YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Xuanru, Kashyap, Anshul, Li, Steve, Sharma, Ayati, Morin, Brittany, Baquirin, David, Vonk, Jet, Ezzes, Zoe, Miller, Zachary, Tempini, Maria Luisa Gorno, Lian, Jiachen, Anumanchipalli, Gopala Krishna
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912028176678912
author Zhou, Xuanru
Kashyap, Anshul
Li, Steve
Sharma, Ayati
Morin, Brittany
Baquirin, David
Vonk, Jet
Ezzes, Zoe
Miller, Zachary
Tempini, Maria Luisa Gorno
Lian, Jiachen
Anumanchipalli, Gopala Krishna
author_facet Zhou, Xuanru
Kashyap, Anshul
Li, Steve
Sharma, Ayati
Morin, Brittany
Baquirin, David
Vonk, Jet
Ezzes, Zoe
Miller, Zachary
Tempini, Maria Luisa Gorno
Lian, Jiachen
Anumanchipalli, Gopala Krishna
contents Dysfluent speech detection is the bottleneck for disordered speech analysis and spoken language learning. Current state-of-the-art models are governed by rule-based systems which lack efficiency and robustness, and are sensitive to template design. In this paper, we propose YOLO-Stutter: a first end-to-end method that detects dysfluencies in a time-accurate manner. YOLO-Stutter takes imperfect speech-text alignment as input, followed by a spatial feature aggregator, and a temporal dependency extractor to perform region-wise boundary and class predictions. We also introduce two dysfluency corpus, VCTK-Stutter and VCTK-TTS, that simulate natural spoken dysfluencies including repetition, block, missing, replacement, and prolongation. Our end-to-end method achieves state-of-the-art performance with a minimum number of trainable parameters for on both simulated data and real aphasia speech. Code and datasets are open-sourced at https://github.com/rorizzz/YOLO-Stutter
format Preprint
id arxiv_https___arxiv_org_abs_2408_15297
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection
Zhou, Xuanru
Kashyap, Anshul
Li, Steve
Sharma, Ayati
Morin, Brittany
Baquirin, David
Vonk, Jet
Ezzes, Zoe
Miller, Zachary
Tempini, Maria Luisa Gorno
Lian, Jiachen
Anumanchipalli, Gopala Krishna
Audio and Speech Processing
Artificial Intelligence
Computation and Language
Dysfluent speech detection is the bottleneck for disordered speech analysis and spoken language learning. Current state-of-the-art models are governed by rule-based systems which lack efficiency and robustness, and are sensitive to template design. In this paper, we propose YOLO-Stutter: a first end-to-end method that detects dysfluencies in a time-accurate manner. YOLO-Stutter takes imperfect speech-text alignment as input, followed by a spatial feature aggregator, and a temporal dependency extractor to perform region-wise boundary and class predictions. We also introduce two dysfluency corpus, VCTK-Stutter and VCTK-TTS, that simulate natural spoken dysfluencies including repetition, block, missing, replacement, and prolongation. Our end-to-end method achieves state-of-the-art performance with a minimum number of trainable parameters for on both simulated data and real aphasia speech. Code and datasets are open-sourced at https://github.com/rorizzz/YOLO-Stutter
title YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection
topic Audio and Speech Processing
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2408.15297