Metraipolis › archive › dc_686d4312a1dc

Training-Free Pronunciation Transcription via Text-Constrained Acoustic Rescoring — arXiv:2609.30924

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30924
License (as archived)
CC0-1.0
Archived
2026-10-08T02:04:03.072Z
SHA-256 of the archived text
6fb50357872113a910a8ae7254bf686520f03e5f718f35e8c5e0450ac8e0dcf1
Stable URL of this page
https://metraipolis.com/documento/dc_686d4312a1dc

How to cite

Training-Free Pronunciation Transcription via Text-Constrained Acoustic Rescoring — arXiv:2609.30924 — arXiv (en), https://arxiv.org/abs/2609.30924 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_686d4312a1dc (Metraipolis archive dc_686d4312a1dc, sha256 6fb50357872113a910a8ae7254bf686520f03e5f718f35e8c5e0450ac8e0dcf1)
BibTeX
@misc{dc686d4312a1dc,
  title = {Training-Free Pronunciation Transcription via Text-Constrained Acoustic Rescoring — arXiv:2609.30924},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30924},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_686d4312a1dc; sha256 6fb50357872113a910a8ae7254bf686520f03e5f718f35e8c5e0450ac8e0dcf1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30924. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate and efficient pronunciation transcription is essential for preparing text-to-speech training data at scale. Existing approaches have different limitations: grapheme-to-pronunciation (G2P) and speech-to-pronunciation (S2P) methods each capture only partial information, using only text or only speech, while speech-and-text-to-pronunciation (ST2P) methods use both but require costly pronunciation-annotated data. To address this problem, we propose a training-free ST2P pipeline that integrates both lexical and acoustic information at inference time. Lexical resources and G2P tools generate text-constrained candidates, and a left-to-right greedy search selects the best one using whole-sequence negative log-likelihoods from frozen pretrained S2P models. On three Japanese corpora, our method reduces Character Error Rate (CER) from 0.60--1.40\% (text-only baseline) to 0.04--0.17\% with reference transcripts, and 0.64--1.58\% with ASR transcripts. It outperforms all baselines, including a trained ST2P model and commercial multimodal LLMs. Our greedy search method is 3--3.5$\times$ faster than beam search at similar CER, and the cascade is 2$\times$ faster than direct decoding ensuring the efficiency and accuracy. In Spanish, French, and preliminary English, it also surpasses four open multimodal LLMs and the best traditional methods.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Sound (cs.SD); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.30924 — 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 2026-10-08T01:38:49.448Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).