO) was used to optimize the initial weight and threshold of BP neural network to obtain the best parameter combination, thereby improving the output accuracy of BP neural network. The experimental data showed that it is effective to measure the resonant frequency of the transducer by PSO-BP neural network, and the measurement error was 1 Hz. Compared to traditional measurement method, the intelligent method has the advantages of low cost, high efficiency, fast response speed, and strong robustness.

Intelligent Measurement and Monitoring by Integrating Fieldbus and Robotic Arm

In response to the rapid global development of industrial technologies and the resulting rapid growth in the production lines of industry and manufacturing, traditional manufacturing must become intelligent and automated, and undergo the process of informatization. Machines can reduce human errors, replace manpower, and even work better than manpower in certain aspects. Over recent years, the Internet of Things (IoT) has been applied in a wide range of fields. IoT helps control all the production information of factories in real time, and accordingly, reduces labor cost, improves quality, efficiently handles exceptions, and swiftly meets market demands, and how to achieve such a goal is a focus of current studies. This study proposes an IoT-based communication system that can monitor the operations of robotic arms and return data to users through a system interface in real time. This communication system is based on Fieldbus as the system architecture, and utilizes HIWIN Company (HI-tech WINner) Robot System Software (HRSS) and an electric gripper’s intelligent measurement function to collect and analyze data. On this basis, this study efficiently determines whether the quality of products meets the standard, and uses the Weintek human-machine interface to remotely adjust robotic arms to achieve intelligent monitoring.

ИНТЕЛЛЕКТУАЛЬНЫЕ ИЗМЕРЕНИЯ В ЭПОХУ ЦИФРОВИЗАЦИИ: НОВЫЕ ВОЗМОЖНОСТИ И ОПЫТ ИСПОЛЬЗОВАНИЯ

The broad digitalization of the company's activities is focused on solving complex tasks of monitoring and managing production and socioeconomic systems. The functioning of such systems takes place in conditions of significant uncertainty of information, active and unpredictable influence of the external environment, dynamism of situations.Therefore, for the effective implementation of digitalization systems, special methodologies, technologies and systems focused on such situations are required. First of all, this concerns methods and means of obtaining measurement information. The article discusses a new direction of modern measurement theory, which has been called intelligent measurements. A comparison of classical and intellectual measurement methodologies is given. It is shown that classical measurements are a special case of intelligent measurements. The advantages of using this type of measurement are indicated both for the theory and practice of measurements, and for solving problems of artificial intelligence. Examples of the use of Bayesian measurement methodology, technology and practice for solving various applied problems are given.

A Two-Stage Deep Neuroevolutionary Technique for Self-Adaptive Speech Enhancement

This paper presents a novel self-adaptive approach for speech enhancement in the context of highly nonstationary noise. A two-stage deep neuroevolutionary technique for speech enhancement is proposed. The first stage is composed of a deep neural network (DNN) method for speech enhancement. Two DNN methods were tested at this stage, namely, both a deep complex convolution recurrent network (DCCRN) and a residual long short-term memory neural network (ResLSTM). The ResLSTM method was combined with a minimum mean-square error method to perform a preliminary enhancement. The ResLSTM network is used as an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a priori</i> signal-to-noise ratio (SNR) estimator. The second stage implements a self-adaptive multiband spectral subtraction enhancement method using tuning optimization based on a genetic algorithm. The proposed two-stage technique is evaluated using objective measures of speech quality and intelligibility. The experiments are carried out using the NOIZEUS noisy speech corpus using conditions of real-world stationary, colored, and nonstationary noise sources at multiple SNR levels. These experiments demonstrate the advantage of building a cooperative approach using evolutionary and deep learning-based techniques that are capable of achieving robust speech enhancement in adverse conditions. Indeed, the experimental tests show that the proposed two-stage technique outperformed a baseline implementation using a state-of-the-art deep learning approach by an average 13% and 6% improvement for six noise conditions at a −5 dB and a 0 dB input SNR, respectively.