Publication Details

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

WIESNER Matthew, LIU Chunxi, ONDEL Yang Lucas Antoine Francois, HARMAN Craig, MANOHAR Vimal, TRMAL Jan, HUANG Zhongqiang, DEHAK Najim and KHUDANPUR Sanjeev. Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages. In: Proceedings of Interspeech. Hyderabad: International Speech Communication Association, 2018, pp. 2052-2056. ISSN 1990-9772. Available from: https://www.isca-speech.org/archive/Interspeech_2018/abstracts/1836.html
Czech title
Automatické rozpoznávání řeči a identifikace témat pro jazyky s téměř neexistujícími zdroji
Type
conference paper
Language
english
Authors
Wiesner Matthew (JHU)
Liu Chunxi (JHU)
Ondel Yang Lucas Antoine Francois, Mgr., Ph.D. (DCGM FIT BUT)
Harman Craig (JHU)
Manohar Vimal (JHU)
Trmal Jan (JHU)
Huang Zhongqiang (Raytheon BBN)
Dehak Najim (JHU)
Khudanpur Sanjeev (JHU)
URL
Keywords

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

Abstract

Automatic speech recognition (ASR) systems often need to be developed for extremely low-resource languages to serve enduses such as audio content categorization and search. While universal phone recognition is natural to consider when no transcribed speech 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 to be studied, particularly with state-of-the-art DNN-based acoustic models. The DARPA LORELEI program provides a framework for such very-low-resource ASR studies, and provides an extrinsic metric for evaluating ASR performance in a humanitarian assistance, disaster relief setting. This paper presents our Kaldi-based systems for the program, which employ a universal phone modeling approach to ASR, and describes recipes for very rapid adaptation of this universal ASR system. The results we obtain significantly outperform results obtained by many competing approaches on the NIST LoReHLT 2017 Evaluation datasets

Published
2018
Pages
2052-2056
Journal
Proceedings of Interspeech - on-line, vol. 2018, no. 9, ISSN 1990-9772
Proceedings
Proceedings of Interspeech
Conference
Interspeech Conference, Hyderabad, India, IN
Publisher
International Speech Communication Association
Place
Hyderabad, IN
DOI
UT WoS
000465363900431
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB12241,
   author = "Matthew Wiesner and Chunxi Liu and Francois Antoine Lucas Yang Ondel and Craig Harman and Vimal Manohar and Jan Trmal and Zhongqiang Huang and Najim Dehak and Sanjeev Khudanpur",
   title = "Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages",
   pages = "2052--2056",
   booktitle = "Proceedings of Interspeech",
   journal = "Proceedings of Interspeech - on-line",
   volume = 2018,
   number = 9,
   year = 2018,
   location = "Hyderabad, IN",
   publisher = "International Speech Communication Association",
   ISSN = "1990-9772",
   doi = "10.21437/Interspeech.2018-1836",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12241"
}
Back to top