This paper presents two toolsets for transcribing and annotating spoken language: the EXMARaLDA system, developed at the University of Hamburg, and the FOLK tools, developed at the Institute for the German Language in Mannheim. Both systems are targeted at users interested in the analysis of spontaneous, multi-party discourse. Their main user community is situated in conversation analysis, prag...

During this show & Tell event, we present the latest version of our new software VisArtico. The software allows visualizing electromagnetic articulography (EMA) data. It is intended for researchers that need to visualize the data acquired from an articulograph with no excessive processing. This software is very useful for the speech science community, makes the use of articulatory data more acc...

Deep learning techniques have demonstrated tremendous success in the speech and language processing community in recent years, establishing new state-ofthe-art performance in speech recognition, language modeling, and have shown great potential for many other natural language processing tasks. The focus of this tutorial is to provide an extensive overview on recent deep learning approaches to p...

During the past three decades, the issue of processing spectral phase has been largely neglected in speech applications. There is no doubt that the interest of speech processing community towards the use of phase information in a big spectrum of speech technologies, from automatic speech and speaker recognition to speech synthesis, from speech enhancement and source separation to speech coding,...

In many online communities, it is the norm to redact names and other sensitive text from posted screenshots. Sometimes solid bars are used; sometimes a blur or other image transform is used. We consider the effectiveness of two popular image transforms— mosaicing (also known as pixelization) and blurring— for redaction of text. Our main finding is that we can use a simple but powerful class of ...

cology is the study of life and its interactions with the physical environment. Because climate change requires rapid adaptation, new data analysis tools are essential to quantify those changes in the midst of high natural variability. Ecology is a science in which studies have been performed primarily by small groups of individuals, with data recorded and stored in notebooks. But large synthes...

AIMS To examine the impact of cancer awareness training for community-based health workers on confidence to talk about cancer, and knowledge of cancer risk factors and signs and symptoms. METHODS Community-based health workers from Sandwell, Birmingham and Solihull were invited to take part in one of 14 one-day training workshops. Trainees completed questionnaires at the beginning of the work...

Automatic prosodic events detection and annotation are important for both speech understanding and natural speech synthesis. In this paper, the complementary model method is proposed to detect prosodic events. This method discards the independent assumption between the acoustic features and the lexical and syntactic features, models not only the features of the current syllable but also the con...

Mismatched crowdsourcing derives speech transcriptions using crowd workers unfamiliar with the language being spoken. This approach has been demonstrated for isolated word transcription tasks, but never yet for continuous speech. In this work, we demonstrate mismatched crowdsourcing of continuous speech with a word error rate of under 45% in a large-vocabulary transcription task of short speech...

This paper gives an overview of the activities at the Bavarian Archive of Speech Signals (BAS) that was founded as a non-pro t organization in 1995. The main purpose of BAS is the development of a Complete Phonetic Theory (CPT) of German based on the empirical exploitation of very large databases of spoken German. However, on our way to that goal BAS will act as a focal point for all computer r...