DO LEARNED SPEECH SYMBOLS FOLLOW ZIPF'S LAW?

Shinnosuke Takamichi; Hiroki Maeda; Joonyong Park; Daisuke Saito; Hiroshi Saruwatari

doi:10.1109/ICASSP48485.2024.10448331

DO LEARNED SPEECH SYMBOLS FOLLOW ZIPF'S LAW?

Shinnosuke Takamichi, Hiroki Maeda, Joonyong Park, Daisuke Saito, Hiroshi Saruwatari

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this study, we investigate whether speech symbols, learned through deep learning, follow Zipf's law, akin to natural language symbols. Zipf's law is an empirical law that delineates the frequency distribution of words, forming fundamentals for statistical analysis in natural language processing. Natural language symbols, which are invented by humans to symbolize speech content, are recognized to comply with this law. On the other hand, recent breakthroughs in spoken language processing have given rise to the development of learned speech symbols; these are data-driven symbolizations of speech content. Our objective is to ascertain whether these data-driven speech symbols follow Zipf's law, as the same as natural language symbols. Through our investigation, we aim to forge new ways for the statistical analysis of spoken language processing.

Original language	English
Title of host publication	2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	12526-12530
Number of pages	5
ISBN (Electronic)	9798350344851
DOIs	https://doi.org/10.1109/ICASSP48485.2024.10448331
Publication status	Published - 2024
Externally published	Yes
Event	49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Seoul, Korea, Republic of Duration: 2024 Apr 14 → 2024 Apr 19

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Conference

Conference	49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Country/Territory	Korea, Republic of
City	Seoul
Period	24/4/14 → 24/4/19

Keywords

generative spoken language model
speech analysis
speech representation
Zipf's law

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP48485.2024.10448331

Cite this

Takamichi, S., Maeda, H., Park, J., Saito, D., & Saruwatari, H. (2024). DO LEARNED SPEECH SYMBOLS FOLLOW ZIPF'S LAW? In 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings (pp. 12526-12530). (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP48485.2024.10448331

DO LEARNED SPEECH SYMBOLS FOLLOW ZIPF'S LAW? / Takamichi, Shinnosuke; Maeda, Hiroki; Park, Joonyong et al.
2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2024. p. 12526-12530 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Takamichi, S, Maeda, H, Park, J, Saito, D & Saruwatari, H 2024, DO LEARNED SPEECH SYMBOLS FOLLOW ZIPF'S LAW? in 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 12526-12530, 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024, Seoul, Korea, Republic of, 24/4/14. https://doi.org/10.1109/ICASSP48485.2024.10448331

Takamichi S, Maeda H, Park J, Saito D, Saruwatari H. DO LEARNED SPEECH SYMBOLS FOLLOW ZIPF'S LAW? In 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2024. p. 12526-12530. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP48485.2024.10448331

Takamichi, Shinnosuke ; Maeda, Hiroki ; Park, Joonyong et al. / DO LEARNED SPEECH SYMBOLS FOLLOW ZIPF'S LAW?. 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2024. pp. 12526-12530 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{6e996382a7ff408196f02c9cdea94877,

title = "DO LEARNED SPEECH SYMBOLS FOLLOW ZIPF'S LAW?",

abstract = "In this study, we investigate whether speech symbols, learned through deep learning, follow Zipf's law, akin to natural language symbols. Zipf's law is an empirical law that delineates the frequency distribution of words, forming fundamentals for statistical analysis in natural language processing. Natural language symbols, which are invented by humans to symbolize speech content, are recognized to comply with this law. On the other hand, recent breakthroughs in spoken language processing have given rise to the development of learned speech symbols; these are data-driven symbolizations of speech content. Our objective is to ascertain whether these data-driven speech symbols follow Zipf's law, as the same as natural language symbols. Through our investigation, we aim to forge new ways for the statistical analysis of spoken language processing.",

keywords = "generative spoken language model, speech analysis, speech representation, Zipf's law",

author = "Shinnosuke Takamichi and Hiroki Maeda and Joonyong Park and Daisuke Saito and Hiroshi Saruwatari",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 ; Conference date: 14-04-2024 Through 19-04-2024",

year = "2024",

doi = "10.1109/ICASSP48485.2024.10448331",

language = "English",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "12526--12530",

booktitle = "2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings",