Christoph Draxler

WebTranscribe – an extensible web-based speech annotation framework

WebTranscribe is a platform independent and extensible web-based annotation framework for speech research and spoken language technology. The framework consists of an annotation editor front-end running as a Java Web Start application on a client computer, and a DBMS on a server. The framework implements a “select – annotate – save” annotation workflow. The annotation capabilities are determined by annotation editors, implemented as plug-ins to the general framework. An annotation configuration generally consists of an editor, editing buttons, a signal display and a quality assessment panel. A configuration file determines which plug-ins to use for a given annotation project. WebTranscribe has been used in numerous projects at BAS and has reached a mature state now. The software is freely available [19].

An Acoustic Analysis of the Vowel Space in Young and Old Cochlear-Implant Speakers

The main purpose of this study was to compare acoustically the vowel spaces of two groups of cochlear implantees (CI) with two age-matched normal hearing groups. Five young test persons (15–25 years) and five older test persons (55–70 years) with CI and two control groups of the same age with normal hearing were recorded. The speech material consisted of five German vowels V = /aː, eː, iː, oː, uː/ in bilabial and alveolar contexts. The results showed no differences between the two groups on Euclidean distances for the first formant frequency. In contrast, Euclidean distances for F2 of the CI group were shorter than those of the control group, causing their overall vowel space to be compressed. The main differences between the groups are interpreted in terms of the extent to which the formants are associated with visual cues to the vowels. Further results were partially longer vowel durations for the CI speakers.

A multi-level description of date expressions in German telephone speech

The ability to efficiently and reliably process date expressions is crucial to many speech-based applications. A multi-level description which contains the syntactic deep structure, the orthographic surface form, a citation form representation, and the phonetic transcription is proposed. With this representation, high-level constraints, e.g. on syntactic structure, can be exploited to restrict the search space on the lower levels. This multi-level representation is applied to read and spontaneous date expressions of the German SpeechDat(M) telephone speech corpus, and the results of an analysis of the transcriptions of 3000 recordings are presented.

Towards the next generation of speech tools and corpora

This special edition picks up the theme 16 years after Bird and Harrington (2001) of current developments in software tools for processing speech and language data. The main objective now is much as it was then: to design and make freely available tools that are independent of the research task and computing environment for creating, annotating, querying, and analysing data from extensive speech and language corpora that often originate from a wide range of disciplinary perspectives in the speech sciences. Since then, the advances in web-technology combined with greater processing power and data storage have resulted in what Schiel and Kisler (2017) refer to as a paradigm shift in developing software tools for speech and language corpora (see also predictions already made in this direction by Draxler (1997) through the development of his WWWTranscribe tool). There have also been major changes in the nature of the data that are analysed in at least two ways. Firstly, in terms of the disciplines that the development of speech and language corpora brings together: as Cassidy and Estival (2017) note, these encompass at the very least ’acoustic phonetics, speech technology, natural language processing, lexicography, socio-linguistics and linguistics more generally, but also include aspects of psychology and musicology’. Secondly, in terms of quantity: recording, annotating, analysing and processing the 3.1 million infant vocalisations referred to in Beckman et al. (2017) of nearly 1500 day-long recordings (at 2 h of processing time per day) would have been scarcely possible back in 2001. The major paradigm shift is that emerging web technologies and standards foster the development of web services that complement or even replace specialised stand-alone tools for processing speech and language data. The advantages of a web-based approach as also outlined in Cassidy and Estival (2017), Schiel and Kisler (2017), and Winkelmann et al. (2017) are clear: because the tools are run within a web-browser, they are platform-independent, thereby removing both the need for programmers to update tools separately on each platform and for users to reinstall the tools locally after system upgrades. There are also some disadvantages: ubiquitous and high-speed network access is necessary, access to the local machine is restricted for security reasons, there still are browser incompatibilities, and there are legal issues when sensitive data have to be transferred via the network (see a brief discussion in Schiel and Kisler 2017). Web-based solutions have nevertheless led to an increasing democratisation of speech and language analysis: on the one hand, the availability of high-quality open source software for visualisation and analysis has made it easier for researchers and students of speech and language processing to process large amounts of speech and language data; on the other, the familiarity and ubiquity of the web has led to a standardised work flow and data management that facilitates access to and reuse of speech data. Advances in hardware technology, reduced cost, and the adaptation of novel techniques also contributed to this democratisation. The contributions in this volume reflect the technological and methodological developments since 2001. Although each article has a specific thematic focus, the individual articles are linked by common challenges, technological requirements and data structures.