.png){kind=icon}
.png){kind=icon}
Return
Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization
.png){kind=icon}
OA
AI
DOI：10.1109/ojsp.2026.3711530.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Self-supervised learning
speech language models
speech tokenization
syllable discovery
Journal
IF:
2.7
Papers:
140
Citations:
535