Publication detail

MGB-3 BUT System: Low-resource ASR on Egyptian YOUTUBE data

VESELÝ, K. BASKAR, M. DIEZ SÁNCHEZ, M. BENEŠ, K.

Original Title

MGB-3 BUT System: Low-resource ASR on Egyptian YOUTUBE data

Type

conference paper

Language

English

Original Abstract

This paper presents a series of experiments we performed during our work on the MGB-3 evaluations. We both describe the submitted system, as well as the post-evaluation analysis. Our initial BLSTM-HMM system was trained on 250 hours of MGB-2 data (Al-Jazeera), it was adapted with 5 hours of Egyptian data (YouTube). We included such techniques as diarization, n-gram language model adaptation, speed perturbation of the adaptation data, and the use of all 4 correct references. The 4 references were either used for supervision with a confusion network, or we included each sentence 4x with the transcripts from all the annotators. Then, it was also helpful to blend the augmented MGB-3 adaptation data with 15 hours of MGB-2 data. Although we did not rank with our single system among the best teams in the evaluations, we believe that our analysis will be highly interesting not only for the other MGB-3 challenge participants.

Keywords

MGB-3, ASR adaptation, low-resource ASR, Egyptian Arabic, diarization

Authors

VESELÝ, K.; BASKAR, M.; DIEZ SÁNCHEZ, M.; BENEŠ, K.

Released

16. 12. 2017

Publisher

IEEE Signal Processing Society

Location

Okinawa

ISBN

978-1-5090-4788-8

Book

Proceedings of ASRU 2017

Pages from

368

Pages to

373

Pages count

6

URL

BibTex

@inproceedings{BUT144502,
  author="Karel {Veselý} and Murali Karthick {Baskar} and Mireia {Diez Sánchez} and Karel {Beneš}",
  title="MGB-3 BUT System: Low-resource ASR on Egyptian YOUTUBE data",
  booktitle="Proceedings of ASRU 2017",
  year="2017",
  pages="368--373",
  publisher="IEEE Signal Processing Society",
  address="Okinawa",
  doi="10.1109/ASRU.2017.8268959",
  isbn="978-1-5090-4788-8",
  url="https://www.fit.vut.cz/research/publication/11595/"
}