arXiv:2607.07408v1 Announce Type: new Abstract: 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
The proliferation of advanced deep learning models like Whisper is enabling the application of sophisticated AI techniques to previously underserved languages and specific linguistic challenges.
This development addresses a critical gap in AI's ability to handle less dominant languages, potentially unlocking new markets and improving accessibility for non-English speakers.
The ability to accurately segment prosodic boundaries in Brazilian Portuguese using deep learning will enhance speech recognition, synthesis, and natural language processing applications for that language.
- · Brazilian Portuguese speakers
- · AI researchers in linguistics
- · Speech technology developers
- · Companies targeting Latin American markets
- · Rule-based language processing systems
- · Traditional machine-learning methods for BP prosody
Improved speech-to-text accuracy and naturalness for Brazilian Portuguese AI applications.
Increased adoption of voice interfaces and AI assistants in Brazil due to better language support.
The methodology could be rapidly adapted to other less-resourced languages, leading to a broader democratization of advanced speech AI capabilities globally.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL