Publication detail

BCN2BRNO: ASR System Fusion for Albayzin 2020 Speech to Text Challenge

KOCOUR, M. CÁMBARA, G. LUQUE, J. BONET, D. FARRÚS, M. KARAFIÁT, M. VESELÝ, K. ČERNOCKÝ, J.

Original Title

BCN2BRNO: ASR System Fusion for Albayzin 2020 Speech to Text Challenge

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

This paper describes the joint effort of BUT and Telefónica Researchon the development of Automatic Speech Recognitionsystems for the Albayzin 2020 Challenge. We compare approachesbased on either hybrid or end-to-end models. In hybridmodelling, we explore the impact of a SpecAugment layeron performance. For end-to-end modelling, we used a convolutionalneural network with gated linear units (GLUs). Theperformance of such model is also evaluated with an additionaln-gram language model to improve word error rates. We furtherinspect source separation methods to extract speech fromnoisy environments (i.e. TV shows). More precisely, we assessthe effect of using a neural-based music separator named Demucs.A fusion of our best systems achieved 23.33% WER inofficial Albayzin 2020 evaluations. Aside from techniques usedin our final submitted systems, we also describe our efforts inretrieving high-quality transcripts for training.

Keywords

fusion, end-to-end model, hybrid model, semisupervised,automatic speech recognition, convolutional neuralnetwork.

Authors

KOCOUR, M.; CÁMBARA, G.; LUQUE, J.; BONET, D.; FARRÚS, M.; KARAFIÁT, M.; VESELÝ, K.; ČERNOCKÝ, J.

Released

24. 3. 2021

Publisher

International Speech Communication Association

Location

Vallaloid

Pages from

113

Pages to

117

Pages count

5

URL

https://www.isca-speech.org/archive/iberspeech_2021/kocour21_iberspeech.html

BibTex

@inproceedings{BUT175823,
  author="KOCOUR, M. and CÁMBARA, G. and LUQUE, J. and BONET, D. and FARRÚS, M. and KARAFIÁT, M. and VESELÝ, K. and ČERNOCKÝ, J.",
  title="BCN2BRNO: ASR System Fusion for Albayzin 2020 Speech to Text Challenge",
  booktitle="Proceedings of IberSPEECH 2021",
  year="2021",
  pages="113--117",
  publisher="International Speech Communication Association",
  address="Vallaloid",
  doi="10.21437/IberSPEECH.2021-24",
  url="https://www.isca-speech.org/archive/iberspeech_2021/kocour21_iberspeech.html"
}

Documents

kocour21_iberspeech.pdf