
NL
Nan Lu, Qifan Liang
· 1 min read
ResearcharXiv cs.CV
Speaking-Clock Mamba: Phoneme-Conditioned State-Space Modeling for Visual Forced Alignment
arXiv:2611.18667v1 Announce Type: new
Abstract: Visual forced alignment (VFA) locates phoneme and word boundaries in a silent talking-face video given its transcript. Existing methods mainly enforce transcript order at the decoding stage, leaving the encoder without an explicit mechanism to anchor its temporally evolving representation to transcript progress. As a result, phoneme-specific evidence is blurred and alignment drift accumulates over long sequences. In this paper, we propose Speaking-Clock Mamba, which makes transcript progress part of the temporal recurrence. A selective state-space (Mamba) backbone is inserted between the visual frontend and the Conformer cross-attention encoder, and a Phoneme-Conditioned Selective Scan (PCSS) conditions its input-dependent step size on a supervised, structurally monotone speaking clock that estimates progress through the transcript. Since causal and bidirectional variants of this backbone make complementary errors, a training-free selector picks the more confident alignment per utterance. Experiments on LRS2 and LRS3 show consistent gains over protocol-matched baselines, and the supervised clock provides an explicit estimate of alignment progress.
Original source
This story was published by arXiv cs.CV and written by Nan Lu, Qifan Liang. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


