Refine
Year of publication
Document Type
- Part of a Book (19)
- Conference Proceeding (16)
- Article (13)
- Working Paper (9)
- Book (3)
- Other (1)
- Preprint (1)
Keywords
- Gesprochene Sprache (62) (remove)
Publicationstate
- Veröffentlichungsversion (29)
- Zweitveröffentlichung (12)
- Postprint (6)
- Erstveröffentlichung (1)
Reviewstate
- Peer-Review (22)
- (Verlags)-Lektorat (19)
- Verlags-Lektorat (1)
Publisher
- Institut für Deutsche Sprache (6)
- de Gruyter (5)
- European Language Resources Association (4)
- European Language Resources Association (ELRA) (4)
- Leibniz-Institut für Deutsche Sprache (IDS) (3)
- Linköping University Electronic Press (3)
- Verlag für Gesprächsforschung (3)
- Wilhelm Fink (3)
- Leibniz-Institut für Deutsche Sprache (2)
- Lexical Computing CZ s.r.o. (2)
Im vorliegenden Artikel wird ein Überblick über das von der DFG geförderte Projekt Zugänge zu multimodalen Korpora gesprochener Sprache – Vernetzung und zielgruppenspezifische Ausdifferenzierung (ZuMult) gegeben. Dabei wird zunächst auf die Sprachdaten und auf die technische Basis der Applikationen eingegangen, die dem Projekt zugrunde liegen. Im Anschluss werden die weiteren Beiträge in diesem Themenheft von KorDaF kurz vorgestellt. Übergeordnetes Thema von ZuMult ist die Verbesserung der Zugänglichkeit von digitalen mündlichen Sprachdaten für verschiedene Anwendungen und Zielgruppen, wobei der Fokus dieses Themenhefts auf Applikationen und Anwender:innen aus der Fremdsprachendidaktik und der DaF-/DaZ-Forschung und -Lehre liegt. Die einzelnen Beiträge beleuchten zentrale methodische und/oder technische Aspekte dieses Themas und beschreiben die Architektur und verschiedene prototypische Anwendungen, die das Projekt entwickelt hat.
Transkriptionswerkzeuge sind spezialisierte Softwaretools für die Transkription und Annotation von Audio- oder Videoaufzeichnungen gesprochener Sprache. Dieses Kapitel erklärt einleitend, worin der zusätzliche Nutzen solcher Werkzeuge gegenüber einfacher Textverarbeitungssoftware liegt, und gibt dann einen Überblick über grundlegende Prinzipien und einige weitverbreitete Tools dieser Art. Am Beispiel der Editoren FOLKER und OrthoNormal wird schließlich der praktische Einsatz zweier Werkzeuge in den Arbeitsabläufen eines Korpusprojekts illustriert.
As a part of the ZuMult-project, we are currently modelling a backend architecture that should provide query access to corpora from the Archive of Spoken German (AGD) at the Leibniz-Institute for the German Language (IDS). We are exploring how to reuse existing search engine frameworks providing full text indices and allowing to query corpora by one of the corpus query languages (QLs) established and actively used in the corpus research community. For this purpose, we tested MTAS - an open source Lucene-based search engine for querying on text with multilevel annotations. We applied MTAS on three oral corpora stored in the TEI-based ISO standard for transcriptions of spoken language (ISO 24624:2016). These corpora differ from the corpus data that MTAS was developed for, because they include interactions with two and more speakers and are enriched, inter alia, with timeline-based annotations. In this contribution, we report our test results and address issues that arise when search frameworks originally developed for querying written corpora are being transferred into the field of spoken language.
The newest generation of speech technology caused a huge increase of audio-visual data nowadays being enhanced with orthographic transcripts such as in automatic subtitling in online platforms. Research data centers and archives contain a range of new and historical data, which are currently only partially transcribed and therefore only partially accessible for systematic querying. Automatic Speech Recognition (ASR) is one option of making that data accessible. This paper tests the usability of a state-of-the-art ASR-System on a historical (from the 1960s), but regionally balanced corpus of spoken German, and a relatively new corpus (from 2012) recorded in a narrow area. We observed a regional bias of the ASR-System with higher recognition scores for the north of Germany vs. lower scores for the south. A detailed analysis of the narrow region data revealed – despite relatively high ASR-confidence – some specific word errors due to a lack of regional adaptation. These findings need to be considered in decisions on further data processing and the curation of corpora, e.g. correcting transcripts or transcribing from scratch. Such geography-dependent analyses can also have the potential for ASR-development to make targeted data selection for training/adaptation and to increase the sensitivity towards varieties of pluricentric languages.
The newest generation of speech technology caused a huge increase of audio-visual data nowadays being enhanced with orthographic transcripts such as in automatic subtitling in online platforms. Research data centers and archives contain a range of new and historical data, which are currently only partially transcribed and therefore only partially accessible for systematic querying. Automatic Speech Recognition (ASR) is one option of making that data accessible. This paper tests the usability of a state-of-the-art ASR-System on a historical (from the 1960s), but regionally balanced corpus of spoken German, and a relatively new corpus (from 2012) recorded in a narrow area. We observed a regional bias of the ASR-System with higher recognition scores for the north of Germany vs. lower scores for the south. A detailed analysis of the narrow region data revealed – despite relatively high ASR-confidence – some specific word errors due to a lack of regional adaptation. These findings need to be considered in decisions on further data processing and the curation of corpora, e.g. correcting transcripts or transcribing from scratch. Such geography-dependent analyses can also have the potential for ASR-development to make targeted data selection for training/adaptation and to increase the sensitivity towards varieties of pluricentric languages.
This contribution presents the background, design and results of a study of users of three oral corpus platforms in Germany. Roughly 5.000 registered users of the Database for Spoken German (DGD), the GeWiss corpus and the corpora of the Hamburg Centre for Language Corpora (HZSK) were asked to participate in a user survey. This quantitative approach was complemented by qualitative interviews with selected users. We briefly introduce the corpus resources involved in the study in section 2. Section 3 describes the methods employed in the user studies. Section 4 summarizes results of the studies focusing on selected key topics. Section 5 attempts a generalization of these results to larger contexts.
This paper describes EXMARaLDA, an XML-based framework for the construction, dissemination and analysis of corpora of spoken language transcriptions. Departing from a prototypical example of a “partitur” (musical score) transcription, the EXMARaLDA “single timeline, multiple tiers” data model and format is presented alongside with the EXMARaLDA Partitur-Editor, a tool for inputting and visualizing such data. This is followed by a discussion of the interaction of EXMARaLDA with other frameworks and tools that work with similar data models. Finally, this paper presents an extension of the “single timeline, multiple tiers” data model and describes its application within the EXMARaLDA system.