The article discusses the importance of syllable stress in English pronunciation and the potential misunderstandings that can arise from incorrect syllable stress. The authors present a self-attention model for the detection of syllable stress levels in spoken English, considering various prosodic and categorical features. The model predicts syllable-level stresses with an accuracy of over 88% and 93% on different datasets. The authors suggest that this model could be beneficial in various scenarios, such as online meetings and English learning.
Publication date: 3 Nov 2023
Project Page: https://github.com/wangweiying303/stress-detection-model
Paper: https://arxiv.org/pdf/2311.00301
