Stutter-Solver: End-to-end Multi-lingual Dysfluency Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Xuanru, Cho, Cheol Jun, Sharma, Ayati, Morin, Brittany, Baquirin, David, Vonk, Jet, Ezzes, Zoe, Miller, Zachary, Tee, Boon Lead, Tempini, Maria Luisa Gorno, Lian, Jiachen, Anumanchipalli, Gopala
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917775687024640
author Zhou, Xuanru
Cho, Cheol Jun
Sharma, Ayati
Morin, Brittany
Baquirin, David
Vonk, Jet
Ezzes, Zoe
Miller, Zachary
Tee, Boon Lead
Tempini, Maria Luisa Gorno
Lian, Jiachen
Anumanchipalli, Gopala
author_facet Zhou, Xuanru
Cho, Cheol Jun
Sharma, Ayati
Morin, Brittany
Baquirin, David
Vonk, Jet
Ezzes, Zoe
Miller, Zachary
Tee, Boon Lead
Tempini, Maria Luisa Gorno
Lian, Jiachen
Anumanchipalli, Gopala
contents Current de-facto dysfluency modeling methods utilize template matching algorithms which are not generalizable to out-of-domain real-world dysfluencies across languages, and are not scalable with increasing amounts of training data. To handle these problems, we propose Stutter-Solver: an end-to-end framework that detects dysfluency with accurate type and time transcription, inspired by the YOLO object detection algorithm. Stutter-Solver can handle co-dysfluencies and is a natural multi-lingual dysfluency detector. To leverage scalability and boost performance, we also introduce three novel dysfluency corpora: VCTK-Pro, VCTK-Art, and AISHELL3-Pro, simulating natural spoken dysfluencies including repetition, block, missing, replacement, and prolongation through articulatory-encodec and TTS-based methods. Our approach achieves state-of-the-art performance on all available dysfluency corpora. Code and datasets are open-sourced at https://github.com/eureka235/Stutter-Solver
format Preprint
id arxiv_https___arxiv_org_abs_2409_09621
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Stutter-Solver: End-to-end Multi-lingual Dysfluency Detection
Zhou, Xuanru
Cho, Cheol Jun
Sharma, Ayati
Morin, Brittany
Baquirin, David
Vonk, Jet
Ezzes, Zoe
Miller, Zachary
Tee, Boon Lead
Tempini, Maria Luisa Gorno
Lian, Jiachen
Anumanchipalli, Gopala
Audio and Speech Processing
Artificial Intelligence
Sound
Current de-facto dysfluency modeling methods utilize template matching algorithms which are not generalizable to out-of-domain real-world dysfluencies across languages, and are not scalable with increasing amounts of training data. To handle these problems, we propose Stutter-Solver: an end-to-end framework that detects dysfluency with accurate type and time transcription, inspired by the YOLO object detection algorithm. Stutter-Solver can handle co-dysfluencies and is a natural multi-lingual dysfluency detector. To leverage scalability and boost performance, we also introduce three novel dysfluency corpora: VCTK-Pro, VCTK-Art, and AISHELL3-Pro, simulating natural spoken dysfluencies including repetition, block, missing, replacement, and prolongation through articulatory-encodec and TTS-based methods. Our approach achieves state-of-the-art performance on all available dysfluency corpora. Code and datasets are open-sourced at https://github.com/eureka235/Stutter-Solver
title Stutter-Solver: End-to-end Multi-lingual Dysfluency Detection
topic Audio and Speech Processing
Artificial Intelligence
Sound
url https://arxiv.org/abs/2409.09621