@inproceedings{khanna-etal-2025-stud,
title = "{S}tu{D}: A Multimodal Approach for Stuttering Detection with {RAG} and Fusion Strategies",
author = "Khanna, Pragya and
Kommagouni, Priyanka and
Narasinga, Vamshi Raghu Simha and
Vuppala, Anil",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.ijcnlp-long.39/",
pages = "698--707",
ISBN = "979-8-89176-298-5",
abstract = "Stuttering is a complex speech disorder that challenges both ASR systems and clinical assessment. We propose a multimodal stuttering detection and classification model that integrates acoustic and linguistic features through a two-stage fusion mechanism. Fine-tuned Wav2Vec 2.0 and HuBERT extract acoustic embeddings, which are early fused with MFCC features to capture fine-grained spectral and phonetic variations, while Llama-2 embeddings from Whisper ASR transcriptions provide linguistic context. To enhance robustness against out-of-distribution speech patterns, we incorporate Retrieval-Augmented Generation or adaptive classification. Our model achieves state-of-the-art performance on SEP-28k and FluencyBank, demonstrating significant improvements in detecting challenging stuttering events. Additionally, our analysis highlights the complementary nature of acoustic and linguistic modalities, reinforcing the need for multimodal approaches in speech disorder detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khanna-etal-2025-stud">
<titleInfo>
<title>StuD: A Multimodal Approach for Stuttering Detection with RAG and Fusion Strategies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pragya</namePart>
<namePart type="family">Khanna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyanka</namePart>
<namePart type="family">Kommagouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vamshi</namePart>
<namePart type="given">Raghu</namePart>
<namePart type="given">Simha</namePart>
<namePart type="family">Narasinga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anil</namePart>
<namePart type="family">Vuppala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-298-5</identifier>
</relatedItem>
<abstract>Stuttering is a complex speech disorder that challenges both ASR systems and clinical assessment. We propose a multimodal stuttering detection and classification model that integrates acoustic and linguistic features through a two-stage fusion mechanism. Fine-tuned Wav2Vec 2.0 and HuBERT extract acoustic embeddings, which are early fused with MFCC features to capture fine-grained spectral and phonetic variations, while Llama-2 embeddings from Whisper ASR transcriptions provide linguistic context. To enhance robustness against out-of-distribution speech patterns, we incorporate Retrieval-Augmented Generation or adaptive classification. Our model achieves state-of-the-art performance on SEP-28k and FluencyBank, demonstrating significant improvements in detecting challenging stuttering events. Additionally, our analysis highlights the complementary nature of acoustic and linguistic modalities, reinforcing the need for multimodal approaches in speech disorder detection.</abstract>
<identifier type="citekey">khanna-etal-2025-stud</identifier>
<location>
<url>https://aclanthology.org/2025.ijcnlp-long.39/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>698</start>
<end>707</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T StuD: A Multimodal Approach for Stuttering Detection with RAG and Fusion Strategies
%A Khanna, Pragya
%A Kommagouni, Priyanka
%A Narasinga, Vamshi Raghu Simha
%A Vuppala, Anil
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-298-5
%F khanna-etal-2025-stud
%X Stuttering is a complex speech disorder that challenges both ASR systems and clinical assessment. We propose a multimodal stuttering detection and classification model that integrates acoustic and linguistic features through a two-stage fusion mechanism. Fine-tuned Wav2Vec 2.0 and HuBERT extract acoustic embeddings, which are early fused with MFCC features to capture fine-grained spectral and phonetic variations, while Llama-2 embeddings from Whisper ASR transcriptions provide linguistic context. To enhance robustness against out-of-distribution speech patterns, we incorporate Retrieval-Augmented Generation or adaptive classification. Our model achieves state-of-the-art performance on SEP-28k and FluencyBank, demonstrating significant improvements in detecting challenging stuttering events. Additionally, our analysis highlights the complementary nature of acoustic and linguistic modalities, reinforcing the need for multimodal approaches in speech disorder detection.
%U https://aclanthology.org/2025.ijcnlp-long.39/
%P 698-707
Markdown (Informal)
[StuD: A Multimodal Approach for Stuttering Detection with RAG and Fusion Strategies](https://aclanthology.org/2025.ijcnlp-long.39/) (Khanna et al., IJCNLP-AACL 2025)
ACL
- Pragya Khanna, Priyanka Kommagouni, Vamshi Raghu Simha Narasinga, and Anil Vuppala. 2025. StuD: A Multimodal Approach for Stuttering Detection with RAG and Fusion Strategies. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 698–707, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.