@inproceedings{lian-anumanchipalli-2024-towards,
title = "Towards Hierarchical Spoken Language Disfluency Modeling",
author = "Lian, Jiachen and
Anumanchipalli, Gopala",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.32",
pages = "539--551",
abstract = "Speech dysfluency modeling is the bottleneck for both speech therapy and language learning. However, there is no AI solution to systematically tackle this problem. We first propose to define the concept of dysfluent speech and dysfluent speech modeling. We then present Hierarchical Unconstrained Dysfluency Modeling (H-UDM) approach that addresses both dysfluency transcription and detection to eliminate the need for extensive manual annotation. Furthermore, we introduce a simulated dysfluent dataset called VCTK++ to enhance the capabilities of H-UDM in phonetic transcription. Our experimental results demonstrate the effectiveness and robustness of our proposed methods in both transcription and detection tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lian-anumanchipalli-2024-towards">
<titleInfo>
<title>Towards Hierarchical Spoken Language Disfluency Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiachen</namePart>
<namePart type="family">Lian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gopala</namePart>
<namePart type="family">Anumanchipalli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Speech dysfluency modeling is the bottleneck for both speech therapy and language learning. However, there is no AI solution to systematically tackle this problem. We first propose to define the concept of dysfluent speech and dysfluent speech modeling. We then present Hierarchical Unconstrained Dysfluency Modeling (H-UDM) approach that addresses both dysfluency transcription and detection to eliminate the need for extensive manual annotation. Furthermore, we introduce a simulated dysfluent dataset called VCTK++ to enhance the capabilities of H-UDM in phonetic transcription. Our experimental results demonstrate the effectiveness and robustness of our proposed methods in both transcription and detection tasks.</abstract>
<identifier type="citekey">lian-anumanchipalli-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.32</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>539</start>
<end>551</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Hierarchical Spoken Language Disfluency Modeling
%A Lian, Jiachen
%A Anumanchipalli, Gopala
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F lian-anumanchipalli-2024-towards
%X Speech dysfluency modeling is the bottleneck for both speech therapy and language learning. However, there is no AI solution to systematically tackle this problem. We first propose to define the concept of dysfluent speech and dysfluent speech modeling. We then present Hierarchical Unconstrained Dysfluency Modeling (H-UDM) approach that addresses both dysfluency transcription and detection to eliminate the need for extensive manual annotation. Furthermore, we introduce a simulated dysfluent dataset called VCTK++ to enhance the capabilities of H-UDM in phonetic transcription. Our experimental results demonstrate the effectiveness and robustness of our proposed methods in both transcription and detection tasks.
%U https://aclanthology.org/2024.eacl-long.32
%P 539-551
Markdown (Informal)
[Towards Hierarchical Spoken Language Disfluency Modeling](https://aclanthology.org/2024.eacl-long.32) (Lian & Anumanchipalli, EACL 2024)
ACL
- Jiachen Lian and Gopala Anumanchipalli. 2024. Towards Hierarchical Spoken Language Disfluency Modeling. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 539–551, St. Julian’s, Malta. Association for Computational Linguistics.