MMSD-Net: Towards Multi-modal Stuttering Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nie, Liangyu, Kadiri, Sudarsana Reddy, Agrawal, Ruchit
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911956958445568
author Nie, Liangyu
Kadiri, Sudarsana Reddy
Agrawal, Ruchit
author_facet Nie, Liangyu
Kadiri, Sudarsana Reddy
Agrawal, Ruchit
contents Stuttering is a common speech impediment that is caused by irregular disruptions in speech production, affecting over 70 million people across the world. Standard automatic speech processing tools do not take speech ailments into account and are thereby not able to generate meaningful results when presented with stuttered speech as input. The automatic detection of stuttering is an integral step towards building efficient, context-aware speech processing systems. While previous approaches explore both statistical and neural approaches for stuttering detection, all of these methods are uni-modal in nature. This paper presents MMSD-Net, the first multi-modal neural framework for stuttering detection. Experiments and results demonstrate that incorporating the visual signal significantly aids stuttering detection, and our model yields an improvement of 2-17% in the F1-score over existing state-of-the-art uni-modal approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2407_11492
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MMSD-Net: Towards Multi-modal Stuttering Detection
Nie, Liangyu
Kadiri, Sudarsana Reddy
Agrawal, Ruchit
Sound
Computation and Language
Multimedia
Audio and Speech Processing
Stuttering is a common speech impediment that is caused by irregular disruptions in speech production, affecting over 70 million people across the world. Standard automatic speech processing tools do not take speech ailments into account and are thereby not able to generate meaningful results when presented with stuttered speech as input. The automatic detection of stuttering is an integral step towards building efficient, context-aware speech processing systems. While previous approaches explore both statistical and neural approaches for stuttering detection, all of these methods are uni-modal in nature. This paper presents MMSD-Net, the first multi-modal neural framework for stuttering detection. Experiments and results demonstrate that incorporating the visual signal significantly aids stuttering detection, and our model yields an improvement of 2-17% in the F1-score over existing state-of-the-art uni-modal approaches.
title MMSD-Net: Towards Multi-modal Stuttering Detection
topic Sound
Computation and Language
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2407.11492