Detail výsledku

Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages

WIESNER, M.; LIU, C.; ONDEL YANG, L.; HARMAN, C.; MANOHAR, V.; TRMAL, J.; HUANG, Z.; DEHAK, N.; KHUDANPUR, S. Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages. In Proceedings of Interspeech. Proceedings of Interspeech. Hyderabad: International Speech Communication Association, 2018. no. 9, p. 2052-2056. ISSN: 1990-9772.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Wiesner Matthew, PhD., FIT (FIT)
Liu Chunxi, FIT (FIT)
ONDEL YANG, L.
HARMAN, C.
MANOHAR, V.
Trmal Jan, Ing., Ph.D.
HUANG, Z.
Dehak Najim
Khudanpur Sanjeev
Abstrakt

Automatic speech recognition (ASR) systems often need to bedeveloped for extremely low-resource languages to serve endusessuch as audio content categorization and search. Whileuniversal phone recognition is natural to consider when no transcribedspeech is available to train an ASR system in a language,adapting universal phone models using very small amounts(minutes rather than hours) of transcribed speech also needs tobe studied, particularly with state-of-the-art DNN-based acousticmodels. The DARPA LORELEI program provides a frameworkfor such very-low-resource ASR studies, and provides anextrinsic metric for evaluating ASR performance in a humanitarianassistance, disaster relief setting. This paper presentsour Kaldi-based systems for the program, which employ a universalphone modeling approach to ASR, and describes recipesfor very rapid adaptation of this universal ASR system. Theresults we obtain significantly outperform results obtained bymany competing approaches on the NIST LoReHLT 2017 Evaluationdatasets

Klíčová slova

Universal acoustic models, topic identification,cross-language information retrieval, transfer learning, lowresourcespeech recognition

URL
Rok
2018
Strany
2052–2056
Časopis
Proceedings of Interspeech, roč. 2018, č. 9, ISSN 1990-9772
Sborník
Proceedings of Interspeech
Konference
Interspeech Conference
Vydavatel
International Speech Communication Association
Místo
Hyderabad
DOI
10.21437/Interspeech.2018-1836
UT WoS
000465363900431
EID Scopus
2-s2.0-85054975668
BibTeX 
@inproceedings{BUT163405,
  author="WIESNER, M. and LIU, C. and ONDEL YANG, L. and HARMAN, C. and MANOHAR, V. and TRMAL, J. and HUANG, Z. and DEHAK, N. and KHUDANPUR, S.",
  title="Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages",
  booktitle="Proceedings of Interspeech",
  year="2018",
  journal="Proceedings of Interspeech",
  volume="2018",
  number="9",
  pages="2052--2056",
  publisher="International Speech Communication Association",
  address="Hyderabad",
  doi="10.21437/Interspeech.2018-1836",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/Interspeech_2018/abstracts/1836.html"
}
Soubory
Projekty
DARPA Jazyky s omezenými zdroji pro potenciální krizové situace (LORELEI) - Využití jazykové informace pro situační povědomí (ELISA, University of Southern California, zahájení: 2015-09-01, ukončení: 2020-03-31, ukončen
Zpracování, zobrazování a analýza multimediálních a 3D dat, VUT, Vnitřní projekty VUT, FIT-S-17-3984, zahájení: 2017-03-01, ukončení: 2020-02-29, ukončen
Výzkumné skupiny
Výzkumná skupina dolování dat z řeči BUT Speech@FIT (VZ SPEECH)
Pracoviště
Ústav počítačové grafiky a multimédií (UPGM)
Nahoru