Detail publikace
BUT system for low resource Indian language ASR
PULUGUNDLA, B. BASKAR, M. KESIRAJU, S. EGOROVA, E. KARAFIÁT, M. BURGET, L. ČERNOCKÝ, J.
Originální název
BUT system for low resource Indian language ASR
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
This paper describes the BUT Jilebi teams speech recognitionsystems created for the 2018 low resource speech recognitionchallenge for Indian languages. We investigate modifications ofmultilingual time-delay neural network (TDNN) architectureswith transfer learning and compare them to bi-directionalresidual memory networks (BRMN) and bi-directional LSTM.Our best submission based on system combination achievedword error rates of 13.92% (Tamil), 14.71% (Telugu) and14.06% (Gujarati). We present the details of submitted systemsand also the post-evaluation analysis done for lexicon discoveryusing unsupervised word segmentation.
Klíčová slova
Indian languages, low resource ASR, multilingual, LF-MMI
Autoři
PULUGUNDLA, B.; BASKAR, M.; KESIRAJU, S.; EGOROVA, E.; KARAFIÁT, M.; BURGET, L.; 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
3182
Strany do
3186
Strany počet
5
URL
BibTex
@inproceedings{BUT155101,
author="Bhargav {Pulugundla} and Murali Karthick {Baskar} and Santosh {Kesiraju} and Ekaterina {Egorova} and Martin {Karafiát} and Lukáš {Burget} and Jan {Černocký}",
title="BUT system for low resource Indian language ASR",
booktitle="Proceedings of Interspeech 2018",
year="2018",
journal="Proceedings of Interspeech",
volume="2018",
number="9",
pages="3182--3186",
publisher="International Speech Communication Association",
address="Hyderabad",
doi="10.21437/Interspeech.2018-1302",
issn="1990-9772",
url="https://www.isca-speech.org/archive/Interspeech_2018/abstracts/1302.html"
}
Dokumenty