Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Using Automatic Speech Recognition in Spoken Corpus Curation

: Gorisch, Jan; Gref, Michael; Schmidt, Thomas

Volltext urn:nbn:de:0011-n-5927881 (415 KByte PDF)
MD5 Fingerprint: 93f92520217d08ee11b9c1de317e84bd
(CC) by-nc
Erstellt am: 9.6.2020

Calzolari, N. ; European Language Resources Association -ELRA-, Paris:
12th Language Resources and Evaluation Conference, LREC 2020. Proceedings. Online resource : May 11-16, 2020, Palais du Pharo, Marseille, France : conference proceedings
Paris: ELRA, 2020
ISBN: 979-10-95546-34-4
Language Resources and Evaluation Conference (LREC) <12, 2020, Marseille/cancelled>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IAIS ()
oral corpora; automatic transcription; ASR; corpus curation; pluricentric; spoken German; Ripuarian

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 f or 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.