Transformer-based segmentation of prosodic boundaries in Brazilian Portuguese
It provides the first deep learning approach for prosodic segmentation in Brazilian Portuguese, outperforming prior rule-based and traditional ML methods.
This paper introduces SAMPA, a Whisper-based segmenter for automatic prosodic boundary detection in Brazilian Portuguese, achieving F1 scores of 0.731 on held-out test data and 0.796 on an out-of-distribution dataset.
Automatic prosodic segmentation identifies boundaries between speech units from acoustic and linguistic evidence. Although recent deep learning approaches have produced strong results for English, automatic segmentation for Brazilian Portuguese (BP) still relies mostly 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-SP dataset and evaluate different training and test-time filtering configurations, including out-of-distribution testing on the MuPe-Diversidades dataset. SAMPA achieves competitive boundary-detection performance across settings, with the best models reaching F1=0.731 on the held-out test split and F1=0.796 on MuPe-Diversidades. Finally, through n-gram and acoustic-visual analyses, we show that our model follows morphosyntactic, semantic, and prosodic cues for detecting prosodic boundaries.