2026-10-27 · ArXiv
arXiv:2607.07408v3 Announce Type: replace-cross
Abstract: Automatic prosodic segmentation identifies boundaries between speech units based on acoustic and linguistic evidence. Although recent deep learning approaches have achieved strong results for English, automatic segmentation for Brazilian Portuguese (BP) still relies largely on rule-based or traditional machine-learning methods. This paper presents SAMPA, a Whisper-based segmenter that transcribes BP speech while inserting explicit markers for terminal prosodic boundaries. We fine-tune Whisper large-v3 on manually segmented recordings from the NURC-Sampa dataset and evaluate different training and test-time filtering configurations, including out-of-distribution testing on the MuPe-Diversidades dataset. Without test-time filtering, the best models reach f1 binary of 0.730 on the held-out test split and 0.793 on MuPe-Diversidades, outperforming an out-of-the-box Whisper baseline and a retrained feature-based classifier. Finally, n-gram and acoustic-visual analyses provide qualitative observations that help interpret the model's predictions and formulate hypotheses about the linguistic and prosodic cues that may influence its boundary decisions.
原文链接：https://arxiv.org/abs/2607.07408
查看更多资讯请见 AI 行业资讯。