Detail publikace

Lightly supervised vs. semi-supervised training of acoustic model on Luxembourgish for low-resource automatic speech recognition

VESELÝ, K. PERALES, C. SZŐKE, I. LUQUE, J. ČERNOCKÝ, J.

Originální název

Lightly supervised vs. semi-supervised training of acoustic model on Luxembourgish for low-resource automatic speech recognition

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

In this work, we focus on exploiting inexpensive data in order to to improve the DNN acoustic model for ASR. We explore two strategies: The first one uses untranscribed data from the target domain. The second one is related to the proper selection of excerpts from imperfectly transcribed out-of-domain public data, as parliamentary speeches. We found out that both approaches lead to similar results, making them equally beneficial for practical use. The Luxembourgish ASR seed system had a 38.8% WER and it improved by roughly 4% absolute, leading to 34.6% for untranscribed and 34.9% for lightlysupervised data. Adding both databases simultaneously led to 34.4% WER, which is only a small improvement. As a secondary research topic, we experiment with semi-supervised state-level minimum Bayes risk (sMBR) training. Nonetheless, for sMBR we saw no improvement from adding the automatically transcribed target data, despite that similar techniques yield good results in the case of cross-entropy (CE) training.

Klíčová slova

Luxembourgish, call centers, speech recognition, low-resourced ASR, unsupervised training

Autoři

VESELÝ, K.; PERALES, C.; SZŐKE, I.; LUQUE, J.; ČERNOCKÝ, J.

Vydáno

2. 9. 2018

Nakladatel

International Speech Communication Association

Místo

Hyderabad

ISSN

1990-9772

Periodikum

Proceedings of Interspeech

Ročník

2018

Číslo

9

Stát

Francouzská republika

Strany od

2883

Strany do

2887

Strany počet

5

URL

BibTex

@inproceedings{BUT155104,
  author="VESELÝ, K. and PERALES, C. and SZŐKE, I. and LUQUE, J. and ČERNOCKÝ, J.",
  title="Lightly supervised vs. semi-supervised training of acoustic model on Luxembourgish for low-resource automatic speech recognition",
  booktitle="Proceedings of Interspeech 2018",
  year="2018",
  journal="Proceedings of Interspeech",
  volume="2018",
  number="9",
  pages="2883--2887",
  publisher="International Speech Communication Association",
  address="Hyderabad",
  doi="10.21437/Interspeech.2018-2361",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/Interspeech_2018/abstracts/2361.html"
}

Dokumenty