فیلترها/جستجو در نتایج    

فیلترها

سال

بانک‌ها



گروه تخصصی











متن کامل


اطلاعات دوره: 
  • سال: 

    2019
  • دوره: 

    7
  • شماره: 

    1
  • صفحات: 

    74-87
تعامل: 
  • استنادات: 

    0
  • بازدید: 

    221
  • دانلود: 

    0
چکیده: 

This paper proposes two algorithms for Voice Activity Detection (VAD) based on sparse Representation in Spectro-Temporal Domain. Spectral-Temporal components which, in addition to the frequency and time dimensions, have two other dimensions of the scale and rate. Scale means spectral modulation and the rate means Temporal modulation. On the other hand, using sparse Representation in learning dictionaries of speech and noise, separate the speech and noise segment to be better separated. The first algorithm was made using two-dimensional STRF (Spectro-Temporal Response Field) space based on sparse Representation. Dictionaries with different atomic sizes and two dictionary learning methods: NMF (non-negative matrix factorization) and the K-SVD (k-means clustering method), were investigated in this approach. This algorithm revealed good results at high SNRs (signal-to-noise ratio). The second algorithm, whose approach is more complicated, suggests a speech detector using the sparse Representation in four-dimensional STRF space. Due to the large volume of STRF's four-dimensional space, this space was divided into cubes, with dictionaries made for each cube separately by NMF (non-negative matrix factorization) learning algorithm. Simulation results were presented to illustrate the effectiveness of our new VAD algorithms. The results revealed that the achieved performance was 90. 11% and 91. 75% under-5 dB SNR in white and car noise respectively, outperforming most of the state-of-the-art VAD algorithms.

شاخص‌های تعامل:   مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

بازدید 221

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesدانلود 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesاستناد 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesمرجع 0
نویسندگان: 

Esfandian N.

اطلاعات دوره: 
  • سال: 

    2020
  • دوره: 

    33
  • شماره: 

    1 (TRANSACTIONS A: Basics)
  • صفحات: 

    105-111
تعامل: 
  • استنادات: 

    0
  • بازدید: 

    179
  • دانلود: 

    0
چکیده: 

This article presents a new feature extraction technique based on the Temporal tracking of clusters in Spectro-Temporal features space. In the proposed method, auditory cortical outputs were clustered. The attributes of speech clusters were extracted as secondary features. However, the shape and position of speech clusters change during the time. The clusters Temporally tracked and Temporal tracking parameters were considered in secondary features. The new architecture was proposed for phoneme classification by a combining classifier using both tracked and energy-based features. Clustered based Spectro-Temporal features vectors were used for the classification of several subsets of TIMIT database phonemes. The results show that the phoneme classification rate was improved Using tracked Spectro-Temporal features. The results were improved to 78. 9% on voiced plosives classification which was relatively 3. 3% higher than the results of non-tracked Spectro-Temporal feature vectors. The results on other subsets of phonemes showed good improvement in classification rate too.

شاخص‌های تعامل:   مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

بازدید 179

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesدانلود 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesاستناد 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesمرجع 0
نویسندگان: 

Esfandian N. | Hosseinpour K.

اطلاعات دوره: 
  • سال: 

    2021
  • دوره: 

    34
  • شماره: 

    2
  • صفحات: 

    452-457
تعامل: 
  • استنادات: 

    0
  • بازدید: 

    16
  • دانلود: 

    0
چکیده: 

In this paper, a new feature extraction method is presented based on Spectro-Temporal Representation of speech signal for phoneme classification. In the proposed method, an artificial neural network approach is used to cluster Spectro-Temporal Domain. Self-organizing map artificial neural network (SOM) was applied to clustering of features space. Scale, rate and frequency were used as spatial information of each point and the magnitude component was used as similarity attribute in clustering algorithm. Three mechanisms were considered to select attributes in Spectro-Temporal features space. Spatial information of clusters, the magnitude component of samples in Spectro-Temporal Domain and the average of the amplitude components of each cluster points were considered as secondary features. The proposed features vectors were used for phonemes classification. The results demonstrate that a significant improvement is obtained in classification rate of different sets of phonemes in comparison to previous clustering-based methods. The obtained results of new features indicate the system error is compensated in all vowels and consonants subsets in compare to weighted K-means clustering.

شاخص‌های تعامل:   مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

بازدید 16

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesدانلود 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesاستناد 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesمرجع 0
مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources
نویسندگان: 

مومنی مریم

اطلاعات دوره: 
  • سال: 

    1398
  • دوره: 

    10
  • شماره: 

    2
  • صفحات: 

    59-70
تعامل: 
  • استنادات: 

    0
  • بازدید: 

    938
  • دانلود: 

    466
چکیده: 

امروزه تشخیص احساس از گفتار در مواردی که ارتباط متقابل انسان و ماشین وجود دارد مورد توجه قرار گرفته است. با وجود تلاش های زیاد در این زمینه همچنان فاصله زیادی بین احساسات طبیعی انسان و درک کامپیوتر نسبت به آن وجود دارد. دلیل اصلی این موضوع نیز عدم توانایی رایانه در درک احساس کاربر است. هدف از این مقاله، طراحی یک سیستم تشخیص احساس از گفتار بر روی پایگاه داده گفتار احساسی فارسی که شامل 5 احساس خوشحالی، تنفر، ترس، ناراحتی و عصبانیت است. در این مقاله، پس از استخراج داده های چهار بعدی مقیاس، نرخ (سرعت)، زمان و فرکانس گفتار به کمک سیستم مدل شنوایی گوش انسان، داده دو بعدی مقیاس و فرکانس حاصل شد که بیشینه مقدار این داده ها به عنوان بردار ویژگی استفاده شد. در نهایت با استفاده از طبقه بند ماشین بردار پشتیبان احساس این پایگاه داده طبقه بندی شدند. نتایج آزمایش ها نشان می دهد الگوریتم پیشنهادی عملکرد قابل قبولی در مقایسه با سیستم های تشخیص خودکار احساسات از گفتار در زبان فارسی ارائه می دهد.

شاخص‌های تعامل:   مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

بازدید 938

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesدانلود 466 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesاستناد 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesمرجع 0
اطلاعات دوره: 
  • سال: 

    2022
  • دوره: 

    20
  • شماره: 

    2
  • صفحات: 

    185-198
تعامل: 
  • استنادات: 

    0
  • بازدید: 

    52
  • دانلود: 

    0
چکیده: 

Objectives: Auditory processing disorder (APD) is due to the deficits in perceptual processing of acoustic information in the auditory system, characterized by poor speech perception of noise, regardless of normal hearing. The variability in speech function of APD children can be partly explained by changes in the encoding of Spectro-Temporal modulations (STMs) which have been overlooked, despite their significance. Given that enhancing STM sensitivity and its processing can be an appropriate way to improve the listener’, s ability to retrieve and integrate speech segments covered by noise, we decided to evaluate the effects of STM-based auditory training on speech perception in noise and the reliability of this training in children with APD. Methods: Thirty-five children with APD (8-12 years old) were randomly divided into the training (n=17) and control groups (n=18) to evaluate the effectiveness and reliability of STM training on speech in noise perception. The intervention group was trained to detect STM by 120 trials every day for ten days. The STM detection thresholds and speech perception in noise were evaluated before and immediately after the finalization of formal training sessions in both groups. To address the training reliability, the tests were repeated one month after practice in the training group. Results: Following the completion of STM auditory training, the trained APD children improved notably in STM detection tasks and speech in noise tests (P<0. 05). The post-training progress of STM detection thresholds and consonant-vowel in the noise test was preserved for one month after training (P>0. 05), but the word in the noise test, especially in the right ear, was not retained (P<0. 05). Discussion: Auditory Spectro-Temporal modulation training can lead to better processing of STM modulation. Its effects can be generalized to higher-order processing, such as speech perception in noise. Auditory training based on STM processing enhancement can play an essential role in improving speech comprehension in the noise abilities of children with APD.

شاخص‌های تعامل:   مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

بازدید 52

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesدانلود 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesاستناد 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesمرجع 0
اطلاعات دوره: 
  • سال: 

    2010
  • دوره: 

    23
  • شماره: 

    2 (TRANSACTIONS B: APPLICATIONS)
  • صفحات: 

    119-130
تعامل: 
  • استنادات: 

    0
  • بازدید: 

    229
  • دانلود: 

    0
چکیده: 

Motion-JPEG is a common video format for compression of motion images with high quality using JPEG standard for each frame of the video. During transmission through a noisy channel some blocks of data are lost or corrupted, and the quality of decompression frames decreased. In this paper, for reconstruction of these blocks, several Temporal-Domain, spatial-Domain, and frequency-Domain error concealment methods are investigated. Then a novel method is proposed for recovery of channel errors with a mixture of Temporal-Domain and frequency-Domain error concealment methods. To reconstruct the missed blocks in the proposed novel method, when two successive frames are similar, a proposed two phase block matching algorithm is performed in Temporal-Domain. When two successive frames are different, our proposed method reconstructs the missed block by the estimation of DC and AC coefficient, in frequency-Domain. The proposed method and the other similar methods are simulated for different noise and quality factors. The results of quality measurements are indicated that in all tested video sequences, the proposed method shows higher quality in reconstruction of missed blocks.

شاخص‌های تعامل:   مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

بازدید 229

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesدانلود 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesاستناد 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesمرجع 0
مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources
اطلاعات دوره: 
  • سال: 

    1403
  • دوره: 

    12
  • شماره: 

    3
  • صفحات: 

    101-119
تعامل: 
  • استنادات: 

    0
  • بازدید: 

    40
  • دانلود: 

    4
چکیده: 

استعاره به منزلة فرایندی شناختی، مقوله های ذهنی را در حوزه ای ملموس، عینیت می بخشد و امکان مطالعۀ ساختار ذهنی انسان را فراهم می کند. هدف پژوهش حاضر، بررسی کلان استعارۀ «ازدواج شکار است» و بازنمایی منفی آن در حوزۀ عشق (همسرگزینی و ازدواج) براساس نظریۀ استعارۀ مفهومی و زبان شناسی فرهنگی (پالمر، 1996؛ شریفیان، 1392) است. با استناد به پیکرۀ دادگان زبان فارسی و ضرب المثل های فارسی، استعارۀ «ازدواج شکار است» و بازنمایی منفی آن در این حوزه را بررسی کردیم. سه خرده استعارۀ «همسرگزینی و ازدواج، شکار است»، «همسرگزینی و ازدواج، سرقت است» و «همسرگزینی و ازدواج، اسارت است» به دست آمد. این خرده استعاره ها در قالب استعاره های زبانی «شکارکردن»، «به چنگ آوردن»، «عقل و هوش ربودن»، «قاپ دزدیدن»، «قرزدن»، «تورکردن»، «گرفتارکردن»، «به دام انداختن»، «اسیرکردن»، «به بندگی گرفتن» و «درکمندکشیدن» با بار عاطفی منفی دربارة مرد یا زن به کار می روند. یافته ها نشان داد که در زبان فارسی بازنمایی استعاری منفی حوزۀ شکار درزمینۀ «همسرگزینی و ازدواج» درمورد زن و مرد مشاهده می شود. گاه زن صیدی ارزشمند و طعمۀ مرد است و گاه نقش صیاد را پیدا می کند و مرد به عنوان طعمۀ شکارچیِ زن معرفی می شود. نتایج نشان داد که عواملی مانند جنسیت، تعهد نسبت به زندگی مشترک و تناسب زوجین به لحاظ ظاهری، اقتصادی، سن، تجرد و اخلاق مداری بر بازنمایی های استعاری تأثیرگذار هستند.

شاخص‌های تعامل:   مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

بازدید 40

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesدانلود 4 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesاستناد 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesمرجع 0
اطلاعات دوره: 
  • سال: 

    1402
  • دوره: 

    13
  • شماره: 

    3
  • صفحات: 

    105-121
تعامل: 
  • استنادات: 

    0
  • بازدید: 

    171
  • دانلود: 

    14
چکیده: 

A B S T R A C T Temperature is one of the climate elements that has fluctuated a lot over time. When these fluctuations increase and decrease more than normal and are placed in the upper and lower regions of the statistical distribution, if continued, it can lead to the creation of heating and cooling waves. The purpose of this study is to analyze the Temporal and spatial changes in heating and cooling waves in Iran during a period of 50 years. For this purpose, the temperature of 663 synoptic stations from 1962 to 2004 was obtained from the Esfazari database. Then, in order to complete this database, the daily temperature from 2004 to 2011 was obtained from the Meteorological Organization of the country and added to the aforementioned database. In order to perform calculations and draw maps, Matlab, grads and Surfer software have been used. The results of this study showed that the index of cooling waves and heating waves, while having a direct effect on each other, had an increasing trend in most of the area of Iran. The statistical distribution of the index of cooling waves is more heterogeneous than that of the index of heating waves. So that the spatial variation coefficient for cold waves is 84.22%. Also, the index of cooling waves has more spatial variability. The highest common diffraction of the index of heating and cooling waves has been seen in the northwest, east and along the Zagros mountains. Analysis of the indexes trends show that heat waves have intensified in 65.8% of Iran and the intensity of cold waves has decreased in 48.5% of Iran Extended Abstract Introduction Temperature is one of the major climatic variables, which it has a direct impact on different aspects of human life. It plays an essential role in the growth of crops and is considered a key driver of the biological system(Reicosky et al, 1988). It is associated with several types of extremes, for example, heat and cold waves which caused human societies maximum damage. Past occurrences of heat waves hitherto had significant impacts on several aspects of society. Have increased Mortality and morbidity. Ecosystems can be affected, as well as increased pressure on infrastructures that support society, such as water, transportation, and energy(Dewce, 2016). The long-term change of extreme temperatures has a key role in climatic change. The form of statistical distribution and the variability of mean values and also extreme event indicate a change in the region. It can be a small relative change in the mean as a result of a large change in the probability of extreme occurrence. Also, the variation in temperature data variance is significantly more important than the mean, for assessing the extreme occurrence of climate(Toreti and Desiato, 2008). The average surface temperature has increased the world between 0.56 and 0.92 ° C over the past 100 years(IPCC, 2007). Meanwhile, it was in the Middle East, the average daily temperature increased by 0.4-0.5 ° C in decades(Kostopoulou et al, 2014; Tanarhte et al, 2012). Considering that not many studies have been done in the field of spatio-Temporal Variations of the heating and cooling waves thresholds in Iran, in this study, the spatio-Temporal Variations of the heating and cooling waves thresholds in Iran during 50 years were examined and analyzed.   Methodology The daily temperature from the beginning of the year 21/03/1967 to 19/05/2005 was obtained from the Esfazari database prepared by Dr. Masoudian at the University of Isfahan. In order to increase the time resolution of the mentioned database, the daily temperature of observations from 05/21/2005 to 05/12/2012 has been added to the mentioned database using the same method, and the exact spatial resolution (15 x 15 km) is used as a database. Threshold indices of heating waves are the average numbers between the 95th and 99th percentiles, that is, the extreme hot threshold to the limit of excessively extreme hot. For extreme cool, from the 5th percentile down to zero is used. Of course, a condition was added to these thresholds, which is that these thresholds must be repeated two days in a row. These thresholds were extracted for each day in the 50 years of the study period and used as the original database. In order to analyze the relationship between cooling and heating waves, Pearson's correlation coefficient was used and regression was used to analyze the trend.   Results and discussion The average of cold waves was 5.26 ° C and for the heat waves is 30.20° C. Generally, if the temperature is upper or lower than this threshold, it is considered as hot or cold temperatures. A comparison of the median, mode, and average of cold waves with heat waves shows that the distribution is more heterogeneous for cold waves and its CV is 84.22%. In southern Iran, the average threshold heat waves are higher. This situation can be caused by the effects of subtropical high-pressure radiation, low latitude, and proximity to the sea. Though the threshold is higher in these areas, fewer fluctuations and changes are seen in the area. Heights moderate the temperature so they pose a minimum threshold for heat waves i.e. an iso-threshold of 25 ° C is consistent along the Zagros mountain chains, but in the west and east of Zagros Mountains, the threshold of heat waves is increased. Heat waves have increased in most areas of the country. So nearly 85 percent of the Iran has been an increasing trend, of which 65.8 percent is statistically significant at the 95% confidence level. Still, more areas of the country (60 percent) have a trend between 0.00828 and 0.00161. As can be seen, only 15% of the land area (including the southwest and northwest of the Country) had decreased heat waves. Cold waves, in most parts of the country, have a Positive Trend. However, about 25 percent of the study area's cold waves have a negative trend. they are located in areas higher than Latitude 30°. The largest decline of the wave's trend along the country is highlands. Nowadays, most of the country, has a trend between 0.01494 and 0.00828 ° C, respectively. Conclusion Common changes and effects of heat and cold waves had a direct relationship in many parts of the country. It is remarkable common variance in the East reached 55 percent, according to statistical significance. In some areas of the northwest and southwest, which have been impressive heights, the common variance is 40 percent. This common variance in mountains area has been high values. Investigation of heat waves trend shows that 65.8% of Iran significant positive trend and 7.1% significant negative trend. Also, the cold waves trend has indicated a 48.5% significant positive trend and a 10.8% significant negative trend. Climate change and global warming have changed the frequency and severity of temperature extremes. The present study, by examining the number of warm waves, concluded that the warm waves have increased in magnitude in 65.8% of the Iran zone. Also, the study of the cold waves trend showed that 48.5 percent of Iran had a positive trend, which means that the amount of temperature in the cold waves increased In other words, the severity of the cold has been reduced And only 10.8 percent of Iran had a negative cold wave trend And it shows the intensity of these waves is reduced.   Funding There is no funding support.   Authors’ Contribution The authors contributed equally to the conceptualization and writing of the article. All of the authors approthe contenttent of the manuscript and agreed on all aspects of the work declaration of competing interest none.   Conflict of Interest The authors declared no conflict of interest.   Acknowledgments  We are grateful to all the scientific consultants of this paper.

شاخص‌های تعامل:   مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

بازدید 171

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesدانلود 14 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesاستناد 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesمرجع 0
نویسندگان: 

اطلاعات دوره: 
  • سال: 

    2022
  • دوره: 

    126
  • شماره: 

    -
  • صفحات: 

    0-0
تعامل: 
  • استنادات: 

    1
  • بازدید: 

    18
  • دانلود: 

    0
کلیدواژه: 
چکیده: 

شاخص‌های تعامل:   مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

بازدید 18

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesدانلود 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesاستناد 1 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesمرجع 0
اطلاعات دوره: 
  • سال: 

    2019
  • دوره: 

    7
  • شماره: 

    3
  • صفحات: 

    48-67
تعامل: 
  • استنادات: 

    0
  • بازدید: 

    99
  • دانلود: 

    0
چکیده: 

Assessment of pavement distresses is one of the important parts of pavement management systems to adopt the most effective road maintenance strategy. In the last decade, extensive studies have been done to develop automated systems for pavement distress processing based on machine vision techniques. One of the most important structural components of computer vision is the feature extraction method. In most of the application areas of image processing, textural features provide more efficient information of image regions properties than other characteristics. In this research, three different algorithms were used to extract the feature vector and statistically analyzing the texture of six various types of asphalt pavement surface distresses. The first algorithm is based on the extraction of images second-order textural statistics utilizing gray level co-occurrence matrix in spatial Domain. In second and third algorithms, the second-order descriptors of images local binary patterns were extracted in spatial and wavelet transform Domain, respectively. The classification of the distress images based on a combination of K-nearest neighbor method and Mahalanobis distance, indicates that two stages arranging of the gray levels of the distress images edges by applying wavelet transform and local binary pattern (third algorithm) had a superior result in comparison with other algorithms in texture recognition and separation of pavement distresses. Classification performance accuracy of the distress images based on first, second and third feature extraction algorithms is 61%, 75% and 97%, respectively.

شاخص‌های تعامل:   مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

بازدید 99

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesدانلود 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesاستناد 0 مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resourcesمرجع 0
litScript
telegram sharing button
whatsapp sharing button
linkedin sharing button
twitter sharing button
email sharing button
email sharing button
email sharing button
sharethis sharing button