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

A method for signal reception in a digital communication system is disclosed, in which an output background signal is generated from received characteristics which characterise a transmitter-side background signal in a background signal generator. An output background signal is thus generated in the background signal generator from the received characteristics with a given bandwidth, which is greater than a bandwidth of the background signal characterised by the received characteristics.

Method for signal reception

In this work we present two novel methods to improve speech residuals for speech enhancement. A deep neural network is used to enhance residual signals in the cepstral domain, thereby exceeding a former cepstral excitation manipulation (CEM) approach in different ways: One variant provides higher speech component quality by 0.1 PESQ points in low-SNR conditions, while another one delivers substantially higher noise attenuation by 1.5 dB, without loss of speech component quality or speech intelligibility. Compared to traditional speech enhancement based on the decision-directed (DD) a priori SNR estimation, a gain of even up to 3.5 dB noise attenuation is obtained. A semi-formal comparative category rating (CCR) subjective listening test confirms the superiority of the proposed approach over DD by 0.25 CMOS points (or even by 0.48 if two outlier subjects are not considered).

Improvement of Speech Residuals for Speech Enhancement

For wireless transmission systems for high-quality digital speech signals a low end-to-end delay is desired Furthermore, signals transmitted over wireless channels may suffer from error bursts which would lead to sustained periods of annoying artifacts if no appropriate error concealment strategies are employed In this contribution we present a Bayesian approach to delayless soft-decision speech decoding for wireless burst channels which can be applied to, e g, wireless microphones Besides channel reliability information we only exploit residual redundancy in the speech signal for the computation of prediction probabilities within a Bayesian framework In contrast to existing (narrowband) speech error concealment techniques, we employ higher-order adaptive predictors in order to compute the prediction probabilities in this work Simulations with representative speech data transmitted over burst channels demonstrate a notable increase in signal quality

NLMS-Supported Decoding of High-Quality Speech for Burst Channels

Robust MPEG-4 High-Efficiency AAC With Fixed- and Variable-Length Soft-Decision Decoding

In recent years, semantic segmentation has taken benefit from various works in computer vision. Inspired by the very versatile CycleGAN architecture, we combine semantic segmentation with the concept of cycle consistency to enable a multitask training protocol. However, learning is largely prevented by the so-called steganography effect, which expresses itself as watermarks in the latent segmentation domain, making image reconstruction a too easy task. To combat this, we propose a noise injection, based either on quantization noise or on Gaussian noise addition to avoid this disadvantageous information flow in the cycle architecture. We find that noise injection significantly reduces the generation of watermarks and thus allows the recognition of highly relevant classes such as “traffic signs”, which are hardly detected by the ERFNet baseline. We report mIoU and PSNR results on the Cityscapes dataset for semantic segmentation and image reconstruction, respectively. The proposed methodology allows to achieve an mIoU improvement on the Cityscapes validation set of 5.7 % absolute over the same CycleGAN without noise injection, and still an absolute 4.9 % over the ERFNet non-cyclic baseline.

Tim Fingscheidt

Papers

Method for signal reception

Improvement of Speech Residuals for Speech Enhancement

NLMS-Supported Decoding of High-Quality Speech for Burst Channels

Robust MPEG-4 High-Efficiency AAC With Fixed- and Variable-Length Soft-Decision Decoding

Improving Performance of Semantic Segmentation CycleGANs by Noise Injection into the Latent Segmentation Space