Detail výsledku

Analysis of Multilingual BLSTM Acoustic Model on Low and High Resource Languages

KARAFIÁT, M.; BASKAR, M.; VESELÝ, K.; GRÉZL, F.; BURGET, L.; ČERNOCKÝ, J. Analysis of Multilingual BLSTM Acoustic Model on Low and High Resource Languages. In Proceedings of ICASSP 2018. Calgary: IEEE Signal Processing Society, 2018. p. 5789-5793. ISBN: 978-1-5386-4658-8.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Karafiát Martin, Ing., Ph.D., UPGM (FIT)
Baskar Murali Karthick, Ing., Ph.D., UPGM (FIT)
Veselý Karel, Ing., Ph.D., UPGM (FIT)
Grézl František, Ing., Ph.D., UPGM (FIT)
Burget Lukáš, doc. Ing., Ph.D., UPGM (FIT)
Černocký Jan, prof. Dr. Ing., UPGM (FIT)
Abstrakt

The paper provides an analysis of automatic speech recognitionsystems (ASR) based on multilingual BLSTM, where weused multi-task training with separate classification layer foreach language. The focus is on low resource languages, whereonly a limited amount of transcribed speech is available. Insuch scenario, we found it essential to train the ASR systemsin a multilingual fashion and we report superior resultsobtained with pre-trained multilingual BLSTM on this task.The high resource languages are also taken into account andwe show the importance of language richness for multilingualtraining. Next, we present the performance of this techniqueas a function of amount of target language data. The importanceof including context information into BLSTM multilingualsystems is also stressed, and we report increased resilienceof large NNs to overtraining in case of multi-tasktraining.

Klíčová slova

Automatic speech recognition, Multilingualneural networks, Bidirectional Long Short Term Memory

URL
Rok
2018
Strany
5789–5793
Sborník
Proceedings of ICASSP 2018
Konference
IEEE International Conference on Acoustics, Speech and Signal Processing
ISBN
978-1-5386-4658-8
Vydavatel
IEEE Signal Processing Society
Místo
Calgary
DOI
10.1109/ICASSP.2018.8462083
UT WoS
000446384605189
EID Scopus
2-s2.0-85054214229
BibTeX 
@inproceedings{BUT155042,
  author="Martin {Karafiát} and Murali Karthick {Baskar} and Karel {Veselý} and František {Grézl} and Lukáš {Burget} and Jan {Černocký}",
  title="Analysis of Multilingual BLSTM Acoustic Model on Low and High Resource Languages",
  booktitle="Proceedings of ICASSP 2018",
  year="2018",
  pages="5789--5793",
  publisher="IEEE Signal Processing Society",
  address="Calgary",
  doi="10.1109/ICASSP.2018.8462083",
  isbn="978-1-5386-4658-8",
  url="https://www.fit.vut.cz/research/publication/11720/"
}
Soubory
Projekty
IT4Innovations excellence in science, MŠMT, Národní program udržitelnosti II, LQ1602, zahájení: 2016-01-01, ukončení: 2020-12-31, ukončen
Neuronové sítě pro zpracování signálu a dolování informací v řeči - NOSIČI, TAČR, Program na podporu aplikovaného výzkumu ZÉTA, TJ01000208, zahájení: 2018-01-01, ukončení: 2019-12-31, ukončen
Výzkumné skupiny
Výzkumná skupina dolování dat z řeči BUT Speech@FIT (VZ SPEECH)
Pracoviště
Ústav počítačové grafiky a multimédií (UPGM)
Nahoru