Search

In this paper, a simple and efficient no-reference image quality assessment technique based on polynomial coefficient and reduced Gerschgorin circle is presented. The dominant features and dynamics of the test images are captured using the polynomial coefficient. Moreover, the image focus measure is modeled using the concept of reduced Gerschgorin's higher circle bound. The presented image focus measure is tested on different synthetic images datasets such as LIVE, TID2008, CSIQ, Cornel and IVC. Further, the proposed approach is also examined on real-time images captured by the camera in different conditions. It is observed that the proposed approach demonstrates important properties of focus measures such as unimodality and contrast invariance. Moreover, the presented technique is robust under the different varying noisy conditions. [ABSTRACT FROM AUTHOR]

In this paper, a simple and efficient no-reference image quality assessment metric is proposed. It is based on the concept of polynomial coefficients, power of companion matrix, and Gerschgorin circles bound. The polynomial coefficient-based companion matrix captures the main features and dynamics of an image. Moreover, the Gerschgorin circles bound is used to define the focus metric. The proposed focus metric is tested on various real as well as synthetic image data sets. It is observed that the presented metric is unimodal to noise and invariant to the contrast changes that occur due to the variation in illumination effect. Moreover, it is robust under the varying salt-and-pepper and Gaussian noise. The performance of the proposed focus metric is also compared with the various existing focus metrics. [ABSTRACT FROM AUTHOR]

As a fundamental research problem, blind image quality assessment (BIQA) has attracted increasing interest in recent years. Although great progress has been made, BIQA still remains a challenge. To better understand the research progress and challenges in this field, we review BIQA methods in this paper. First, we introduce the BIQA problem definition and related methods. Second, we provide a detailed review of the existing BIQA methods in terms of representative hand-crafted features, learning-based features and quality regressors for two-stage methods, as well as one-stage DNN models with various architectures. Moreover, we also present and analyze the performance of competing BIQA methods on six public IQA datasets. Finally, we conclude our paper with possible future research directions based on a performance analysis of the BIQA methods. This review will provide valuable references for researchers interested in the BIQA problem. [ABSTRACT FROM AUTHOR]

• We proposed a deep-learning-based model for perceptual speech quality assessment. • We presented an application of this model as perceptual regularization for speech enhancement. • Experimental results show significant improvement in the enhanced speech naturalness. Many speech enhancement methods require perceptual quality metrics for evaluation. The "holy grail" of perceptual speech quality assessment is human subjective ratings, known as the mean opinion score. However, acquiring human ratings is time-consuming, laborious, and expensive. Existing objective quality metrics, on the other hand, are efficient and easy to compute but do not correlate well with human ratings. In this paper, we propose a relatively lightweight deep-learning-based model to predict the human ratings of speech signals. Since it is differentiable, it can be easily employed as a perceptual regularization to improve existing deep-learning-based speech enhancement methods. Experimental results demonstrate that the predictions of our proposed model correlate well with human judgments. We present application in speech enhancement and show that, interestingly, while there is a degradation in performance in terms of traditional objective metrics, there is a significant improvement in the perceptual quality and the naturalness of the enhanced speech. [ABSTRACT FROM AUTHOR]

In order to solve the problem of poor consistency between the traditional super-resolution image quality assessment (SRIQA） index and human subjective perception, this paper presents a reference free super-resolution image quality evaluation method by using multi-layer perceptron(MLP). This method used the pre trained VGG16 network to extract the perceptual quality features of the super-resolution image, and established the regression model between the perceptual quality features of the super-resolution image and the corresponding subjective quality score through MLP. Experimental results show that the Pearson linear correlation coefficient (PLCC) and Spearman rank order correlation coefficient (SROCC) of the proposed algorithm on the public super-resolution image data set exceed 0.95, which is significantly superior to other existing image quality evaluation methods, and has higher consistency with human subjective perception. [ABSTRACT FROM AUTHOR]

Image quality markedly affects the evaluation of images, and its control is crucial in studies using natural visual scenes as stimuli. Various image elements, such as sharpness or naturalness, can impact how observers view images and, more directly, how they evaluate their quality. To gain a better understanding of the types of interactions between these various elements, we conducted a study with a large set of images with multiple overlapping distortions, covering a wide range of quality variation. Observers assigned a quality rating of the images on a 0-10 scale and gave a verbal description explaining the elements on which their rating was based. A regression model predicting image quality ratings using 68 attributes uncovered the link between verbal descriptions and quality ratings and the importance of the image quality rating for each of the 68 image attributes. Brightness, naturalness, and good colors seem to be related to the highest image quality preference. However, the most important elements for predicting good image quality were related to image fidelity such as graininess and sharpness. This indicates that a certain level of image fidelity must be achieved before more subjective associations with, for instance, naturalness can emerge. Of the attributes, 72% had a negative impact on the preference judgment. This negative bias may be due to the fact that there are more ways that observers can perceive an image to fail than to excel when they are asked to evaluate image quality. [ABSTRACT FROM AUTHOR]

Nowadays, video streaming has become one of the most dominant services due to increasing interest in watching online television programs and video-on-demand activities. Providing this service requires high quality, high speed and high-capacity network infrastructures. In this work, we propose a data-drivenbased fuzzy logic inference algorithm for quality of experience (QoE) modeling of video streaming services in Addis Ababa City LTE network. The proposed fuzzy logic inference system model is used to measure the user perception from the key quality of indicator (KQI) parameters. The model is essential to replace conventional subjective measurement techniques that are costly and inefficient. In addition, the proposed fuzzy logic inference system model is helpful for business decision making, network planning and optimization activities. To analyze the performance of the proposed model, we consider main KQI parameters such as video streaming start success rate, video streaming start delay, video streaming play disconnection rate, video streaming stall frequency and video streaming stalled time rate. We perform numerical simulation to analyze the proposed model and to validate the impacts of main KQI parameters on the quality of experience in LTE video streaming services. The simulation results show that video streaming stall frequency and video streaming start delay rate play a major impact on user perception by 33% and 25%, respectively. Besides, validation of the results shows that the proposed fuzzy logic inference system model is accurate, consistent and linear compared to currently existing models. [ABSTRACT FROM AUTHOR]

The release of WaveNet and Tacotron has forever transformed the speech synthesis landscape. Thanks to these game-changing innovations, the quality of synthetic speech has reached unprecedented levels. However, to measure this leap in quality, an overwhelming majority of studies still rely on the Absolute Category Rating (ACR) protocol and compare systems using its output; the Mean Opinion Score (MOS). This protocol is not without controversy, and as the current state-of-the-art synthesis systems now produce outputs remarkably close to human speech, it is now vital to determine how reliable this score is. To do so, we conducted a series of four experiments replicating and following the 2013 edition of the Blizzard Challenge. With these experiments, we asked four questions about the MOS: How stable is the MOS of a system across time? How do the scores of lower quality systems influence the MOS of higher quality systems? How does the introduction of modern technologies influence the scores of past systems? How does the MOS of modern technologies evolve in isolation? The results of our experiments are manyfold. Firstly, we verify the superiority of modern technologies in comparison to historical synthesis. Then, we show that despite its origin as an absolute category rating, MOS is a relative score. While minimal variations are observed during the replication of the 2013-EH2 task, these variations can still lead to different conclusions for the intermediate systems. Our experiments also illustrate the sensitivity of MOS to the presence/absence of lower and higher anchors. Overall, our experiments suggest that we may have reached the end of a cul-de-sac by only evaluating the overall quality with MOS. We must embark on a new road and develop different evaluation protocols better suited to the analysis of modern speech synthesis technologies. [ABSTRACT FROM AUTHOR]

In a recent scenario of advancement in the upcoming next-generation system reconstructed speech(voice) signal by the side of the receiver side found stiffened, barely audible, and slim because of limited bandwidth of 300-3.4 kHz. To get back the genuineness of speech(voice) signal, narrow band speech encoders must be upgraded to wide band encoders supporting 50-kHz bandwidth. The extensive period has been left for advancement from N.B. to fully W.B.'s well-suited systems. The terminal and network must be altered to make the N.B. system compatible with the W.B. system. During that span novel technique has been urbanized to widen the N.B. bandwidth of speech (voice) signal at handset end (receiver) for humanizing final speech quality. The technique of attaining the original W.B. signal from a band-limited N.B. speech(voice) signal without actually transmitting the W.B. signal is called bandwidth extension. The same concept applies to attain super wideband from the W.B. signal. B.W.E. based on sinusoidal transform coding, linear prediction, non-linear device is giving good results compared to spectral folding/spectral translation approaches employed by various researchers. In the modern scenario of advancement in technology, various coding algorithms have been urbanized for S.W.B. and F.B. to obtain the full benefit of advancement in available telecommunications bandwidth, predominantly for the internet. In the proposed method based on source filter model fundamental thought adopted for the B. W.E. are the separate extension of the spectral envelope and the residual signal. Each part is processed separately through different speech enrichment procedure to get the highband component and added to the resampled and delayed version of the signal to acquire the final extended output which is compared through intelligibly(subjective) and quality(objective) perspective and results are compared with baseline algorithm and next-generation super wide band coder algorithms to prove that obtained results are comparable with both algorithms. Algebraic evaluation for getting missing high band components from the original W.B. signal is not needed and method tremendously well-organized and commence only minor time interval or delay.. [ABSTRACT FROM AUTHOR]

A number of full reference and reduced reference methods have been proposed in order to estimate the perceived visual quality of 3D meshes. However, in most practical situations, there is a limited access to the information related to the reference and the distortion type. For these reasons, the development of a no-reference mesh visual quality (MVQ) approach is a critical issue, and more emphasis needs to be devoted to blind methods. In this work, we propose a no-reference convolutional neural network (CNN) framework to estimate the perceived visual quality of 3D meshes. The method is called SCNN-BMQA (3D visual saliency and CNN for blind mesh quality assessment). The main contribution is the usage of a CNN and 3D visual saliency to estimate the perceived visual quality of distorted meshes. To do so, the CNN architecture is fed by small patches selected carefully according to their level of saliency. First, the visual saliency of the 3D mesh is computed. Afterward, we render 2D projections from the 3D mesh and its corresponding 3D saliency map. Then the obtained views are split into 2D small patches that pass through a saliency filter in order to select the most relevant patches. Finally, a CNN is used for the feature learning and the quality score estimation. Extensive experiments are conducted on four prominent MVQ assessment databases, including several tests to study the effect of the CNN parameters, the effect of visual saliency and comparison with existing methods. Results show that the trained CNN achieves good rates in terms of correlation with human judgment and outperforms the most effective state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Traditionally, random sensing matrices such as Gaussian are widely used in Compressed Sensing (CS). The higher computational complexity and non-structure of matrix make it inappropriate for practical use. Hence, we have projected the application of structural sensing matrices in CS. Since these matrices impose structure and hence easy to implement in hardware. In this paper, we have proposed optimization method based on structural sensing matrices and Grassmannian frame theory. These proposed sensing matrices are DCT–Grassmannian sensing matrix, Hadamard–Grassmannian sensing matrix, and Walsh–Hadamard Grassmannian sensing matrix, respectively. These sensing matrices are optimized for minimal mutual coherence based on shrinkage method; which further improves the signal recovery performance of speech signal. The result demonstrates that the performance of the proposed optimization method based on structural sensing matrices is improved compared to conventional Elad's method which employs the Gaussian sensing matrix. Furthermore, the result reveals that the proposed optimization method with Hadamard–Grassmannian sensing matrix yields better performance compared to conventional Elad's method. Finally, speech quality is evaluated using subjective MOS and objective measures such as LLR and WSS. The result exhibited that the proposed optimization method based on Hadamard–Grassmannian sensing matrix and DCT–Grassmannian sensing matrix exhibits the better MOS, LLR, and WSS performance indicating the good quality of speech. [ABSTRACT FROM AUTHOR]

In this study, the authors present results of a call testing campaign using voice over long term evolution (VoLTE) technology on the radio access network of the operator Telecom Italia mobile. The quality of the voice call is expressed by means of the mean opinion score (MOS). The electromagnetic propagation environment has been reproduced within a reverberation chamber, and its effect on MOS has been evaluated by varying the signal strength, i.e. the reference signal received power and the signal‐to‐interference noise ratio. The aim is to find a correlation between the radio propagation environment and the perceived quality of the speech. Regardless of the networks technology, voice quality could be impacted by several factors: traffic load of LTE evolved Node B, quality of service, radio pathloss, mutual radio interference, multipath and so on. Interference and multipath are added to the useful signal in order to deteriorate the MOS, until the VoLTE calls dropped. Target of such work is to properly set the thresholds that trigger a handover of single radio voice call continuity to other radio access technologies (UMTS or GSM). Tests take also into account the adaptive multi‐rate CoDec selected by the network. [ABSTRACT FROM AUTHOR]

This research proposes an enhanced measurement method for VoIP quality assessment which provides an improvement to accuracy and reliability. To improve the objective measurement tool called the simplified E-model for the selected codec, G.729, it has been enhanced by utilizing a model of Mean Opinion Score (MOS), called a subjective MOS prediction model, based on native Thai users who use the Thai-tonal language. Then, the different results from the simplified E-model and subjective MOS prediction model were used to create the Bias function, before adding to the simplified E-model. Finally, it has been found that the outputs from the enhanced simplified E-model for the G.729 codec show better accuracy when compared to the original simplified E-model, specially, after the enhanced model has been evaluated with 4 test sets. The major contribution of this enhancement is that errors are reduced by 58.87% when compared to the generic simplified E-model. That means the enhanced simplified E-model as proposed in this study can provide improvement beyond the original simplified one significantly. [ABSTRACT FROM AUTHOR]

Many histogram equalisations‐based methods have been proposed to be applied in contrast enhancement. However, a few methods that can simultaneously create a natural enhancement in images with low, median, and high brightness ranges are suggested. Here, a robust contrast enhancement algorithm, which is called triple clipped dynamic histogram equalisation based on standard deviation (TCDHE‐SD), is proposed. In the proposed method, the histogram of the input image is partitioned into three parts with approximately the same number of pixels based on the standard deviation. Then, the process of histogram clipping is performed on each sub‐histogram. After that, all histograms will be mapped to a new dynamic range by means of applying some simple calculations, and finally, the sub‐histogram equalisation process will be performed independently. This method is proposed to achieve the multiple purposes of the maximum average information content (entropy), controlling the enhancement ratio and preserving reasonable brightness. It also provides a natural enhancement by generating clear images with maximum details. The performance assessment of the proposed method in terms of entropy as well as visual quality based on the mean opinion score (MOS) indicates a significant advantage of it over the previous ones. [ABSTRACT FROM AUTHOR]

In data service applications over the Internet, user perception and satisfaction can be assessed by quality of experience (QoE) metrics. QoE depends both on the users' perception and the used service, which together form end-to-end metrics. While network optimization has traditionally focused on optimizing network properties such as QoS, we focus in this work on optimizing end-to-end QoE metrics with the aim to deliver to the client a good QoE that can be monitored in real time. We argue that end-user QoE is a relevant measurement for network operators and service providers. In this paper, we present a machine learning approach combined with adaptive video delivery service in order to provide a better QoE for video streaming services. This solution will be established using SDN architecture. The first part of the paper deals with a brief introduction of SDN networks, QoE requirement, and ML algorithms. Secondly, we expose the rating of the web application that we developed. This will help in conducting a subjective study to collect MOS on real-time as well as objective parameters SSIM, VQM, and PSNR. At the end, we expose our QoE-aware monitoring approach and explain what it is based on. [ABSTRACT FROM AUTHOR]

One of the main goals of the future wireless networks is improving the users’ quality of experience (QoE). In this paper, we consider the problem of the QoE-based resource allocation in the downlink of a massive multiple-input multiple-output heterogeneous network. The network consists of a macrocell with a number of small cells embedded in it. The small cells’ base stations (BSs) are equipped with a few antennas, while the macro BS is equipped with a massive number of antennas. We consider the two services Video and Web Browsing and design the beamforming vectors at the BSs. The objective is to maximize the aggregated mean opinion score (MOS) of the users under constraints on the BSs’ powers and the required quality of service of the users. We also consider extra constraints on the QoE of users to more strongly enforce the QoE in the beamforming design. To reduce the complexity of the optimization problem, we suggest suboptimal and computationally efficient solutions. Our results illustrate that increasing the number of antennas at the BSs and also increasing the number of small cells’ antennas in the network leads to a higher user satisfaction. [ABSTRACT FROM AUTHOR]

Spectrum handoff plays an important role in cognitive radio networks (CRNs). Secondary users (SUs) use spectrum handoff to hold on the idle channel or to free the channel for primary users (PUs). Spectrum handoff scheme greatly affects the transmission quality and the success rate of SUs connection. In this Letter, a reinforcement learning‐based spectrum handoff scheme with the measured packet drop rate (PDR) for multimedia transmissions over CRNs is proposed. In a system model with multiple PUs and SUs, a new state space description method is designed and an observed state includes not only the status whether PUs arrive on each channel but also several other important factors. Also, the measured PDR, instead of the calculated one, is presented to update the mean opinion score, the Q‐table and the handoff policy. Compared with the existing schemes with the calculated PDR from the Quality‐of‐Experience model, the authors' proposed scheme can converge more rapidly in the dynamic radio environment, and reduce the PDR of SUs more significantly. [ABSTRACT FROM AUTHOR]

A large number of subjective image quality assessment databases have been constructed in the last decade, in which the Mean Opinion Score (MOS) (with single or double stimulus), and Paired Comparison (PC) are two dominant approaches for collecting the ground truth quality ratings and usually up to 15 or more subjects are needed for each image. In this paper, we show the fact that there is a potential “dictatorship” risk of using such averaging-over-multiple-rating type of method. Using Arrow’s Impossibility Theorem (AIT), we prove that meeting of the unanimity and independence of irrelevant alternatives (IIA) will generate a “pivotal subject”, who in fact determines the final rank of image quality. We also prove that no an ideal democratic approach to synthesize the whole opinions of subjects. Therefore, we advocate to recruit a small number of experts (a.k.a the “golden eyes”) for subjective viewing tests. In order to verify the reliability of our proposal, experiments on two different databases conducting on the general distorted images and professional images (here is Terahertz security image) are performed. In each experiment, the raw scores of images are subjectively assigned by at least 15 inexperienced viewers and 3 experts, and meanwhile the MOS or difference mean opinion score (DMOS) are obtained. Afterwards, the correlation of the scores rated by naive subjects and experts is analyzed. For general image experiment, it is revealed that DMOS of inexperience viewers are highly related to DMOS of experts based on six effective evaluation metrics. In professional image experiment, the preferences of experts also maintain favourable relevance with the opinions of inexperienced viewers in overall quality of THz image. Moreover, considering the quality assessments of illegal substance regions in THz images, the experts have higher accuracy than the inexperienced observers. In conclusion, the results of two validation experiments verify that a small number of experts are more suitable for assessing the perceptual quality of images, which can reduce cost and simplify procedure of creating databases. [ABSTRACT FROM AUTHOR]

In this paper, we propose a Multi-Constraint Quality-of-Experience (QoE) centric Routing (MCQR) technique for efficient real-time video streaming over Mobile Ad-hoc Networks (MANETs). The dynamic estimation of link quality metric during MCQR route discovery process is the key of enhancing QoE at end user. MCQR limits end-to-end delay and jitter of received data packets by selecting long lifetime routes with maximum permissible delay. This minimizes the distortion caused fluctuations in perceived video. To prove the effectiveness of MCQR for real-time video streaming, we have designed a hybrid MANET consisting of simulated nodes and physical machines. In our hybrid network, the source and destination nodes are video traffic generators and receivers running on physical devices. Emulation results are obtained using real-time video streaming over high fidelity virtual wireless network, and conforming that the MCQR protocol provides satisfactory QoE to end users as compared to existing similar techniques. The packet delivery ratio of MCQR is higher than 90 % and its mean opinion score is higher than three (i.e., satisfactory) even when mobility and shadowing effects are kept high in target network scenarios. These improvements are achieved along with still maintaining similar or better routing overhead and processing delays. [ABSTRACT FROM AUTHOR]

Referenceless image quality assessment is a challenging and critical problem in today's multimedia applications. Texture patterns in images are normally at high frequencies compared to lower ones. Due to the effect of distortions during acquisition, compression, and transmission, texture deviation artifacts are generated that cause a granular effect in the image. Other artifacts, such as blocking, affect high frequencies in an image, causing distorted edges. Combining the analysis of texture deviation and other artifacts helps in determining the quality of an image. The proposed approach uses variation in the energy of pixels to quantify the quality of an image. These variations are calculated using texture energy measures and pattern strength-based statistical features. In the proposed approach, machine learning-based classifiers are used to predict the quality score for an image. The performance of the proposed method is tested for all images ranging from pristine to poor quality from LIVE and TID2008 databases. For different distortions, results are shown to have good correlation if they lie between the predicted score and the differential mean opinion score. Results obtained with this approach are compared with other widely used referenceless approaches. It is observed that the proposed approach shows better performance in the quantification of the quality of an image. [ABSTRACT FROM AUTHOR]

With the explosive growth of mobile video applications, analysis of video quality becomes increasingly important because it is an important Key Performance Indicator (KPI) for Quality of Experience (QoE). In this paper, a framework for non-reference video quality analysis is proposed and applied to Video Telephony (VT) in LTE networks. Three metrics, blockiness, blur and freezing, are used to estimate the MOS. Blockiness is detected by taking the H.264 codec features into account, blur is estimated by utilizing the percentage of noticeable blurred edges in each frame, and freezing is evaluated by using a sigmoid function to mimic the effect of different freezing duration on the Human Visual System (HVS). Furthermore, the three metrics are combined into one objective MOS by considering different weighting factors and using the linear curve fitting. Above 90% correlation is achieved between the objective MOS score and subjective MOS score. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of the speech quality improvement using adaptive filtering algorithms. Recently in Djendi and Bendoumia (2014) [1], we have proposed a new two-channel backward algorithm for noise reduction and speech intelligibility enhancement. The main drawback of proposed two-channel subband algorithm is its poor performance when the number of subband is high. This inconvenience is well seen in the steady state regime values. The source of this problem is the fixed step-sizes of the cross-adaptive filtering algorithms that distort the speech signal when they are selected high and degrade the convergence speed behaviours when they are selected small. In this paper, we propose four modifications of this algorithm which allow improving both the convergence speed and the steady state values even in very noisy condition and a high number of subbands. To confirm the good performance of the four proposed variable-step-size SBBSS algorithms, we have carried out several simulations in various noisy environments. In these simulations, we have evaluated objective and subjective criteria as the system mismatch, the cepstral distance, the output signal-to-noise-ratio, and the mean opinion score (MOS) method to compare the four proposed variables step-size versions of the SBBSS algorithm with their original versions and with the two-channel fullband backward (2CFB) least mean square algorithm. [ABSTRACT FROM AUTHOR]

A cochlear implant is an implanted electronic device used to provide a sensation of hearing to a person who is hard of hearing. The cochlear implant is often referred to as a bionic ear. This paper presents an undecimated wavelet-based speech coding strategy for cochlear implants, which gives a novel speech processing strategy. The undecimated wavelet packet transform (UWPT) is computed like the wavelet packet transform except that it does not down-sample the output at each level. The speech data used for the current study consists of 30 consonants, sampled at 16 kbps. The performance of our proposed UWPT method was compared to that of infinite impulse response (IIR) filter in terms of mean opinion score (MOS), short-time objective intelligibility (STOI) measure and segmental signal-to-noise ratio (SNR). Undecimated wavelet had better segmental SNR in about 96% of the input speech data. The MOS of the proposed method was twice in comparison with that of the IIR filter-bank. The statistical analysis revealed that the UWT-based N-of-M strategy significantly improved the MOS, STOI and segmental SNR (P < 0.001) compared with what obtained with the IIR filter-bank based strategies. The advantage of UWPT is that it is shift-invariant which gives a dense approximation to continuous wavelet transform. Thus, the information loss is minimal and that is why the UWPT performance was better than that of traditional filter-bank strategies in speech recognition tests. Results showed that the UWPT could be a promising method for speech coding in cochlear implants, although its computational complexity is higher than that of traditional filter-banks. [ABSTRACT FROM AUTHOR]

Highlights: [•] Objective image quality measure (VPSNR) is developed. [•] VPSNR has good correlation with MOS for compressed images. [•] VPSNR can be calculated in the spatial domain. [•] VPSNR coincides with PSNR on conner cases. [ABSTRACT FROM AUTHOR]

Highlights: [•] Subjective quality assessments for video streaming over tablet devices. [•] Parametric quality model useful for system control and optimization. [•] Comparison of with alternative subjective assessment results and models. [ABSTRACT FROM AUTHOR]

Underwater images contain an interacting mixture of distortions due to the physicochemical properties of the water, suspended organic matter and floating particles in water. Unlike images in traditional natural image quality databases, underwater images are often difficult to acquire with reference images and sets of images with gradient distortion. Therefore, it is even more difficult for the viewers to assign an absolute psychophysical scale to the quality of underwater images. In this paper, we propose a pairwise subjective comparison procedure for underwater images quality ranking inspired by the intuitive suppression and competence mechanisms in visual perception. In the proposed method, we construct a preselection based initial image quality dataset by full pairwise comparison, which also enables online adaptive new image updating. The proposed method is not constrained by the lack of reference images, and is reliable and sensitive to images with discriminable distortion level and various image contents. The proposed pairwise comparison further allows an uncertain choice, which does not require a reinforce human opinion. To the best of our knowledge, this is the first implementation for underwater image subjective quality ranking, and a new approach to the image quality ranking for different image contents with unknown distortion level. We demonstrate that the obtained subjective image ranking correlates well with the human perception of quality difference among the underwater images than that of the single stimuli image quality assessment with finite labor burden. Moreover, our proposed method accurately characterize the gradual degradation in the underwater image sequence taken in controlled conditions. The proposed progressive learning ranking is also an alternative way to realize adaptive extension of the existing image quality databases. • The first trial for subjective quality ranking of underwater image. • An objective image quality prescreening is incorporated in the ranking methods. • The pairwise sorting is formulated as a three-choice judgment. • The laboratory evaluation and online voting is combined. • The proposed method is a reliable way to rank all underwater images in the corpus. [ABSTRACT FROM AUTHOR]

Usage of Automatic Speech Recognition (ASR) systems is increasing day-by-day for voice centric applications in mobile handheld and Voice over Internet Protocol (VoIP) devices. The necessity is also increasing to find out the ASR performance under different network impediments. Among them, speech and audio coding standards is the one, which affects the ASR performance greatly, when, using them with different sampling and bit rates in the practical systems. Another common impediment which influences the ASR accuracy is the bit errors in the wireless networks and packet drop conditions in the VoIP networks. ASR performance with some of the speech coding standards under noise conditions for the wireless networks is reported in the literature. However, each study is reporting the ASR performance for few narrowband codecs with different speech databases and different ASR toolkits like RAPHEL, HTK, SPHINX, etc. In this paper, the analysis on ASR performance while using both narrowband and wideband speech and audio coding standards, which are currently accepted for GSM mobile and VoIP networks, using the common speech database-TIMIT, and using ASR toolkit-SPHINX, is presented. The Mean Opinion Score (MOS), which is the generally accepted speech quality measurement technique, is also analyzed for all the speech and audio coding standards, using the same speech database. The results of the studies carried out for the ASR word accuracies and MOS values for different narrowband and wideband speech and audio codecs under no-loss conditions are presented. Results for different rates of packet drop condition which is the common noise scenario in wired networks such as VoIP (which is also merging with wireless networks) are also presented. The observation is that though some of the codecs are showing poor MOS performance at lower bit rates, the corresponding ASR performance is comparable with other codecs at higher bit rates. [ABSTRACT FROM AUTHOR]

This paper proposes a novel two-scale auditory feature based algorithm for non-intrusive evaluation of speech quality. The neuron firing probabilities along the length of the basilar membrane, from an explicit auditory model, are used to extract features from the distorted speech signal. This is in contrast to previous methods, which either use standard vocal tract based features, or incorporate only some aspects of the human auditory perception mechanism. The features are extracted at two scales, namely a global scale spanning all voiced frames in an utterance, and a local scale spanning voiced frames from contiguous voiced segments in the utterance. This is followed by a simple information fusion at the score level using Gaussian Mixture Models (GMMs). The use of an explicit auditory model to extract features is based on the premise that similar processing (in a qualitative sense) happens in human speech perception. In addition, auditory feature extraction at two scales incorporates the effects of both long term and short term distortions on speech quality. The proposed algorithm is shown to perform at least as good as the ITU-T Recommendation P.563. [ABSTRACT FROM AUTHOR]

A common communications convergence scenario which is being adopted in personal communications relates to the combination of wireless and cellular networks by the use of multimode terminals. Since most of the wireless networks were initially dimensioned only for data communications, this paper shows how voice over wireless LAN dimensioning could be addressed under the optimal network throughput and the perspective of voice quality, using a simple approach. The maximum number of simultaneous users resulting from throughput is limited by the collisions taking place in the shared medium with the statistical contention protocol. The voice quality is conditioned by the delay and the packet loss in the contention protocol. Both approaches are analyzed within the scope of the voice codecs commonly used in voice over wireless LANs, to conclude that voice dimensioning based on network throughput and voice quality show complementary results. Additionally the use of low rate codecs in voice over wireless LANs is advantageous for the network performance point of view but may produce poor voice quality results. Mid range codecs like G729 could represent a trade-off for quality throughput. For these reasons, voice quality and wireless network throughput have to be taken into account in the network admission control, design and deployment to ensure a satisfactory user experience. The impact of handoff interval of wireless convergent networks on the conversation quality need also be assessed for a proper network design. [ABSTRACT FROM AUTHOR]

Lightfield (LF) technology has attained significant attention in recent years due to its capability to capture much richer textural and geometric information in the scene compared to the classical 2D representation. The resampling and compression operations on LFs often lead to visual quality degradation, thus, sophisticated visual quality assessment methods play a crucial role to ensure a pleasant viewing experience. To this end, it is necessary to examine the performance of quality assessment methods for LF contents. The paper provides a comprehensive study on the reliability of various objective algorithms for LF quality prediction. Three subjectively-annotated LF data sets were selected and an extensive quality estimation analysis has been conducted using several objective quality assessment methods. In total, 250 LFs (more than 48000 perspective images) were evaluated. The results were compared against human opinion scores using various correlation indices and their statistical significance. Next, a decision-making strategy was adopted to choose the most reliable quality metrics for evaluation of LFs and finally, a metric fusion framework was proposed to further improve the quality prediction accuracy. To best of our knowledge, the benchmark and the analytical methodologies used in this paper are the most comprehensive study on the objective quality assessment methods for LF application. • A comprehensive benchmark of 24 objective quality assessment methods is performed for Light-field visual quality prediction. • The most reliable quality metrics for light fields are selected based on the statistical tests and by using a decision-making strategy. • A metric fusion framework is adopted to improve the quality assessment accuracy. [ABSTRACT FROM AUTHOR]

An important question, that is whether for the subjective evaluation of three‐dimensional (3D) video can be performed on one type of 3D monitor only or whether multiple types of displays are required in order to obtain reliable results, is answered. The experimental material used in this reported work includes mean opinion score (MOS) data collected on two types of monitors: polarisation and autostereoscopic. An analysis of this data is reported. The observed high correlation of the gathered quality metrics clearly indicates that the results obtained using the polarisation monitor are as statistically significant as the results obtained using the autostereoscopic one. Therefore, to save time, only one type of monitor can be used. [ABSTRACT FROM AUTHOR]

Although there has been some research on the relation between random errors that cause speech quality impairment and mean opinion score (MOS), speech quality impairment factors have not been clarified for the bursty code error noise. A subjective evaluation experiment that uses a free conversational form is conducted and the effect of bursty code error noise on speech quality is studied. Moreover, Q-value quantification of bursty code error noise and random code error noise and its additivity are studied. MOS and tolerance rate change linearly according to a logarithmic number of bursts during a certain length of conversation. Impairment changes according to the number of error bit rates in a random bit error. A more simplified relationship can be obtained by converting MOSs to Q values. It is con- firmed that the additivity law holds between Q values for impairment that is due to random and bursty errors. [ABSTRACT FROM AUTHOR]

• Low latency, real-time automatic punctuation model. • RNN-based punctuation outperforms the MaxEnt baseline. • Subjective tests confirm that humans prefer punctuated captions. • Deaf or hard of hearing users prefer automatic punctuation even more. In Automatic Speech Recognition (ASR), inserting the punctuation marks into the word chain hypothesis has long been given low priority, as efforts were concentrated on minimizing word error rates. Punctuation, however, also has a high impact on the transcription quality perceived by the users. Prosody, textual context and their combination have since been used successfully for automatic punctuation of ASR outputs. The recently proposed RNN based solutions show encouraging performance. We believe that current bottlenecks of punctuation technology are on one hand the complex punctuation models, which, having high latency, are not suitable for use-cases with real-time requirements; and on the other hand, punctuation efforts have not been validated against human perception and user impression. The ambition of this paper is to propose a lightweight, yet powerful RNN punctuation model for on-line (real-time including low latency) environment, and also to assess user opinion, in general and also for target users living with hearing loss or impairment. The proposed on-line RNN punctuation model is evaluated against a Maximum Entropy (MaxEnt) baseline, for Hungarian and for English, whereas subjective assessment tests are carried out on real broadcast data subtitled with ASR (closed captioning). As it can be expected, the RNN outperforms the MaxEnt baseline system, but of course not the off-line systems: limiting the future context to minimize latency results only in a slighter performance drop, but ASR errors obviously influence punctuation performance considerably. A genre analysis is also carried out w.r.t. the punctuation performance showing that both recognition and punctuation of more spontaneous speech styles is challenging. Overall, the subjective tests confirmed that users perceive a significant quality improvement when punctuation is added, even in presence of word errors and even if punctuation is automatic and hence itself may contain further errors. For users living with hearing loss or deafness, an even higher, clear preference for the punctuated captions could be confirmed. [ABSTRACT FROM AUTHOR]

• It is a data-driven, model-independent and high performance ECG denoising technique. • The proposed ECG denoising technique outperforms state-of-the-art ECG denoising methods. • The mean opinion score of the denoised ECG signal falls under the category „very good‟ as per the gold standard subjective measure. • The proposed technique could be adapted for denoising other biomedical signals exhibiting periodic or quasi-periodic nature. An efficient and robust electrocardiogram (ECG) denoising technique caters three-fold benefits in the subsequent processing steps: first, it helps improving the accuracy of extracted features. Second, the improved accuracy in the extracted features enhances the performance as well as the reliability of computerised cardiovascular-disease diagnosis systems, and third, it also makes the interpretation task easier for the clinicians. Albeit a number of ECG denoising techniques are proposed in the literature, but most of these techniques suffer from one or more of the following drawbacks: i) model or function dependency, ii) sampling-rate dependency, or iii) high time-complexity. This paper presents a singular spectrum analysis (SSA)-based ECG denoising technique addressing most of these afore-mentioned shortcomings. First, a trajectory matrix of dimension K × L is formed using the original one-dimensional ECG signal of length N. In SSA operation the parameter L , which is denoted as the window-length, plays a very important role and is related to the sampling frequency of the signal. In this research the value of L is calculated dynamically based on the morphological property of the ECG signal. Then, the matrix is decomposed using singular value decomposition technique, and the principal components (PC) of the original ECG signal are computed. Next, the reconstructed components (RC) are calculated from the PCs, and all the RCs are filtered through Butterworth bandpass and notch filters. An optimum number of filtered RCs are retained based on their significance. Finally, these retained RCs are summed up to obtain the denoised ECG signal. Evaluation result shows that the proposed technique outperforms state-of-the-art ECG denoising methods; in particular, the mean opinion score of the denoised signal falls under the category 'very good' as per the gold standard subjective measure. Both the quantitative and qualitative distortion measure metrics show that the proposed ECG denoising technique is robust enough to filter various noises present in the signal without jeopardizing the clinical content. The proposed technique could be adapted for denoising other biomedical signals exhibiting periodic or quasi-periodic nature such as photoplethysmogram and esophageal pressure signal. [ABSTRACT FROM AUTHOR]