@inproceedings{a-shams-etal-2024-uncovering,
title = "Uncovering Syllable Constituents in the Self-Attention-Based Speech Representations of Whisper",
author = "A Shams, Erfan and
Gessinger, Iona and
Carson-Berndsen, Julie",
editor = "Belinkov, Yonatan and
Kim, Najoung and
Jumelet, Jaap and
Mohebbi, Hosein and
Mueller, Aaron and
Chen, Hanjie",
booktitle = "Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP",
month = nov,
year = "2024",
address = "Miami, Florida, US",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.blackboxnlp-1.16",
pages = "238--247",
abstract = "As intuitive units of speech, syllables have been widely studied in linguistics. A syllable can be defined as a three-constituent unit with a vocalic centre surrounded by two (in some languages optional) consonant clusters. Syllables are also used to design automatic speech recognition (ASR) models. The significance of knowledge-driven syllable-based tokenisation in ASR over data-driven byte-pair encoding has often been debated. However, the emergence of transformer-based ASR models employing self-attention (SA) overshadowed this debate. These models learn the nuances of speech from large corpora without prior knowledge of the domain; yet, they are not interpretable by design. Consequently, it is not clear if the recent performance improvements are related to the extraction of human-interpretable knowledge. We probe such models for syllable constituents and use an SA head pruning method to assess the relevance of the SA weights. We also investigate the role of vowel identification in syllable constituent probing. Our findings show that the general features of syllable constituents are extracted in the earlier layers of the model and the syllable-related features mostly depend on the temporal knowledge incorporated in specific SA heads rather than on vowel identification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="a-shams-etal-2024-uncovering">
<titleInfo>
<title>Uncovering Syllable Constituents in the Self-Attention-Based Speech Representations of Whisper</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erfan</namePart>
<namePart type="family">A Shams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iona</namePart>
<namePart type="family">Gessinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julie</namePart>
<namePart type="family">Carson-Berndsen</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 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Najoung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Jumelet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Mohebbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, US</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As intuitive units of speech, syllables have been widely studied in linguistics. A syllable can be defined as a three-constituent unit with a vocalic centre surrounded by two (in some languages optional) consonant clusters. Syllables are also used to design automatic speech recognition (ASR) models. The significance of knowledge-driven syllable-based tokenisation in ASR over data-driven byte-pair encoding has often been debated. However, the emergence of transformer-based ASR models employing self-attention (SA) overshadowed this debate. These models learn the nuances of speech from large corpora without prior knowledge of the domain; yet, they are not interpretable by design. Consequently, it is not clear if the recent performance improvements are related to the extraction of human-interpretable knowledge. We probe such models for syllable constituents and use an SA head pruning method to assess the relevance of the SA weights. We also investigate the role of vowel identification in syllable constituent probing. Our findings show that the general features of syllable constituents are extracted in the earlier layers of the model and the syllable-related features mostly depend on the temporal knowledge incorporated in specific SA heads rather than on vowel identification.</abstract>
<identifier type="citekey">a-shams-etal-2024-uncovering</identifier>
<location>
<url>https://aclanthology.org/2024.blackboxnlp-1.16</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>238</start>
<end>247</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uncovering Syllable Constituents in the Self-Attention-Based Speech Representations of Whisper
%A A Shams, Erfan
%A Gessinger, Iona
%A Carson-Berndsen, Julie
%Y Belinkov, Yonatan
%Y Kim, Najoung
%Y Jumelet, Jaap
%Y Mohebbi, Hosein
%Y Mueller, Aaron
%Y Chen, Hanjie
%S Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, US
%F a-shams-etal-2024-uncovering
%X As intuitive units of speech, syllables have been widely studied in linguistics. A syllable can be defined as a three-constituent unit with a vocalic centre surrounded by two (in some languages optional) consonant clusters. Syllables are also used to design automatic speech recognition (ASR) models. The significance of knowledge-driven syllable-based tokenisation in ASR over data-driven byte-pair encoding has often been debated. However, the emergence of transformer-based ASR models employing self-attention (SA) overshadowed this debate. These models learn the nuances of speech from large corpora without prior knowledge of the domain; yet, they are not interpretable by design. Consequently, it is not clear if the recent performance improvements are related to the extraction of human-interpretable knowledge. We probe such models for syllable constituents and use an SA head pruning method to assess the relevance of the SA weights. We also investigate the role of vowel identification in syllable constituent probing. Our findings show that the general features of syllable constituents are extracted in the earlier layers of the model and the syllable-related features mostly depend on the temporal knowledge incorporated in specific SA heads rather than on vowel identification.
%U https://aclanthology.org/2024.blackboxnlp-1.16
%P 238-247
Markdown (Informal)
[Uncovering Syllable Constituents in the Self-Attention-Based Speech Representations of Whisper](https://aclanthology.org/2024.blackboxnlp-1.16) (A Shams et al., BlackboxNLP 2024)
ACL