Detail výsledku

Topic identification of spoken documents using unsupervised acoustic unit discovery

KESIRAJU, S.; PAPPAGARI, R.; ONDEL YANG, L.; BURGET, L.; DEHAK, N.; KHUDANPUR, S.; ČERNOCKÝ, J.; GANGASHETTY, S. Topic identification of spoken documents using unsupervised acoustic unit discovery. In Proceedings of ICASSP 2017. New Orleans: IEEE Signal Processing Society, 2017. p. 5745-5749. ISBN: 978-1-5090-4117-6.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Kesiraju Santosh, Ph.D., UPGM (FIT)
Pappagari Raghavendra
Ondel Lucas Antoine Francois, Mgr., Ph.D., UPGM (FIT)
Burget Lukáš, doc. Ing., Ph.D., UPGM (FIT)
Dehak Najim
Khudanpur Sanjeev
Černocký Jan, prof. Dr. Ing., UPGM (FIT)
Gangashetty Suryakanth V
Abstrakt

This paper investigates the application of unsupervised acoustic unitdiscovery for topic identification (topic ID) of spoken audio documents.The acoustic unit discovery method is based on a nonparametricBayesian phone-loop model that segments a speech utteranceinto phone-like categories. The discovered phone-like (acoustic)units are further fed into the conventional topic ID framework.Using multilingual bottleneck features for the acoustic unit discovery,we show that the proposed method outperforms other systemsthat are based on cross-lingual phoneme recognizer.

Klíčová slova

topic identification, acoustic unit discovery, unsupervisedlearning, non-parametric Bayesian models

URL
Rok
2017
Strany
5745–5749
Sborník
Proceedings of ICASSP 2017
Konference
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
ISBN
978-1-5090-4117-6
Vydavatel
IEEE Signal Processing Society
Místo
New Orleans
DOI
10.1109/ICASSP.2017.7953257
UT WoS
000414286205181
EID Scopus
2-s2.0-85023738949
BibTeX 
@inproceedings{BUT144450,
  author="Santosh {Kesiraju} and Raghavendra {Pappagari} and Lucas Antoine Francois {Ondel} and Lukáš {Burget} and Najim {Dehak} and Sanjeev {Khudanpur} and Jan {Černocký} and Suryakanth V {Gangashetty}",
  title="Topic identification of spoken documents using unsupervised acoustic unit discovery",
  booktitle="Proceedings of ICASSP 2017",
  year="2017",
  pages="5745--5749",
  publisher="IEEE Signal Processing Society",
  address="New Orleans",
  doi="10.1109/ICASSP.2017.7953257",
  isbn="978-1-5090-4117-6",
  url="https://www.fit.vut.cz/research/publication/11470/"
}
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
IT4Innovations excellence in science, MŠMT, Národní program udržitelnosti II, LQ1602, zahájení: 2016-01-01, ukončení: 2020-12-31, ukončen
Výzkumné skupiny
Výzkumná skupina dolování dat z řeči BUT Speech@FIT (VZ SPEECH)
Pracoviště
Ústav počítačové grafiky a multimédií (UPGM)
Nahoru