The Perceptual Evaluation of Audio Quality (PEAQ) method as described in the International Telecommunication Union (ITU) recommendation ITU-R BS.1387 has been widely used for computationally estimating the quality of perceptually coded audio signals without the need for extensive subjective listening tests. However, many reports have highlighted clear limitations of the scheme after the end of its standardization, particularly involving signals coded with newer technologies such as bandwidth extension or parametric multi-channel coding. Until now, no other method for measuring the quality of both speech and audio signals has been standardized by the ITU. Therefore, a further investigation of the causes for these limitations would be beneficial to a possible update of said scheme. Our experimental results indicate that the performance of PEAQ's model of disturbance loudness is still as good as (and sometimes superior to) other state-of-the-art objective measures, albeit with varying performance depending on the type of degraded signal content (i.e. speech or music). This finding evidences the need for an improved cognitive model. In addition, results indicate that an updated mapping of Model Output Values (MOVs) to PEAQ's Distortion Index (DI) based on newer training data can greatly improve performance. Finally, some suggestions for the improvement of PEAQ are provided based on the reported results and comparison to other systems.
相關內容
Differing from the well-developed horizontal object detection area whereby the computing-friendly IoU based loss is readily adopted and well fits with the detection metrics. In contrast, rotation detectors often involve a more complicated loss based on SkewIoU which is unfriendly to gradient-based training. In this paper, we propose an effective approximate SkewIoU loss based on Gaussian modeling and Gaussian product, which mainly consists of two items. The first term is a scale-insensitive center point loss, which is used to quickly narrow the distance between the center points of the two bounding boxes. In the distance-independent second term, the product of the Gaussian distributions is adopted to inherently mimic the mechanism of SkewIoU by its definition, and show its alignment with the SkewIoU loss at trend-level within a certain distance (i.e. within 9 pixels). This is in contrast to recent Gaussian modeling based rotation detectors e.g. GWD loss and KLD loss that involve a human-specified distribution distance metric which require additional hyperparameter tuning that vary across datasets and detectors. The resulting new loss called KFIoU loss is easier to implement and works better compared with exact SkewIoU loss, thanks to its full differentiability and ability to handle the non-overlapping cases. We further extend our technique to the 3-D case which also suffers from the same issues as 2-D. Extensive results on various public datasets (2-D/3-D, aerial/text/face images) with different base detectors show the effectiveness of our approach.
Personalized treatment effect estimates are often of interest in high-stakes applications -- thus, before deploying a model estimating such effects in practice, one needs to be sure that the best candidate from the ever-growing machine learning toolbox for this task was chosen. Unfortunately, due to the absence of counterfactual information in practice, it is usually not possible to rely on standard validation metrics for doing so, leading to a well-known model selection dilemma in the treatment effect estimation literature. While some solutions have recently been investigated, systematic understanding of the strengths and weaknesses of different model selection criteria is still lacking. In this paper, instead of attempting to declare a global `winner', we therefore empirically investigate success- and failure modes of different selection criteria. We highlight that there is a complex interplay between selection strategies, candidate estimators and the DGP used for testing, and provide interesting insights into the relative (dis)advantages of different criteria alongside desiderata for the design of further illuminating empirical studies in this context.
This work considers Gaussian process interpolation with a periodized version of the Mat{\'e}rn covariance function introduced by Stein (22, Section 6.7). Convergence rates are studied for the joint maximum likelihood estimation of the regularity and the amplitude parameters when the data is sampled according to the model. The mean integrated squared error is also analyzed with fixed and estimated parameters, showing that maximum likelihood estimation yields asymptotically the same error as if the ground truth was known. Finally, the case where the observed function is a fixed deterministic element of a Sobolev space of continuous functions is also considered, suggesting that bounding assumptions on some parameters can lead to different estimates.
Crowdsourcing has emerged as an alternative solution for collecting large scale labels. However, the majority of recruited workers are not domain experts, so their contributed labels could be noisy. In this paper, we propose a two-stage model to predict the true labels for multicategory classification tasks in crowdsourcing. In the first stage, we fit the observed labels with a latent factor model and incorporate subgroup structures for both tasks and workers through a multi-centroid grouping penalty. Group-specific rotations are introduced to align workers with different task categories to solve multicategory crowdsourcing tasks. In the second stage, we propose a concordance-based approach to identify high-quality worker subgroups who are relied upon to assign labels to tasks. In theory, we show the estimation consistency of the latent factors and the prediction consistency of the proposed method. The simulation studies show that the proposed method outperforms the existing competitive methods, assuming the subgroup structures within tasks and workers. We also demonstrate the application of the proposed method to real world problems and show its superiority.
An assisted living facility (ALF) is a place where someone can live, have access to social supports such as transportation, and receive assistance with the activities of daily living such as toileting and dressing. Despite the important role of ALFs, they are not required to be certified with Medicare and there is no public national database of these facilities. We present the first public dataset of ALFs in the United States, covering all 50 states and DC with 44,638 facilities and over 1.2 million beds. This dataset can help provide answers to existing public health questions as well as help those in need find a facility. The dataset was validated by replicating the results of a nationwide study of ALFs that uses closed data [4], where the prevalence of ALFs is assessed with respect to county-level socioeconomic variables related to health disparity such as race, disability, and income. To showcase the value of this dataset, we also propose a novel metric to assess access to community-based care. We calculate the average distance an individual in need must travel in order to reach an ALF. The dataset and all relevant code are available at github.com/antonstengel/assisted-living-data.
Counting the number of distinct elements distributed over multiple data holders is a fundamental problem with many real-world applications ranging from crowd counting to network monitoring. Although a number of space and computational efficient sketch methods (e.g., the Flajolet-Martin sketch and the HyperLogLog sketch) for cardinality estimation have been proposed to solve the above problem, these sketch methods are insecure when considering privacy concerns related to the use of each data holder's personal dataset. Despite a recently proposed protocol that successfully implements the well-known Flajolet-Martin (FM) sketch on a secret-sharing based multiparty computation (MPC) framework for solving the problem of private distributed cardinality estimation (PDCE), we observe that this MPC-FM protocol is not differentially private. In addition, the MPC-FM protocol is computationally expensive, which limits its applications to data holders with limited computation resources. To address the above issues, in this paper we propose a novel protocol DP-DICE, which is computationally efficient and differentially private for solving the problem of PDCE. Experimental results show that our DP-DICE achieves orders of magnitude speedup and reduces the estimation error by several times in comparison with state-of-the-arts under the same security requirements.
Background and purpose: Radiation-induced erectile dysfunction (RiED) is commonly seen in prostate cancer patients. Clinical trials have been developed in multiple institutions to investigate whether dose-sparing to the internal-pudendal-arteries (IPA) will improve retention of sexual potency. The IPA is usually not considered a conventional organ-at-risk (OAR) due to segmentation difficulty. In this work, we propose a deep learning (DL)-based auto-segmentation model for the IPA that utilizes CT and MRI or CT alone as the input image modality to accommodate variation in clinical practice. Materials and methods: 86 patients with CT and MRI images and noisy IPA labels were recruited in this study. We split the data into 42/14/30 for model training, testing, and a clinical observer study, respectively. There were three major innovations in this model: 1) we designed an architecture with squeeze-and-excite blocks and modality attention for effective feature extraction and production of accurate segmentation, 2) a novel loss function was used for training the model effectively with noisy labels, and 3) modality dropout strategy was used for making the model capable of segmentation in the absence of MRI. Results: The DSC, ASD, and HD95 values for the test dataset were 62.2%, 2.54mm, and 7mm, respectively. AI segmented contours were dosimetrically equivalent to the expert physician's contours. The observer study showed that expert physicians' scored AI contours (mean=3.7) higher than inexperienced physicians' contours (mean=3.1). When inexperienced physicians started with AI contours, the score improved to 3.7. Conclusion: The proposed model achieved good quality IPA contours to improve uniformity of segmentation and to facilitate introduction of standardized IPA segmentation into clinical trials and practice.
Substandard and falsified pharmaceuticals, prevalent in low- and middle-income countries, substantially increase levels of morbidity, mortality and drug resistance. Regulatory agencies combat this problem using post-market surveillance by collecting and testing samples where consumers purchase products. Existing analysis tools for post-market surveillance data focus attention on the locations of positive samples. This paper looks to expand such analysis through underutilized supply-chain information to provide inference on sources of substandard and falsified products. We first establish the presence of unidentifiability issues when integrating this supply-chain information with surveillance data. We then develop a Bayesian methodology for evaluating substandard and falsified sources that extracts utility from supply-chain information and mitigates unidentifiability while accounting for multiple sources of uncertainty. Using de-identified surveillance data, we show the proposed methodology to be effective in providing valuable inference.
Bid optimization for online advertising from single advertiser's perspective has been thoroughly investigated in both academic research and industrial practice. However, existing work typically assume competitors do not change their bids, i.e., the wining price is fixed, leading to poor performance of the derived solution. Although a few studies use multi-agent reinforcement learning to set up a cooperative game, they still suffer the following drawbacks: (1) They fail to avoid collusion solutions where all the advertisers involved in an auction collude to bid an extremely low price on purpose. (2) Previous works cannot well handle the underlying complex bidding environment, leading to poor model convergence. This problem could be amplified when handling multiple objectives of advertisers which are practical demands but not considered by previous work. In this paper, we propose a novel multi-objective cooperative bid optimization formulation called Multi-Agent Cooperative bidding Games (MACG). MACG sets up a carefully designed multi-objective optimization framework where different objectives of advertisers are incorporated. A global objective to maximize the overall profit of all advertisements is added in order to encourage better cooperation and also to protect self-bidding advertisers. To avoid collusion, we also introduce an extra platform revenue constraint. We analyze the optimal functional form of the bidding formula theoretically and design a policy network accordingly to generate auction-level bids. Then we design an efficient multi-agent evolutionary strategy for model optimization. Offline experiments and online A/B tests conducted on the Taobao platform indicate both single advertiser's objective and global profit have been significantly improved compared to state-of-art methods.
This paper focuses on the expected difference in borrower's repayment when there is a change in the lender's credit decisions. Classical estimators overlook the confounding effects and hence the estimation error can be magnificent. As such, we propose another approach to construct the estimators such that the error can be greatly reduced. The proposed estimators are shown to be unbiased, consistent, and robust through a combination of theoretical analysis and numerical testing. Moreover, we compare the power of estimating the causal quantities between the classical estimators and the proposed estimators. The comparison is tested across a wide range of models, including linear regression models, tree-based models, and neural network-based models, under different simulated datasets that exhibit different levels of causality, different degrees of nonlinearity, and different distributional properties. Most importantly, we apply our approaches to a large observational dataset provided by a global technology firm that operates in both the e-commerce and the lending business. We find that the relative reduction of estimation error is strikingly substantial if the causal effects are accounted for correctly.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191