PHONOTACTIC LANGUAGE RECOGNITION USING A UNIVERSAL PHONEME RECOGNIZER AND A TRANSFORMER ARCHITECTURE

David Romero; Luis Fernando D'Haro; Marcos Estecha-Garitagoitia; Christian Salamea

doi:10.1109/ICASSP43922.2022.9746459

PHONOTACTIC LANGUAGE RECOGNITION USING A UNIVERSAL PHONEME RECOGNIZER AND A TRANSFORMER ARCHITECTURE

David Romero, Luis Fernando D'Haro, Marcos Estecha-Garitagoitia, Christian Salamea

Research Group on Interaction, Robotics and Automatics (GIIRA)

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

2 Scopus citations

Abstract

In this paper, we describe a phonotactic language recognition model that effectively manages long and short n-gram input sequences to learn contextual phonotactic-based vector embeddings. Our approach uses a transformer-based encoder that integrates a sliding window attention to attempt finding discriminative short and long cooccurrences of language dependent n-gram phonetic units. We then evaluate and compare the use of different phoneme recognizers (Brno and Allosaurus) and sub-unit tokenizers to help select the more discriminative n-grams. The proposed architecture is evaluated using the Kalaka-3 database that contains clean and noisy audio recordings for very similar languages (i.e. Iberian languages, e.g., Spanish, Galician, Catalan). We provide results using the Cavg and accuracy metrics used in NIST evaluations. The experimental results show that our proposed approach outperforms by 21% of relative improvement to the best system presented in the Albayzin LR competition.

Original language	English
Title of host publication	2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	6872-6876
Number of pages	5
ISBN (Electronic)	9781665405409
DOIs	https://doi.org/10.1109/ICASSP43922.2022.9746459
State	Published - 2022
Event	47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore Duration: 23 May 2022 → 27 May 2022

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2022-May
ISSN (Print)	1520-6149

Conference

Conference	47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Country/Territory	Singapore
City	Virtual, Online
Period	23/05/22 → 27/05/22

Bibliographical note

Funding Information:
This work has been supported by the Spanish projects AMIC (MINECO, TIN2017-85854-C4-4-R) and CAVIAR (MINECO, TEC2017-84593-C2-1-R) projects partially funded by the European Union. We also gratefully acknowledge the support of the Universidad Politécnica Salesiana.

Publisher Copyright:
© 2022 IEEE

Keywords

acoustic systems
Language recognition
phonotactic information
transformers

Access to Document

10.1109/ICASSP43922.2022.9746459

Cite this

Romero, D., D'Haro, L. F., Estecha-Garitagoitia, M., & Salamea, C. (2022). PHONOTACTIC LANGUAGE RECOGNITION USING A UNIVERSAL PHONEME RECOGNIZER AND A TRANSFORMER ARCHITECTURE. In 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings (pp. 6872-6876). (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2022-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP43922.2022.9746459

Romero, David ; D'Haro, Luis Fernando ; Estecha-Garitagoitia, Marcos et al. / PHONOTACTIC LANGUAGE RECOGNITION USING A UNIVERSAL PHONEME RECOGNIZER AND A TRANSFORMER ARCHITECTURE. 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 6872-6876 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{62305949d1614a90b380ed6fc7c14768,

title = "PHONOTACTIC LANGUAGE RECOGNITION USING A UNIVERSAL PHONEME RECOGNIZER AND A TRANSFORMER ARCHITECTURE",

abstract = "In this paper, we describe a phonotactic language recognition model that effectively manages long and short n-gram input sequences to learn contextual phonotactic-based vector embeddings. Our approach uses a transformer-based encoder that integrates a sliding window attention to attempt finding discriminative short and long cooccurrences of language dependent n-gram phonetic units. We then evaluate and compare the use of different phoneme recognizers (Brno and Allosaurus) and sub-unit tokenizers to help select the more discriminative n-grams. The proposed architecture is evaluated using the Kalaka-3 database that contains clean and noisy audio recordings for very similar languages (i.e. Iberian languages, e.g., Spanish, Galician, Catalan). We provide results using the Cavg and accuracy metrics used in NIST evaluations. The experimental results show that our proposed approach outperforms by 21% of relative improvement to the best system presented in the Albayzin LR competition.",

keywords = "acoustic systems, Language recognition, phonotactic information, transformers",

author = "David Romero and D'Haro, {Luis Fernando} and Marcos Estecha-Garitagoitia and Christian Salamea",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE; 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 ; Conference date: 23-05-2022 Through 27-05-2022",

year = "2022",

doi = "10.1109/ICASSP43922.2022.9746459",

language = "English",

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

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

pages = "6872--6876",

booktitle = "2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings",

address = "United States",

}

Romero, D, D'Haro, LF, Estecha-Garitagoitia, M & Salamea, C 2022, PHONOTACTIC LANGUAGE RECOGNITION USING A UNIVERSAL PHONEME RECOGNIZER AND A TRANSFORMER ARCHITECTURE. in 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2022-May, Institute of Electrical and Electronics Engineers Inc., pp. 6872-6876, 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022, Virtual, Online, Singapore, 23/05/22. https://doi.org/10.1109/ICASSP43922.2022.9746459

PHONOTACTIC LANGUAGE RECOGNITION USING A UNIVERSAL PHONEME RECOGNIZER AND A TRANSFORMER ARCHITECTURE. / Romero, David; D'Haro, Luis Fernando; Estecha-Garitagoitia, Marcos et al.
2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. p. 6872-6876 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2022-May).

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

TY - GEN

T1 - PHONOTACTIC LANGUAGE RECOGNITION USING A UNIVERSAL PHONEME RECOGNIZER AND A TRANSFORMER ARCHITECTURE

AU - Romero, David

AU - D'Haro, Luis Fernando

AU - Estecha-Garitagoitia, Marcos

AU - Salamea, Christian

PY - 2022

Y1 - 2022

N2 - In this paper, we describe a phonotactic language recognition model that effectively manages long and short n-gram input sequences to learn contextual phonotactic-based vector embeddings. Our approach uses a transformer-based encoder that integrates a sliding window attention to attempt finding discriminative short and long cooccurrences of language dependent n-gram phonetic units. We then evaluate and compare the use of different phoneme recognizers (Brno and Allosaurus) and sub-unit tokenizers to help select the more discriminative n-grams. The proposed architecture is evaluated using the Kalaka-3 database that contains clean and noisy audio recordings for very similar languages (i.e. Iberian languages, e.g., Spanish, Galician, Catalan). We provide results using the Cavg and accuracy metrics used in NIST evaluations. The experimental results show that our proposed approach outperforms by 21% of relative improvement to the best system presented in the Albayzin LR competition.

AB - In this paper, we describe a phonotactic language recognition model that effectively manages long and short n-gram input sequences to learn contextual phonotactic-based vector embeddings. Our approach uses a transformer-based encoder that integrates a sliding window attention to attempt finding discriminative short and long cooccurrences of language dependent n-gram phonetic units. We then evaluate and compare the use of different phoneme recognizers (Brno and Allosaurus) and sub-unit tokenizers to help select the more discriminative n-grams. The proposed architecture is evaluated using the Kalaka-3 database that contains clean and noisy audio recordings for very similar languages (i.e. Iberian languages, e.g., Spanish, Galician, Catalan). We provide results using the Cavg and accuracy metrics used in NIST evaluations. The experimental results show that our proposed approach outperforms by 21% of relative improvement to the best system presented in the Albayzin LR competition.

KW - acoustic systems

KW - Language recognition

KW - phonotactic information

KW - transformers

UR - http://www.scopus.com/inward/record.url?scp=85131249455&partnerID=8YFLogxK

U2 - 10.1109/ICASSP43922.2022.9746459

DO - 10.1109/ICASSP43922.2022.9746459

M3 - Conference contribution

AN - SCOPUS:85131249455

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 6872

EP - 6876

BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022

Y2 - 23 May 2022 through 27 May 2022

ER -

Romero D, D'Haro LF, Estecha-Garitagoitia M, Salamea C. PHONOTACTIC LANGUAGE RECOGNITION USING A UNIVERSAL PHONEME RECOGNIZER AND A TRANSFORMER ARCHITECTURE. In 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2022. p. 6872-6876. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP43922.2022.9746459

PHONOTACTIC LANGUAGE RECOGNITION USING A UNIVERSAL PHONEME RECOGNIZER AND A TRANSFORMER ARCHITECTURE

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this