Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization
IEEE Open Journal of Signal Processing · 2026 · 7 · 800-808
DOI: 10.1109/ojsp.2026.3711530 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Open Journal of Signal Processing, 2026. Verfasst von Ryota Komatsu und 3 weiteren Autor:innen. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS KAKENHI.
Abstract (Originalsprache)
Unsupervised syllabic tokenization aims to learn discrete syllabic tokens that capture latent linguistic content-related structure from raw speech. Recent syllabic tokenization methods employ teacher-student distillation of the pretrained HuBERT to organize latent speech frame representations into syllabic segments. However, when trained with an utterance-level cross-entropy objective, the model predicts speaker identity rather than linguistic content, thereby compromising the purity of syllabic tokens. To address this problem, we propose a speaker-disentangled syllabic tokenizer that regresses speaker-perturbed student representations toward clean teacher targets within fixed-length chunks. Experimental results demonstrate that our proposed method achieves state-of-the-art performance in syllable boundary detection and syllabic segment clustering. Moreover, a speech language model trained on our syllabic tokens achieves a 7% relative improvement in syntactic and semantic understanding over the phone-level SpiRit-LM.
Förderung
- JSPS KAKENHI
Zitieren
APA
Komatsu, R., Kawakita, K., Okamoto, T., & Shinozaki, T. (2026). Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization. IEEE Open Journal of Signal Processing, 7, 800-808. https://doi.org/10.1109/ojsp.2026.3711530
Vancouver
Komatsu R, Kawakita K, Okamoto T, Shinozaki T. Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization. IEEE Open Journal of Signal Processing. 2026;7:800-808. doi:10.1109/ojsp.2026.3711530
BibTeX
@article{Komatsu2026,
author = {Komatsu, Ryota and Kawakita, Kota and Okamoto, Takuma and Shinozaki, Takahiro},
title = {Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization},
journal = {IEEE Open Journal of Signal Processing},
year = {2026},
volume = {7},
pages = {800--808},
doi = {10.1109/ojsp.2026.3711530}
}
EUVIMED