Refine
Year of publication
- 2020 (8) (remove)
Document Type
- Conference Proceeding (4)
- Article (2)
- Part of a Book (2)
Is part of the Bibliography
- yes (8)
Keywords
- Korpus <Linguistik> (7)
- Gesprochene Sprache (6)
- Automatische Spracherkennung (3)
- oral corpora (3)
- ASR (2)
- Plurizentrische Sprache (2)
- Ripuarian (2)
- Sprachgeografie (2)
- Text Encoding Initiative (2)
- automatic transcription (2)
Publicationstate
Reviewstate
- Peer-Review (8)
Publisher
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.
We present web services which implement a workflow for transcripts of spoken language following the TEI guidelines, in particular ISO 24624:2016 “Language resource management – Transcription of spoken language”. The web services are available at our website and will be available via the CLARIN infrastructure, including the Virtual Language Observatory and WebLicht.
This paper addresses long-term archival for large corpora. Three aspects specific to language resources are focused, namely (1) the removal of resources for legal reasons, (2) versioning of (unchanged) objects in constantly growing resources, especially where objects can be part of multiple releases but also part of different collections, and (3) the conversion of data to new formats for digital preservation. It is motivated why language resources may have to be changed, and why formats may need to be converted. As a solution, the use of an intermediate proxy object called a signpost is suggested. The approach will be exemplified with respect to the corpora of the Leibniz Institute for the German Language in Mannheim, namely the German Reference Corpus (DeReKo) and the Archive for Spoken German (AGD).
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.
This paper presents experiments on sentence boundary detection in transcripts of spoken dialogues. Segmenting spoken language into sentence-like units is a challenging task, due to disfluencies, ungrammatical or fragmented structures and the lack of punctuation. In addition, one of the main bottlenecks for many NLP applications for spoken language is the small size of the training data, as the transcription and annotation of spoken language is by far more time-consuming and labour-intensive than processing written language. We therefore investigate the benefits of data expansion and transfer learning and test different ML architectures for this task. Our results show that data expansion is not straightforward and even data from the same domain does not always improve results. They also highlight the importance of modelling, i.e. of finding the best architecture and data representation for the task at hand. For the detection of boundaries in spoken language transcripts, we achieve a substantial improvement when framing the boundary detection problem as a sentence pair classification task, as compared to a sequence tagging approach.
Older adults are often exposed to elderspeak, a specialized speech register linked with negative outcomes. However, previous research has mainly been conducted in nursing homes without considering multiple contextual conditions. Based on a novel contextually-driven framework, we examined elderspeak in an acute general versus geriatric German hospital setting. Individuallevel information such as cognitive impairment (CI) and audio-recorded data from care interactions between 105 older patients (M = 83.2 years; 49% with severe CI) and 34 registered nurses (M = 38.9 years) were assessed. Psycholinguistic analyses were based on manual coding (k = .85 to k = .97) and computer-assisted procedures. First, diminutives (61%), collective pronouns (70%), and tag questions (97%) were detected. Second, patients’ functional impairment emerged as an important factor for elderspeak. Our study suggests that functional impairment may be a more salient trigger of stereotype activation than CI and that elderspeak deserves more attention in acute hospital settings.
Dieser Beitrag widmet sich der Beschreibung des Korpus Deutsch in Namibia (DNam), das über die Datenbank für Gesprochenes Deutsch (DGD) frei zugänglich ist. Bei diesem Korpus handelt es sich um eine neue digitale Ressource, die den Sprachgebrauch der deutschsprachigen Minderheit in Namibia sowie die zugehörigen Spracheinstellungen umfassend und systematisch dokumentiert. Wir beschreiben die Datenerhebung und die dabei angewandten Methoden (freie Gespräche, „Sprachsituationen“, semi-strukturierte Interviews), die Datenaufbereitung inklusive Transkription, Normalisierung und Tagging sowie die Eigenschaften des verfügbaren Korpus (Umfang, verfügbare Metadaten usw.) und einige grundlegende Funktionalitäten im Rahmen der DGD. Erste Forschungsergebnisse, die mithilfe der neuen Ressource erzielt wurden, veranschaulichen die vielseitige Nutzbarkeit des Korpus für Fragestellungen aus den Bereichen Kontakt-, Variations-
und Soziolinguistik.