Publication Details

Twenty-Five Years of Evolution in Speech and Language Processing

YU Dong, GONG Yifan, PICHENY Michael Alan, RAMABHADRAN Bhuvana, HAKKANI-TÜR Dilek, PRASAD Rohit, ZEN Heiga, SKOGLUND Jan, ČERNOCKÝ Jan, BURGET Lukáš and MOHAMED Abdelrahman. Twenty-Five Years of Evolution in Speech and Language Processing. IEEE Signal Processing Magazine, vol. 40, no. 5, 2023, pp. 27-39. ISSN 1558-0792. Available from: https://ieeexplore.ieee.org/document/10188908
Czech title
Dvacet pět let evoluce ve zpracování řeči a jazyka
Type
journal article
Language
english
Authors
Yu Dong (Tencent AI Lab)
Gong Yifan ()
Picheny Michael Alan ()
Ramabhadran Bhuvana (Google, Inc.)
Hakkani-tür Dilek ()
Prasad Rohit ()
Zen Heiga ()
Skoglund Jan ()
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Mohamed Abdelrahman ()
URL
Keywords

speech, language, processing

Abstract

In this article, we summarize the evolution of speech and language processing (SLP) in the past 25 years. We first provide a snapshot of popular research topics and the associated state of the art (SOTA) in various subfields of SLP 25 years ago, and then highlight the shift in research topics over the years. We describe the major breakthroughs in each of the subfields and the main driving forces that led us to the SOTA today. Societal impacts and potential future directions are also discussed.

Published
2023
Pages
27-39
Journal
IEEE Signal Processing Magazine, vol. 40, no. 5, ISSN 1558-0792
Publisher
IEEE Signal Processing Society
DOI
10.1109/MSP.2023.3266155
UT WoS
001036023400002
EID Scopus
2-s2.0-85165877407
BibTeX 
@ARTICLE{FITPUB13058,
   author = "Dong Yu and Yifan Gong and Alan Michael Picheny and Bhuvana Ramabhadran and Dilek Hakkani-t{\"{u}}r and Rohit Prasad and Heiga Zen and Jan Skoglund and Jan \v{C}ernock\'{y} and Luk\'{a}\v{s} Burget and Abdelrahman Mohamed",
   title = "Twenty-Five Years of Evolution in Speech and Language Processing",
   pages = "27--39",
   journal = "IEEE Signal Processing Magazine",
   volume = 40,
   number = 5,
   year = 2023,
   ISSN = "1558-0792",
   doi = "10.1109/MSP.2023.3266155",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/13058"
}
Back to top