Skip to content
Hugging Face Daily Papers·· 2026-10-19AI score24

SEAM: A spectral embedding alignment and merging method for low-resource TTS

SEAM: Spectral Embedding Alignment and Merging for Low-Resource TTS

AI briefing

SEAM is a zero-audio initialization method that builds embeddings for unseen tokens using known subwords, preserves temporal phoneme order through spectral filtering, and aligns new embeddings to the pretrained conditioning manifold using closed-form ridge regression. Across three languages and two TTS architectures, SEAM approaches or matches baselines with up to 4x less training data, reducing sample complexity by 75% compared with random initialization and mean pooling. The work has been accepted to EMNLP 2026 Findings.

Open original arxiv.org