@inproceedings{kim-etal-2022-fast,
title = "Fast Bilingual Grapheme-To-Phoneme Conversion",
author = "Kim, Hwa-Yeon and
Kim, Jong-Hwan and
Kim, Jae-Min",
editor = "Loukina, Anastassia and
Gangadharaiah, Rashmi and
Min, Bonan",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track",
month = jul,
year = "2022",
address = "Hybrid: Seattle, Washington + Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-industry.32",
doi = "10.18653/v1/2022.naacl-industry.32",
pages = "289--296",
abstract = "Autoregressive transformer (ART)-based grapheme-to-phoneme (G2P) models have been proposed for bi/multilingual text-to-speech systems. Although they have achieved great success, they suffer from high inference latency in real-time industrial applications, especially processing long sentence. In this paper, we propose a fast and high-performance bilingual G2P model. For fast and exact decoding, we used a non-autoregressive structured transformer-based architecture and data augmentation for predicting output length. Our model achieved better performance than that of the previous autoregressive model and about 2700{\%} faster inference speed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2022-fast">
<titleInfo>
<title>Fast Bilingual Grapheme-To-Phoneme Conversion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hwa-Yeon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jong-Hwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jae-Min</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastassia</namePart>
<namePart type="family">Loukina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Gangadharaiah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonan</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid: Seattle, Washington + Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Autoregressive transformer (ART)-based grapheme-to-phoneme (G2P) models have been proposed for bi/multilingual text-to-speech systems. Although they have achieved great success, they suffer from high inference latency in real-time industrial applications, especially processing long sentence. In this paper, we propose a fast and high-performance bilingual G2P model. For fast and exact decoding, we used a non-autoregressive structured transformer-based architecture and data augmentation for predicting output length. Our model achieved better performance than that of the previous autoregressive model and about 2700% faster inference speed.</abstract>
<identifier type="citekey">kim-etal-2022-fast</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-industry.32</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-industry.32</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>289</start>
<end>296</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fast Bilingual Grapheme-To-Phoneme Conversion
%A Kim, Hwa-Yeon
%A Kim, Jong-Hwan
%A Kim, Jae-Min
%Y Loukina, Anastassia
%Y Gangadharaiah, Rashmi
%Y Min, Bonan
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid: Seattle, Washington + Online
%F kim-etal-2022-fast
%X Autoregressive transformer (ART)-based grapheme-to-phoneme (G2P) models have been proposed for bi/multilingual text-to-speech systems. Although they have achieved great success, they suffer from high inference latency in real-time industrial applications, especially processing long sentence. In this paper, we propose a fast and high-performance bilingual G2P model. For fast and exact decoding, we used a non-autoregressive structured transformer-based architecture and data augmentation for predicting output length. Our model achieved better performance than that of the previous autoregressive model and about 2700% faster inference speed.
%R 10.18653/v1/2022.naacl-industry.32
%U https://aclanthology.org/2022.naacl-industry.32
%U https://doi.org/10.18653/v1/2022.naacl-industry.32
%P 289-296
Markdown (Informal)
[Fast Bilingual Grapheme-To-Phoneme Conversion](https://aclanthology.org/2022.naacl-industry.32) (Kim et al., NAACL 2022)
ACL
- Hwa-Yeon Kim, Jong-Hwan Kim, and Jae-Min Kim. 2022. Fast Bilingual Grapheme-To-Phoneme Conversion. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track, pages 289–296, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.