Standardising Pronunciation for a Grapheme-to-Phoneme Converter for Faroese

Sandra Saxov Lamhauge; Iben Nyholm Debess; Carlos Daniel Hernández Mena; Annika Simonsen; Jón Gudnason

Standardising Pronunciation for a Grapheme-to-Phoneme Converter for Faroese

Sandra Saxov Lamhauge
, Iben Nyholm Debess
, Carlos Daniel Hernández Mena
, Annika Simonsen
, Jón Gudnason

Føroyamálsdeildin - Faculty of Faroese Language and Literature

Research output: Contribution to conference › Paper › peer-review

49 Downloads (Pure)

Abstract

Pronunciation dictionaries allow computational modelling of the pronunciation
of words in a certain language and are widely used in speech technologies, especially in the fields of speech recognition and synthesis. On the other hand, a grapheme-to-phoneme tool is a generalization of a pronunciation dictionary that is not limited to a given and finite vocabulary. In this paper, we present a set of standardized phonological rules for the Faroese language; we introduce FARSAMPA, a machine-readable character set suitable for phonetic transcription of Faroese, and we present a set of grapheme-to-phoneme models for Faroese, which are publicly available and shared under a creative commons license. We
present the G2P converter and evaluate the performance. The evaluation shows reliable results that demonstrate the quality of the data.

Original language	English
Pages	308-317
Number of pages	10
Publication status	Published - May 2023
Event	Nodalida 2023: Nordic Conference on Computational Linguistics - Tórshavn, Faroe Islands Duration: 22 May 2023 → 24 May 2023 Conference number: 24 http://nodalida2023.fo

Conference

Conference	Nodalida 2023
Abbreviated title	Nodalida
Country/Territory	Faroe Islands
City	Tórshavn
Period	22/05/23 → 24/05/23
Internet address	http://nodalida2023.fo

Keywords

pronunciation dictionaries
computational modeling
speech technologies
grapheme-to-phoneme tool
machine-readable character set
Faroese language

Access to Document

Lamhauge_Sandra_S_Standardising_Pronunciation_for_a_Grapheme_to_Phoneme_Converter_for_Faroese_Final published version, 709 KBLicence: CC BY

https://aclanthology.org/2023.nodalida-1.32.pdfLicence: CC BY

Cite this

@conference{8e51c424e0724c71a7e977f482840c78,

title = "Standardising Pronunciation for a Grapheme-to-Phoneme Converter for Faroese",

abstract = "Pronunciation dictionaries allow computational modelling of the pronunciation of words in a certain language and are widely used in speech technologies, especially in the fields of speech recognition and synthesis. On the other hand, a grapheme-to-phoneme tool is a generalization of a pronunciation dictionary that is not limited to a given and finite vocabulary. In this paper, we present a set of standardized phonological rules for the Faroese language; we introduce FARSAMPA, a machine-readable character set suitable for phonetic transcription of Faroese, and we present a set of grapheme-to-phoneme models for Faroese, which are publicly available and shared under a creative commons license. We present the G2P converter and evaluate the performance. The evaluation shows reliable results that demonstrate the quality of the data.",

keywords = "pronunciation dictionaries, computational modeling, speech technologies, grapheme-to-phoneme tool, machine-readable character set, Faroese language",

author = "Lamhauge, \{Sandra Saxov\} and Debess, \{Iben Nyholm\} and \{Hern{\'a}ndez Mena\}, \{Carlos Daniel\} and Annika Simonsen and J{\'o}n Gudnason",

year = "2023",

month = may,

language = "English",

pages = "308--317",

note = "Nodalida 2023 : Nordic Conference on Computational Linguistics, Nodalida ; Conference date: 22-05-2023 Through 24-05-2023",

url = "http://nodalida2023.fo",

}

TY - CONF

T1 - Standardising Pronunciation for a Grapheme-to-Phoneme Converter for Faroese

AU - Lamhauge, Sandra Saxov

AU - Debess, Iben Nyholm

AU - Hernández Mena, Carlos Daniel

AU - Simonsen, Annika

AU - Gudnason, Jón

N1 - Conference code: 24

PY - 2023/5

Y1 - 2023/5

N2 - Pronunciation dictionaries allow computational modelling of the pronunciation of words in a certain language and are widely used in speech technologies, especially in the fields of speech recognition and synthesis. On the other hand, a grapheme-to-phoneme tool is a generalization of a pronunciation dictionary that is not limited to a given and finite vocabulary. In this paper, we present a set of standardized phonological rules for the Faroese language; we introduce FARSAMPA, a machine-readable character set suitable for phonetic transcription of Faroese, and we present a set of grapheme-to-phoneme models for Faroese, which are publicly available and shared under a creative commons license. We present the G2P converter and evaluate the performance. The evaluation shows reliable results that demonstrate the quality of the data.

AB - Pronunciation dictionaries allow computational modelling of the pronunciation of words in a certain language and are widely used in speech technologies, especially in the fields of speech recognition and synthesis. On the other hand, a grapheme-to-phoneme tool is a generalization of a pronunciation dictionary that is not limited to a given and finite vocabulary. In this paper, we present a set of standardized phonological rules for the Faroese language; we introduce FARSAMPA, a machine-readable character set suitable for phonetic transcription of Faroese, and we present a set of grapheme-to-phoneme models for Faroese, which are publicly available and shared under a creative commons license. We present the G2P converter and evaluate the performance. The evaluation shows reliable results that demonstrate the quality of the data.

KW - pronunciation dictionaries

KW - computational modeling

KW - speech technologies

KW - grapheme-to-phoneme tool

KW - machine-readable character set

KW - Faroese language

M3 - Paper

SP - 308

EP - 317

T2 - Nodalida 2023

Y2 - 22 May 2023 through 24 May 2023

ER -

Standardising Pronunciation for a Grapheme-to-Phoneme Converter for Faroese

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this