Brno University of Technology

About: Brno University of Technology is a education organization based out in Brno, Czechia. It is known for research contribution in the topics: Computer science & Fracture mechanics. The organization has 6339 authors who have published 15226 publications receiving 194088 citations. The organization is also known as: Vysoké učení technické v Brně & BUT.

The development of the AMI system for the transcription of speech in meetings

Abstract: The automatic processing of speech collected in conference style meetings has attracted considerable interest with several large scale projects devoted to this area. This paper describes the development of a baseline automatic speech transcription system for meetings in the context of the AMI (Augmented Multiparty Interaction) project. We present several techniques important to processing of this data and show the performance in terms of word error rates (WERs). An important aspect of transcription of this data is the necessary flexibility in terms of audio pre-processing. Real world systems have to deal with flexible input, for example by using microphone arrays or randomly placed microphones in a room. Automatic segmentation and microphone array processing techniques are described and the effect on WERs is discussed. The system and its components presented in this paper yield competitive performance and form a baseline for future research in this domain.

Convolutive Bottleneck Network features for LVCSR

Abstract: In this paper, we focus on improvements of the bottleneck ANN in a Tandem LVCSR system. First, the influence of training set size and the ANN size is evaluated. Second, a very positive effect of linear bottleneck is shown. Finally a Convolutive Bottleneck Network is proposed as extension of the current state-of-the-art Universal Context Network. The proposed training method leads to 5.5% relative reduction of WER, compared to the Universal Context ANN baseline. The relative improvement compared to the 5-layer single-bottleneck network is 17.7%. The dataset ctstrain07 composed of more than 2000 hours of English Conversational Telephone Speech was used for the experiments. The TNet toolkit with CUDA GPGPU implementation was used for fast training.

Programs with lists are counter automata

Abstract: We address the verification problem of programs manipulating one-selector linked data structures. We propose a new automated approach for checking safety and termination for these programs. Our approach is based on using counter automata as accurate abstract models: control states correspond to abstract heap graphs where list segments without sharing are collapsed, and counters are used to keep track of the number of elements in these segments. This allows to apply automatic analysis techniques and tools for counter automata in order to verify list programs. We show the effectiveness of our approach, in particular by verifying automatically termination of some sorting programs.

Probabilistic Noise2Void: Unsupervised Content-Aware Denoising

Abstract: Today, Convolutional Neural Networks (CNNs) are the leading method for image denoising. They are traditionally trained on pairs of images, which are often hard to obtain for practical applications. This motivates self-supervised training methods such as Noise2Void (N2V) that operate on single noisy images. Self-supervised methods are, unfortunately, not competitive with models trained on image pairs. Here, we present Probabilistic Noise2Void (PN2V), a method to train CNNs to predict per-pixel intensity distributions. Combining these with a suitable description of the noise, we obtain a complete probabilistic model for the noisy observations and true signal in every pixel. We evaluate PN2V on publicly available microscopy datasets, under a broad range of noise regimes, and achieve competitive results with respect to supervised state-of-the-art methods.