在这项工作中，我们提出了一个说话者的匿名管道，该管道利用高质量的自动语音识别和合成系统来生成以语音转录和匿名扬声器嵌入为条件的语音。使用电话作为中间表示，可确保从输入中完全消除说话者身份信息，同时尽可能保留原始的语音内容。我们在Librispeech和VCTK Corpora上的实验结果揭示了两个关键发现：1）尽管自动语音识别会产生不完美的转录，但我们的神经语音合成系统可以处理此类错误，使我们的系统可行且健壮，并且2）结合来自不同资源的扬声器嵌入，有益及其适当的归一化至关重要。总体而言，我们的最终最佳系统在2020年语音隐私挑战挑战中提供的基线在与懒惰的攻击者的稳健性方面相当大，同时保持了匿名语音的高度理解性和自然性。

随着自动语音处理（ASR）系统越来越好，使用ASR输出越来越令于进行下游自然语言处理（NLP）任务。但是，很少的开源工具包可用于在不同口语理解（SLU）基准上生成可重复的结果。因此，需要建立一个开源标准，可以用于具有更快的开始进入SLU研究。我们展示了Espnet-SLU，它旨在在一个框架中快速发展口语语言理解。 Espnet-SLU是一个项目内部到结束语音处理工具包，ESPNET，它是一个广泛使用的开源标准，用于各种语音处理任务，如ASR，文本到语音（TTS）和语音转换（ST）。我们增强了工具包，为各种SLU基准提供实现，使研究人员能够无缝混合和匹配不同的ASR和NLU模型。我们还提供预磨损的模型，具有集中调谐的超参数，可以匹配或甚至优于最新的最先进的性能。该工具包在https://github.com/espnet/espnet上公开提供。

In this paper, we propose a new neural network architecture based on the H2 matrix. Even though networks with H2-inspired architecture already exist, and our approach is designed to reduce memory costs and improve performance by taking into account the sparsity template of the H2 matrix. In numerical comparison with alternative neural networks, including the known H2-based ones, our architecture showed itself as beneficial in terms of performance, memory, and scalability.

t-SNE remains one of the most popular embedding techniques for visualizing high-dimensional data. Most standard packages of t-SNE, such as scikit-learn, use the Barnes-Hut t-SNE (BH t-SNE) algorithm for large datasets. However, existing CPU implementations of this algorithm are inefficient. In this work, we accelerate the BH t-SNE on CPUs via cache optimizations, SIMD, parallelizing sequential steps, and improving parallelization of multithreaded steps. Our implementation (Acc-t-SNE) is up to 261x and 4x faster than scikit-learn and the state-of-the-art BH t-SNE implementation from daal4py, respectively, on a 32-core Intel(R) Icelake cloud instance.

We investigate a model for image/video quality assessment based on building a set of codevectors representing in a sense some basic properties of images, similar to well-known CORNIA model. We analyze the codebook building method and propose some modifications for it. Also the algorithm is investigated from the point of inference time reduction. Both natural and synthetic images are used for building codebooks and some analysis of synthetic images used for codebooks is provided. It is demonstrated the results on quality assessment may be improves with the use if synthetic images for codebook construction. We also demonstrate regimes of the algorithm in which real time execution on CPU is possible for sufficiently high correlations with mean opinion score (MOS). Various pooling strategies are considered as well as the problem of metric sensitivity to bitrate.

Online controlled experiments (A/B tests) have become the gold standard for learning the impact of new product features in technology companies. Randomization enables the inference of causality from an A/B test. The randomized assignment maps end users to experiment buckets and balances user characteristics between the groups. Therefore, experiments can attribute any outcome differences between the experiment groups to the product feature under experiment. Technology companies run A/B tests at scale -- hundreds if not thousands of A/B tests concurrently, each with millions of users. The large scale poses unique challenges to randomization. First, the randomized assignment must be fast since the experiment service receives hundreds of thousands of queries per second. Second, the variant assignments must be independent between experiments. Third, the assignment must be consistent when users revisit or an experiment enrolls more users. We present a novel assignment algorithm and statistical tests to validate the randomized assignments. Our results demonstrate that not only is this algorithm computationally fast but also satisfies the statistical requirements -- unbiased and independent.

Vision Transformers convert images to sequences by slicing them into patches. The size of these patches controls a speed/accuracy tradeoff, with smaller patches leading to higher accuracy at greater computational cost, but changing the patch size typically requires retraining the model. In this paper, we demonstrate that simply randomizing the patch size at training time leads to a single set of weights that performs well across a wide range of patch sizes, making it possible to tailor the model to different compute budgets at deployment time. We extensively evaluate the resulting model, which we call FlexiViT, on a wide range of tasks, including classification, image-text retrieval, open-world detection, panoptic segmentation, and semantic segmentation, concluding that it usually matches, and sometimes outperforms, standard ViT models trained at a single patch size in an otherwise identical setup. Hence, FlexiViT training is a simple drop-in improvement for ViT that makes it easy to add compute-adaptive capabilities to most models relying on a ViT backbone architecture. Code and pre-trained models are available at https://github.com/google-research/big_vision

Multi-agent path finding (MAPF) is a task of finding non-conflicting paths connecting agents' specified initial and goal positions in a shared environment. We focus on compilation-based solvers in which the MAPF problem is expressed in a different well established formalism such as mixed-integer linear programming (MILP), Boolean satisfiability (SAT), or constraint programming (CP). As the target solvers for these formalisms act as black-boxes it is challenging to integrate MAPF specific heuristics in the MAPF compilation-based solvers. We show in this work how the build a MAPF encoding for the target SAT solver in which domain specific heuristic knowledge is reflected. The heuristic knowledge is transferred to the SAT solver by selecting candidate paths for each agent and by constructing the encoding only for these candidate paths instead of constructing the encoding for all possible paths for an agent. The conducted experiments show that heuristically guided compilation outperforms the vanilla variants of the SAT-based MAPF solver.

The appearance of an object can be fleeting when it transforms. As eggs are broken or paper is torn, their color, shape and texture can change dramatically, preserving virtually nothing of the original except for the identity itself. Yet, this important phenomenon is largely absent from existing video object segmentation (VOS) benchmarks. In this work, we close the gap by collecting a new dataset for Video Object Segmentation under Transformations (VOST). It consists of more than 700 high-resolution videos, captured in diverse environments, which are 20 seconds long on average and densely labeled with instance masks. A careful, multi-step approach is adopted to ensure that these videos focus on complex object transformations, capturing their full temporal extent. We then extensively evaluate state-of-the-art VOS methods and make a number of important discoveries. In particular, we show that existing methods struggle when applied to this novel task and that their main limitation lies in over-reliance on static appearance cues. This motivates us to propose a few modifications for the top-performing baseline that improve its capabilities by better modeling spatio-temporal information. But more broadly, the hope is to stimulate discussion on learning more robust video object representations.

Unsupervised anomaly detection in time-series has been extensively investigated in the literature. Notwithstanding the relevance of this topic in numerous application fields, a complete and extensive evaluation of recent state-of-the-art techniques is still missing. Few efforts have been made to compare existing unsupervised time-series anomaly detection methods rigorously. However, only standard performance metrics, namely precision, recall, and F1-score are usually considered. Essential aspects for assessing their practical relevance are therefore neglected. This paper proposes an original and in-depth evaluation study of recent unsupervised anomaly detection techniques in time-series. Instead of relying solely on standard performance metrics, additional yet informative metrics and protocols are taken into account. In particular, (1) more elaborate performance metrics specifically tailored for time-series are used; (2) the model size and the model stability are studied; (3) an analysis of the tested approaches with respect to the anomaly type is provided; and (4) a clear and unique protocol is followed for all experiments. Overall, this extensive analysis aims to assess the maturity of state-of-the-art time-series anomaly detection, give insights regarding their applicability under real-world setups and provide to the community a more complete evaluation protocol.