Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Digital processing of speech signals

An intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

Intelligent Automated Assistant

When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Convolutional Neural Network (CNN), but the training data for its existing capabilities are unavailable. We propose our Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities. Our method performs favorably compared to commonly used feature extraction and fine-tuning adaption techniques and performs similarly to multitask learning that uses original task data we assume unavailable. A more surprising observation is that Learning without Forgetting may be able to replace fine-tuning with similar old and new task datasets for improved new task performance.

Learning without Forgetting

The prediction of future trajectories of the surrounding traffic participants is a key component in modern autonomous driving systems. This work presents an analysis of the impact of various representations of the input data on the prediction quality. The analyzed data comprises information recorded by the ego vehicle, including object recognition and object tracking, as well as satellite images and map information. We propose a neural network utilizing long short-term memories (LSTMs) to capture the sequence-to-sequence nature of the underlying problem, as well as a convolutional neural network (CNN) to take the surroundings of the predicted object into account. The input to our network is both the past trajectory of the predicted object, as well as a bird’s eye representation of the scene surrounding the object, fusing various types of information on the scene, e.g., a satellite image and bounding boxes of other traffic participants. We achieve Euclidean distances between the predicted position and the ground truth position of 0.47 m and 6.19 m for a prediction time instant that is 1 s and 6 s in the future, respectively. Additionally, we show the potential of our approach to transfer knowledge from similar road topologies to unseen intersections.

Analysis of the Effect of Various Input Representations for LSTM-Based Trajectory Prediction

In this contribution we propose an a priori signal-to-noise ratio (SNR) estimator based on a probabilistic speech model. Since the a priori SNR is an important means for speech enhancement algorithms, such as weighting rule calculation for noise reduction or speech presence probability computation, its diligent estimation is of wide interest. As a basis for this estimator a Gaussian mixture model (GMM) is trained on clean speech amplitudes and by finding the maximum likelihood (ML) clean speech estimate of the corresponding observed frame the a priori SNR can easily be calculated. Additionally, an iterative scheme is applied to consequently enhance the estimate by repetitively evaluating the GMM. This technique allows to accomplish noise reduction free of musical tones even in nonstationary noise environments and exceeds the quality of the classical decision-directed (DD) approach for typical spectral weighting rules.

An iterative speech model-based a priori SNR estimator.

Analyzing and predicting the traffic scene around the ego vehicle has been one of the key challenges in autonomous driving. Datasets including the trajectories of all road users present in a scene, as well as the underlying road topology are invaluable to analyze the behavior of the various traffic participants. The interaction between the traffic participants is especially high in intersection types that are not regulated by traffic lights, the most common one being the roundabout. We introduce the openDD dataset, including 84,774 accurately-tracked trajectories and HD map data of seven different roundabouts. The openDD dataset is annotated using images taken by a drone in 501 separate flights, totalling in over 62 hours of trajectory data. As of today the openDD is by far the largest publicly available trajectory dataset recorded from a drone perspective, while comparable datasets span 17 hours at most. The data is available, for both commercial and non-commercial use, at: http://www.13pilot.eu/openDD.

openDD: A Large-Scale Roundabout Drone Dataset

While current approaches for neural network training often aim at improving performance, less focus is put on training methods aiming at robustness towards varying noise conditions or directed attacks by adversarial examples. In this paper, we propose to improve robustness by a multi-task training, which extends supervised semantic segmentation by a self-supervised monocular depth estimation on unlabeled videos. This additional task is only performed during training to improve the semantic segmentation model's robustness at test time under several input perturbations. Moreover, we even find that our joint training approach also improves the performance of the model on the original (supervised) semantic segmentation task. Our evaluation exhibits a particular novelty in that it allows to mutually compare the effect of input noises and adversarial attacks on the robustness of the semantic segmentation. We show the effectiveness of our method on the Cityscapes dataset, where our multi-task training approach consistently outperforms the single-task semantic segmentation baseline in terms of both robustness vs. noise and in terms of adversarial attacks, without the need for depth labels in training.

Improved Noise and Attack Robustness for Semantic Segmentation by Using Multi-Task Training with Self-Supervised Depth Estimation.

During the transition to wideband speech telephony, artificial bandwidth extension (ABE) could help to preserve customer satisfaction by enhancing speech quality in case of narrowband (NB) calls. However, the assessment of speech quality for ABE systems is still an open question. In the literature, instrumental measures are often used to judge the quality of ABE solutions. When subjective listening tests are considered, they most often use a comparison category rating (CCR) scale and, more rarely, an absolute category rating (ACR) scale. This paper investigates the relevance of instrumental and subjective assessment methods for ABE systems. An ACR and a CCR test are organized. Their results are compared and discussed. Discrepancies between these two tests open the discussion for the design of a proper subjective listening test for ABE systems. Some instrumental measures are also evaluated. A poor correlation between these measures and the subjective results is observed.

Tim Fingscheidt

Papers

Analysis of the Effect of Various Input Representations for LSTM-Based Trajectory Prediction

An iterative speech model-based a priori SNR estimator.

openDD: A Large-Scale Roundabout Drone Dataset

Improved Noise and Attack Robustness for Semantic Segmentation by Using Multi-Task Training with Self-Supervised Depth Estimation.

On speech quality assessment of artificial bandwidth extension