AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection

Rong Gong, Hongfei Xue, Lezhi Wang, Xin Xu, Qisheng Li +9 more
6/11/2024
cs.SDcs.AIeess.AS

No official code found. Best implementation: StammerTalk/interspeech2024-code (9 stars, last commit 2024-06-07).

Abstract

The rapid advancements in speech technologies over the past two decades have led to human-level performance in tasks like automatic speech recognition (ASR) for fluent speech. However, the efficacy of these models diminishes when applied to atypical speech, such as stuttering. This paper introduces AS-70, the first publicly available Mandarin stuttered speech dataset, which stands out as the largest dataset in its category. Encompassing conversational and voice command reading speech, AS-70 includes verbatim manual transcription, rendering it suitable for various speech-related tasks. Furthermore, baseline systems are established, and experimental results are presented for ASR and stuttering event detection (SED) tasks. By incorporating this dataset into the model fine-tuning, significant improvements in the state-of-the-art ASR models, e.g., Whisper and Hubert, are observed, enhancing their inclusivity in addressing stuttered speech.

View on arXivView PDF

Code Implementations(1)

StammerTalk/interspeech2024-codeCommunity68%

Code for Interspeech2024 paper "AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection"

91Shell, PythonJun 7, 20242 years ago

Similar Papers

Self-supervised Speech Models for Word-Level Stuttered Speech Detection

84% match2024

Optimizing Multi-Stuttered Speech Classification: Leveraging Whisper's Encoder for Efficient Parameter Reduction in Automated Assessment

83% match2024

StutterZero and StutterFormer: End-to-End Speech Conversion for Stuttering Transcription and Correction

82% match2025

Whisper in Focus: Enhancing Stuttered Speech Classification with Encoder Layer Optimization

82% match2023

Revisiting Rule-Based Stuttering Detection: A Comprehensive Analysis of Interpretable Models for Clinical Applications

81% match2025

Stuttering-Aware Automatic Speech Recognition for Indonesian Language

81% match2026

Cite this paper

@article{gong2024as,
  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},
  url    = {http://arxiv.org/abs/2406.07256v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.07256.svg)](https://codeofpaper.com/paper/2406.07256)

Discussion