Representation and learning of long-range dependencies is a central challenge confronted in modern applications of machine learning to sequence data. Yet despite the prominence of this issue, the basic problem of measuring long-range dependence, either in a given data source or as represented in a trained deep model, remains largely limited to heuristic tools. We contribute a statistical framework for investigating long-range dependence in current applications of sequence modeling, drawing on the statistical theory of long memory stochastic processes. By analogy with their linear predecessors in the time series literature, we identify recurrent neural networks (RNNs) as nonlinear processes that simultaneously attempt to learn both a feature representation for and the long-range dependency structure of an input sequence. We derive testable implications concerning the relationship between long memory in real-world data and its learned representation in a deep network architecture, which are explored through a semiparametric framework adapted to the high-dimensional setting. We establish the validity of statistical inference for a simple estimator, which yields a decision rule for long memory in RNNs. Experiments illustrating this statistical framework confirm the presence of long memory in a diverse collection of natural language and music data, but show that a variety of RNN architectures fail to capture this property even after training to benchmark accuracy in a language model.

WaveCycleGAN has recently been proposed to bridge the gap between natural and synthesized speech waveforms in statistical parametric speech synthesis and provides fast inference with a moving average model rather than an autoregressive model and high-quality speech synthesis with the adversarial training. However, the human ear can still distinguish the processed speech waveforms from natural ones. One possible cause of this distinguishability is the aliasing observed in the processed speech waveform via down/up-sampling modules. To solve the aliasing and provide higher quality speech synthesis, we propose WaveCycleGAN2, which 1) uses generators without down/up-sampling modules and 2) combines discriminators of the waveform domain and acoustic parameter domain. The results show that the proposed method 1) alleviates the aliasing well, 2) is useful for both speech waveforms generated by analysis-and-synthesis and statistical parametric speech synthesis, and 3) achieves a mean opinion score comparable to those of natural speech and speech synthesized by WaveNet (open WaveNet) and WaveGlow while processing speech samples at a rate of more than 150 kHz on an NVIDIA Tesla P100.

We present an unsupervised training approach for a neural network-based mask estimator in an acoustic beamforming application. The network is trained to maximize a likelihood criterion derived from a spatial mixture model of the observations. It is trained from scratch without requiring any parallel data consisting of degraded input and clean training targets. Thus, training can be carried out on real recordings of noisy speech rather than simulated ones. In contrast to previous work on unsupervised training of neural mask estimators, our approach avoids the need for a possibly pre-trained teacher model entirely. We demonstrate the effectiveness of our approach by speech recognition experiments on two different datasets: one mainly deteriorated by noise (CHiME 4) and one by reverberation (REVERB). The results show that the performance of the proposed system is on par with a supervised system using oracle target masks for training and with a system trained using a model-based teacher.

Disfluencies in spontaneous speech are known to be associated with prosodic disruptions. However, most algorithms for disfluency detection use only word transcripts. Integrating prosodic cues has proved difficult because of the many sources of variability affecting the acoustic correlates. This paper introduces a new approach to extracting acoustic-prosodic cues using text-based distributional prediction of acoustic cues to derive vector z-score features (innovations). We explore both early and late fusion techniques for integrating text and prosody, showing gains over a high-accuracy text-only model.

We present a novel, data driven approach for solving the problem of registration of two point cloud scans. Our approach is direct in the sense that a single pair of corresponding local patches already provides the necessary transformation cue for the global registration. To achieve that, we first endow the state of the art PPF-FoldNet auto-encoder (AE) with a pose-variant sibling, where the discrepancy between the two leads to pose-specific descriptors. Based upon this, we introduce RelativeNet, a relative pose estimation network to assign correspondence-specific orientations to the keypoints, eliminating any local reference frame computations. Finally, we devise a simple yet effective hypothesize-and-verify algorithm to quickly use the predictions and align two point sets. Our extensive quantitative and qualitative experiments suggests that our approach outperforms the state of the art in challenging real datasets of pairwise registration and that augmenting the keypoints with local pose information leads to better generalization and a dramatic speed-up.

This paper addresses the problem of key phrase extraction from sentences. Existing state-of-the-art supervised methods require large amounts of annotated data to achieve good performance and generalization. Collecting labeled data is, however, often expensive. In this paper, we redefine the problem as question-answer extraction, and present SAMIE: Self-Asking Model for Information Ixtraction, a semi-supervised model which dually learns to ask and to answer questions by itself. Briefly, given a sentence $s$ and an answer $a$, the model needs to choose the most appropriate question $\hat q$; meanwhile, for the given sentence $s$ and same question $\hat q$ selected in the previous step, the model will predict an answer $\hat a$. The model can support few-shot learning with very limited supervision. It can also be used to perform clustering analysis when no supervision is provided. Experimental results show that the proposed method outperforms typical supervised methods especially when given little labeled data.

Person re-identification (ReID) benefits greatly from the accurate annotations of existing datasets (e.g., CUHK03 \cite{li2014deepreid} and Market-1501 \cite{zheng2015scalable}), which are quite expensive because each image in these datasets has to be assigned with a proper label. In this work, we explore to ease the annotation of ReID by replacing the accurate annotation with inaccurate annotation, i.e., we group the images into bags in terms of time and assign a bag-level label for each bag. This greatly reduces the annotation effort and leads to the creation of a large-scale ReID benchmark called SYSU-30$k$. The new benchmark contains $30k$ categories of persons, which is about $20$ times larger than CUHK03 ($1.3k$ categories) and Market-1501 ($1.5k$ categories), and $30$ times larger the ImageNet ($1k$ categories). It totally sums up to 29,606,918 images. Learning a ReID model with bag-level annotation is called the weakly supervised ReID problem. To solve this problem, we introduce conditional random fields (CRFs) to capture the dependencies from all images in a bag and generate a reliable pseudo label for each person image. The pseudo label is further used to supervise the learning of the ReID model. When compared with the fully supervised ReID models, our method achieves the state-of-the-art performance on SYSU-30$k$ and other datasets. The code, dataset, and pretrained model will be available online.

It can be convenient to use a standard computer vision dataset when getting started with deep learning methods for computer vision. Standard datasets are often well understood, small, and easy to load. They can provide the basis for testing techniques and reproducing results in order to build confidence with libraries and methods. In this tutorial, you will discover the standard computer vision datasets provided with the Keras deep learning library. How to Load and Visualize Standard Computer Vision Datasets With Keras Photo by Marina del Castell, some rights reserved.

One of the most common applications of machine learning today is in recommendation algorithms. Netflix and YouTube use them to push you new shows and videos; Google and Facebook use them to rank the content in your search results and news feed. While these algorithms offer a great deal of convenience, they have some undesirable side effects. You've probably heard of them before: filter bubbles and echo chambers. Concern about these effects is not new.

Deep learning a subset of machine learning, has delivered super-human accuracy in a variety of practical uses in the past decade. In contrast to machine learning where an AI agent learns from data based on machine learning algorithms, deep learning is based on a neural network architecture which acts similarly to the human brain, and allows the AI agent to analyze data fed in -- in a structure similar to the way humans do. Deep learning models do not require algorithms to specify what to do with the data, which is made possible thanks to the extraordinary amount of data we as humans, collect and consume -- which in turn is fed to deep learning models [3]. The "traditional" types of deep learning incorporates a different mix of feed-forward modules (frequently convolutional neural networks) and recurrent neural networks (now and then with memory units, such as LSTM [4] or MemNN [5]). These deep learning models are restricted in their capacity to "reason", for example to do long chains of deductions, or streamlining a method to land at an answer.