Metraipolis › archive › dc_4189a5bfb008

Pronunciation Editing for Finnish Speech using Phonetic Posteriorgrams — arXiv:2507.02115

Source
arXiv (en)
Original
https://arxiv.org/abs/2507.02115
License (as archived)
CC0-1.0
Archived
2026-10-07T11:23:32.144Z
SHA-256 of the archived text
104e1a6c00a7f1ee156d53f4f85770a07083176b43827232261cf514f922cdb5
Stable URL of this page
https://metraipolis.com/documento/dc_4189a5bfb008

How to cite

Pronunciation Editing for Finnish Speech using Phonetic Posteriorgrams — arXiv:2507.02115 — arXiv (en), https://arxiv.org/abs/2507.02115 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4189a5bfb008 (Metraipolis archive dc_4189a5bfb008, sha256 104e1a6c00a7f1ee156d53f4f85770a07083176b43827232261cf514f922cdb5)
BibTeX
@misc{dc4189a5bfb008,
  title = {Pronunciation Editing for Finnish Speech using Phonetic Posteriorgrams — arXiv:2507.02115},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2507.02115},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4189a5bfb008; sha256 104e1a6c00a7f1ee156d53f4f85770a07083176b43827232261cf514f922cdb5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2507.02115. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Synthesizing second-language (L2) speech is potentially highly valued for L2 language learning experience and feedback. However, due to the lack of L2 speech synthesis datasets, it is difficult to synthesize L2 speech for low-resourced languages. In this paper, we provide a practical solution for editing native speech to approximate L2 speech and present PPG2Speech, a diffusion-based multispeaker Phonetic-Posteriorgrams-to-Speech model that is capable of editing a single phoneme without text alignment. We use Matcha-TTS's flow-matching decoder as the backbone, transforming Phonetic Posteriorgrams (PPGs) to mel-spectrograms conditioned on external speaker embeddings and pitch. PPG2Speech strengthens the Matcha-TTS's flow-matching decoder with Classifier-free Guidance (CFG) and Sway Sampling. We also propose a new task-specific objective evaluation metric, the Phonetic Aligned Consistency (PAC), between the edited PPGs and the PPGs extracted from the synthetic speech for editing effects. We validate the effectiveness of our method on Finnish, a low-resourced, nearly phonetic language, using approximately 60 hours of data. We conduct objective and subjective evaluations of our approach to compare its naturalness, speaker similarity, and editing effectiveness with TTS-based editing. Our source code is published at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2507.02115 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T11:15:39.468Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).