Exploiting the large-scale German Broadcast Corpus to boost the Fraunhofer IAIS Speech Recognition System

Michael Stadtschnitzer, Jochen Schwenninger, Daniel Stein, Joachim Koehler


Abstract
In this paper we describe the large-scale German broadcast corpus (GER-TV1000h) containing more than 1,000 hours of transcribed speech data. This corpus is unique in the German language corpora domain and enables significant progress in tuning the acoustic modelling of German large vocabulary continuous speech recognition (LVCSR) systems. The exploitation of this huge broadcast corpus is demonstrated by optimizing and improving the Fraunhofer IAIS speech recognition system. Due to the availability of huge amount of acoustic training data new training strategies are investigated. The performance of the automatic speech recognition (ASR) system is evaluated on several datasets and compared to previously published results. It can be shown that the word error rate (WER) using a larger corpus can be reduced by up to 9.1 % relative. By using both larger corpus and recent training paradigms the WER was reduced by up to 35.8 % relative and below 40 % absolute even for spontaneous dialectal speech in noisy conditions, making the ASR output a useful resource for subsequent tasks like named entity recognition also in difficult acoustic situations.
Anthology ID:
L14-1664
Volume:
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)
Month:
May
Year:
2014
Address:
Reykjavik, Iceland
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
3887–3890
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/858_Paper.pdf
DOI:
Bibkey:
Cite (ACL):
Michael Stadtschnitzer, Jochen Schwenninger, Daniel Stein, and Joachim Koehler. 2014. Exploiting the large-scale German Broadcast Corpus to boost the Fraunhofer IAIS Speech Recognition System. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3887–3890, Reykjavik, Iceland. European Language Resources Association (ELRA).
Cite (Informal):
Exploiting the large-scale German Broadcast Corpus to boost the Fraunhofer IAIS Speech Recognition System (Stadtschnitzer et al., LREC 2014)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2014/pdf/858_Paper.pdf