@inproceedings{vietti-etal-2024-sensitivity,
title = "Sensitivity of Syllable-Based {ASR} Predictions to Token Frequency and Lexical Stress",
author = "Vietti, Alessandro and
De Cristofaro, Domenico and
Sara, Picciau",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.106/",
pages = "983--989",
ISBN = "979-12-210-7060-6",
abstract = "Automatic Speech Recognition systems (ASR) based on neural networks achieve great results, but it remains unclear which are the linguistic features and representations that the models leverage to perform the recognition. In our study, we used phonological syllables as tokens to fine-tune an end-to-end ASR model due to their relevance as linguistic units. Furthermore, this strategy allowed us to keep track of different types of linguistic features characterizing the tokens. The analysis of the transcriptions generated by the model reveals that factors such as token frequency and lexical stress have a variable impact on the prediction strategies adopted by the ASR system."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vietti-etal-2024-sensitivity">
<titleInfo>
<title>Sensitivity of Syllable-Based ASR Predictions to Token Frequency and Lexical Stress</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Vietti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Domenico</namePart>
<namePart type="family">De Cristofaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Picciau</namePart>
<namePart type="family">Sara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>Automatic Speech Recognition systems (ASR) based on neural networks achieve great results, but it remains unclear which are the linguistic features and representations that the models leverage to perform the recognition. In our study, we used phonological syllables as tokens to fine-tune an end-to-end ASR model due to their relevance as linguistic units. Furthermore, this strategy allowed us to keep track of different types of linguistic features characterizing the tokens. The analysis of the transcriptions generated by the model reveals that factors such as token frequency and lexical stress have a variable impact on the prediction strategies adopted by the ASR system.</abstract>
<identifier type="citekey">vietti-etal-2024-sensitivity</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.106/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>983</start>
<end>989</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sensitivity of Syllable-Based ASR Predictions to Token Frequency and Lexical Stress
%A Vietti, Alessandro
%A De Cristofaro, Domenico
%A Sara, Picciau
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F vietti-etal-2024-sensitivity
%X Automatic Speech Recognition systems (ASR) based on neural networks achieve great results, but it remains unclear which are the linguistic features and representations that the models leverage to perform the recognition. In our study, we used phonological syllables as tokens to fine-tune an end-to-end ASR model due to their relevance as linguistic units. Furthermore, this strategy allowed us to keep track of different types of linguistic features characterizing the tokens. The analysis of the transcriptions generated by the model reveals that factors such as token frequency and lexical stress have a variable impact on the prediction strategies adopted by the ASR system.
%U https://aclanthology.org/2024.clicit-1.106/
%P 983-989
Markdown (Informal)
[Sensitivity of Syllable-Based ASR Predictions to Token Frequency and Lexical Stress](https://aclanthology.org/2024.clicit-1.106/) (Vietti et al., CLiC-it 2024)
ACL