Podcast, online resources, self-help groups and research about stuttering in Mandarin and English.
News | Mission | Projects | Self-help | About us | Support us | Contact
Projects
Podcast
We interview people who stutter (PWS), speech-language therapists (SLPs), and stuttering researchers to foster open discussions about stuttering, inspire PWS with real-life experiences, and promote scientific understanding of stuttering. Our audio podcast interviews are available on Spotify and 喜马拉雅, and our video podcast interviews can be accessed on Bilibili.
Evidence-based stuttering resources
In Mainland China, PWS and parents of children who stutter are eager to access scientific techniques for managing stuttering, helping them better navigate daily challenges. These techniques range from classic methods such as fluency shaping and speech modification to modern approaches like Acceptance and Commitment Therapy. StammerTalk invites professional SLPs to present these techniques and translates relevant materials from collaborators.
- Stuttering handling strategies and Speech modification techniques (translation)
- Childhood stuttering and parents (translation)
- Practical tips handsout (Section Chinese)
World Stuttering Awareness Day online events and Workshops
We collaborates with SLPs and researchers to co-host World Stuttering Awareness Day online events, featuring knowledge sharing, open-mic sessions, and roundtable discussions with PWS and SLPs. StammerTalk also actively organize online workshops on professional stuttering treatment topics and host Q&A sessions.
- World Stuttering Awareness Day online activities
- Workshop Interpretation of the OASES stuttering assessment
- Workshop SLP experience sharing and Q&A session
Research
AISHELL-Stammertalk Mandarin stuttered speech dataset
StammerTalk is leading the research project to create the first Mandarin stuttered speech dataset, AISHELL-Stammertalk. We believe this dataset will significantly advance research and development in Mandarin stuttered speech technologies, such as Automatic Speech Recognition (ASR) and Stuttering Event Detection (SED), as well as contribute to speech pathology research.
We work closely with AISHELL and AImpower.org to ensure the ethical and compliant collection of data. Our goal is to provide high-quality, well-annotated data suitable for various research topics.
The AISHELL-Stammertalk dataset includes recordings from 70 native Mandarin-speaking adults who stutter (AWS), consisting of 46 males and 24 females, with a total duration of 48.8 hours. Each participant took part in a recording session lasting up to one hour, divided into two parts: conversation and voice command reading.
If you use this dataset in your research, please cite the following publications:
@misc{gong2024as70,
title={AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection},
author={Rong Gong and Hongfei Xue and Lezhi Wang and Xin Xu and Qisheng Li and Lei Xie and Hui Bu and Shaomei Wu and Jiaming Zhou and Yong Qin and Binbin Zhang and Jun Du and Jia Bin and Ming Li},
year={2024},
eprint={2406.07256},
archivePrefix={arXiv},
primaryClass={cs.SD}
}
@inproceedings{10.1145/3613905.3650950,
author = {Li, Qisheng and Wu, Shaomei},
title = {Towards Fair and Inclusive Speech Recognition for Stuttering: Community-led Chinese Stuttered Speech Dataset Creation and Benchmarking},
year = {2024},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
booktitle = {Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Systems},
location = {Honolulu, HI, USA},
series = {CHI EA ‘24}
}