The 2017 KIT IWSLT Speech-to-Text Systems for English and German
Thai-Son Nguyen, Markus Müller, Matthias Sperber, Thomas Zenkel, Sebastian Stüker, Alex Waibel
Abstract
This paper describes our German and English Speech-to-Text (STT) systems for the 2017 IWSLT evaluation campaign. The campaign focuses on the transcription of unsegmented lecture talks. Our setup includes systems using both the Janus and Kaldi frameworks. We combined the outputs using both ROVER [1] and confusion network combination (CNC) [2] to achieve a good overall performance. The individual subsystems are built by using different speaker-adaptive feature combination (e.g., lMEL with i-vector or bottleneck speaker vector), acoustic models (GMM or DNN) and speaker adaptation (MLLR or fMLLR). Decoding is performed in two stages, where the GMM and DNN systems are adapted on the combination of the first stage outputs using MLLR, and fMLLR. The combination setup produces a final hypothesis that has a significantly lower WER than any of the individual sub-systems. For the English lecture task, our best combination system has a WER of 8.3% on the tst2015 development set while our other combinations gained 25.7% WER for German lecture tasks.- Anthology ID:
- 2017.iwslt-1.9
- Volume:
- Proceedings of the 14th International Conference on Spoken Language Translation
- Month:
- December 14-15
- Year:
- 2017
- Address:
- Tokyo, Japan
- Editors:
- Sakriani Sakti, Masao Utiyama
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- International Workshop on Spoken Language Translation
- Note:
- Pages:
- 60–64
- Language:
- URL:
- https://aclanthology.org/2017.iwslt-1.9
- DOI:
- Cite (ACL):
- Thai-Son Nguyen, Markus Müller, Matthias Sperber, Thomas Zenkel, Sebastian Stüker, and Alex Waibel. 2017. The 2017 KIT IWSLT Speech-to-Text Systems for English and German. In Proceedings of the 14th International Conference on Spoken Language Translation, pages 60–64, Tokyo, Japan. International Workshop on Spoken Language Translation.
- Cite (Informal):
- The 2017 KIT IWSLT Speech-to-Text Systems for English and German (Nguyen et al., IWSLT 2017)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2017.iwslt-1.9.pdf