@inproceedings{rose-etal-2024-one,
title = "One-Vs-Rest Neural Network {E}nglish Grapheme Segmentation: A Linguistic Perspective",
author = "Rose, Samuel and
Dethlefs, Nina and
Kambhampati, C.",
editor = "Barak, Libby and
Alikhani, Malihe",
booktitle = "Proceedings of the 28th Conference on Computational Natural Language Learning",
month = nov,
year = "2024",
address = "Miami, FL, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.conll-1.36",
pages = "464--469",
abstract = "Grapheme-to-Phoneme (G2P) correspondences form foundational frameworks of tasks such as text-to-speech (TTS) synthesis or automatic speech recognition. The G2P process involves taking words in their written form and generating their pronunciation. In this paper, we critique the status quo definition of a grapheme, currently a forced alignment process relating a single character to either a phoneme or a blank unit, that underlies the majority of modern approaches. We develop a linguistically-motivated redefinition from simple concepts such as vowel and consonant count and word length and offer a proof-of-concept implementation based on a multi-binary neural classification task. Our model achieves state-of-the-art results with a 31.86{\%} Word Error Rate on a standard benchmark, while generating linguistically meaningful grapheme segmentations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rose-etal-2024-one">
<titleInfo>
<title>One-Vs-Rest Neural Network English Grapheme Segmentation: A Linguistic Perspective</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Dethlefs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="family">Kambhampati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Libby</namePart>
<namePart type="family">Barak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, FL, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grapheme-to-Phoneme (G2P) correspondences form foundational frameworks of tasks such as text-to-speech (TTS) synthesis or automatic speech recognition. The G2P process involves taking words in their written form and generating their pronunciation. In this paper, we critique the status quo definition of a grapheme, currently a forced alignment process relating a single character to either a phoneme or a blank unit, that underlies the majority of modern approaches. We develop a linguistically-motivated redefinition from simple concepts such as vowel and consonant count and word length and offer a proof-of-concept implementation based on a multi-binary neural classification task. Our model achieves state-of-the-art results with a 31.86% Word Error Rate on a standard benchmark, while generating linguistically meaningful grapheme segmentations.</abstract>
<identifier type="citekey">rose-etal-2024-one</identifier>
<location>
<url>https://aclanthology.org/2024.conll-1.36</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>464</start>
<end>469</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T One-Vs-Rest Neural Network English Grapheme Segmentation: A Linguistic Perspective
%A Rose, Samuel
%A Dethlefs, Nina
%A Kambhampati, C.
%Y Barak, Libby
%Y Alikhani, Malihe
%S Proceedings of the 28th Conference on Computational Natural Language Learning
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F rose-etal-2024-one
%X Grapheme-to-Phoneme (G2P) correspondences form foundational frameworks of tasks such as text-to-speech (TTS) synthesis or automatic speech recognition. The G2P process involves taking words in their written form and generating their pronunciation. In this paper, we critique the status quo definition of a grapheme, currently a forced alignment process relating a single character to either a phoneme or a blank unit, that underlies the majority of modern approaches. We develop a linguistically-motivated redefinition from simple concepts such as vowel and consonant count and word length and offer a proof-of-concept implementation based on a multi-binary neural classification task. Our model achieves state-of-the-art results with a 31.86% Word Error Rate on a standard benchmark, while generating linguistically meaningful grapheme segmentations.
%U https://aclanthology.org/2024.conll-1.36
%P 464-469
Markdown (Informal)
[One-Vs-Rest Neural Network English Grapheme Segmentation: A Linguistic Perspective](https://aclanthology.org/2024.conll-1.36) (Rose et al., CoNLL 2024)
ACL