After their introduction to robust speech recognition, power normalized cepstral coefficient (PNCC) features were successfully adopted to other tasks, including speaker verification. However, as a feature extractor with long-term operations on the power spectrogram, its temporal processing and amplitude scaling steps dedicated on environmental compensation may be redundant. Further, they might suppress intrinsic speaker variations that are useful for speaker verification based on deep neural networks (DNN). Therefore, in this study, we revisit and optimize PNCCs by ablating its medium-time processor and by introducing channel energy normalization. Experimental results with a DNN-based speaker verification system indicate substantial improvement over baseline PNCCs on both in-domain and cross-domain scenarios, reflected by relatively 5.8% and 61.2% maximum lower equal error rate on VoxCeleb1 and VoxMovies, respectively.

We address far-field speaker verification with deep neural network (DNN) based speaker embedding extractor, where mismatch between enrollment and test data often comes from convolutive effects (e.g. room reverberation) and noise. To mitigate these effects, we focus on two parametric normalization methods: per-channel energy normalization (PCEN) and parameterized cepstral mean normalization (PCMN). Both methods contain differentiable parameters and thus can be conveniently integrated to, and jointly optimized with the DNN using automatic differentiation methods. We consider both fixed and trainable (data-driven) variants of each method. We evaluate the performance on Hi-MIA, a recent large-scale far-field speech corpus, with varied microphone and positional settings. Our methods outperform conventional mel filterbank features, with maximum of 33.5% and 39.5% relative improvement on equal error rate under matched microphone and mismatched microphone conditions, respectively.

State-of-the-art approaches for visually-guided audio source separation typically assume sources that have characteristic sounds, such as musical instruments. These approaches often ignore the visual context of these sound sources or avoid modeling object interactions that may be useful to better characterize the sources, especially when the same object class may produce varied sounds from distinct interactions. To address this challenging problem, we propose Audio Visual Scene Graph Segmenter (AVSGS), a novel deep learning model that embeds the visual structure of the scene as a graph and segments this graph into subgraphs, each subgraph being associated with a unique sound obtained by co-segmenting the audio spectrogram. At its core, AVSGS uses a recursive neural network that emits mutually-orthogonal sub-graph embeddings of the visual graph using multi-head attention. These embeddings are used for conditioning an audio encoder-decoder towards source separation. Our pipeline is trained end-to-end via a self-supervised task consisting of separating audio sources using the visual graph from artificially mixed sounds. In this paper, we also introduce an "in the wild'' video dataset for sound source separation that contains multiple non-musical sources, which we call Audio Separation in the Wild (ASIW). This dataset is adapted from the AudioCaps dataset, and provides a challenging, natural, and daily-life setting for source separation. Thorough experiments on the proposed ASIW and the standard MUSIC datasets demonstrate state-of-the-art sound separation performance of our method against recent prior approaches.

The micro-segmentation of customers in the finance sector is a non-trivial task and has been an atypical omission from recent scientific literature. Where traditional segmentation classifies customers based on coarse features such as demographics, micro-segmentation depicts more nuanced differences between individuals, bringing forth several advantages including the potential for improved personalization in financial services. AI and representation learning offer a unique opportunity to solve the problem of micro-segmentation. Although ubiquitous in many industries, the proliferation of AI in sensitive industries such as finance has become contingent on the imperatives of responsible AI. We had previously solved the micro-segmentation problem by extracting temporal features from the state space of a recurrent neural network (RNN). However, due to the inherent opacity of RNNs our solution lacked an explanation - one of the imperatives of responsible AI. In this study, we address this issue by extracting an explanation for and providing an interpretation of our temporal features. We investigate the state space of our RNN and through a linear regression model reconstruct the trajectories in the state space with high fidelity. We show that our linear regression coefficients have not only learned the rules used to create the RNN's output data but have also learned the relationships that were not directly evident in the raw data.

Sequential Recommendation aims to recommend items that a target user will interact with in the near future based on the historically interacted items. While modeling temporal dynamics is crucial for sequential recommendation, most of the existing studies concentrate solely on the user side while overlooking the sequential patterns existing in the counterpart, i.e., the item side. Although a few studies investigate the dynamics involved in the dual sides, the complex user-item interactions are not fully exploited from a global perspective to derive dynamic user and item representations. In this paper, we devise a novel Dynamic Representation Learning model for Sequential Recommendation (DRL-SRe). To better model the user-item interactions for characterizing the dynamics from both sides, the proposed model builds a global user-item interaction graph for each time slice and exploits time-sliced graph neural networks to learn user and item representations. Moreover, to enable the model to capture fine-grained temporal information, we propose an auxiliary temporal prediction task over consecutive time slices based on temporal point process. Comprehensive experiments on three public real-world datasets demonstrate DRL-SRe outperforms the state-of-the-art sequential recommendation models with a large margin.

Hand pose estimation (HPE) can be used for a variety of human-computer interaction applications such as gesture-based control for physical or virtual/augmented reality devices. Recent works have shown that videos or multi-view images carry rich information regarding the hand, allowing for the development of more robust HPE systems. In this paper, we present the Multi-View Video-Based 3D Hand (MuViHand) dataset, consisting of multi-view videos of the hand along with ground-truth 3D pose labels. Our dataset includes more than 402,000 synthetic hand images available in 4,560 videos. The videos have been simultaneously captured from six different angles with complex backgrounds and random levels of dynamic lighting. The data has been captured from 10 distinct animated subjects using 12 cameras in a semi-circle topology where six tracking cameras only focus on the hand and the other six fixed cameras capture the entire body. Next, we implement MuViHandNet, a neural pipeline consisting of image encoders for obtaining visual embeddings of the hand, recurrent learners to learn both temporal and angular sequential information, and graph networks with U-Net architectures to estimate the final 3D pose information. We perform extensive experiments and show the challenging nature of this new dataset as well as the effectiveness of our proposed method. Ablation studies show the added value of each component in MuViHandNet, as well as the benefit of having temporal and sequential information in the dataset.

Large-scale pre-trained language models have shown remarkable results in diverse NLP applications. Unfortunately, these performance gains have been accompanied by a significant increase in computation time and model size, stressing the need to develop new or complementary strategies to increase the efficiency of these models. In this paper we propose DACT-BERT, a differentiable adaptive computation time strategy for BERT-like models. DACT-BERT adds an adaptive computational mechanism to BERT's regular processing pipeline, which controls the number of Transformer blocks that need to be executed at inference time. By doing this, the model learns to combine the most appropriate intermediate representations for the task at hand. Our experiments demonstrate that our approach, when compared to the baselines, excels on a reduced computational regime and is competitive in other less restrictive ones.

CAD modeling typically involves the use of simple geometric primitives whereas recent advances in deep-learning based 3D surface modeling have opened new shape design avenues. Unfortunately, these advances have not yet been accepted by the CAD community because they cannot be integrated into engineering workflows. To remedy this, we propose a novel approach to effectively combining geometric primitives and free-form surfaces represented by implicit surfaces for accurate modeling that preserves interpretability, enforces consistency, and enables easy manipulation.

Property inference attacks reveal statistical properties about a training set but are difficult to distinguish from the intrinsic purpose of statistical machine learning, namely to produce models that capture statistical properties about a distribution. Motivated by Yeom et al.'s membership inference framework, we propose a formal and general definition of property inference attacks. The proposed notion describes attacks that can distinguish between possible training distributions, extending beyond previous property inference attacks that infer the ratio of a particular type of data in the training data set such as the proportion of females. We show how our definition captures previous property inference attacks as well as a new attack that can reveal the average node degree or clustering coefficient of a training graph. Our definition also enables a theorem that connects the maximum possible accuracy of inference attacks distinguishing between distributions to the effective size of dataset leaked by the model. To quantify and understand property inference risks, we conduct a series of experiments across a range of different distributions using both black-box and white-box attacks. Our results show that inexpensive attacks are often as effective as expensive meta-classifier attacks, and that there are surprising asymmetries in the effectiveness of attacks. We also extend the state-of-the-art property inference attack to work on convolutional neural networks, and propose techniques to help identify parameters in a model that leak the most information, thus significantly lowering resource requirements for meta-classifier attacks.

In this tutorial, we will package and deploy a simple model that exposes an HTTP API and serves predictions to a device managed by Synpse. Flash is a high-level deep learning framework for fast prototyping, baselining, finetuning and solving deep learning problems. It features a set of tasks for you to use for inference and finetuning out of the box, and an easy to implement API to customize every step of the process for full flexibility. Flash is built for beginners with a simple API that requires very little deep learning background, and for data scientists, Kagglers, applied ML practitioners and deep learning researchers that want a quick way to get a deep learning baseline with advanced features PyTorch Lightning offers. I decided to go with the image_classification as it was important to me to have some kind of service that could differentiate between ants and bees.