LipSody: Lip-to-Speech Synthesis with Enhanced Prosody Consistency

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Jaejun, Oh, Yoori, Lee, Kyogu
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914301264003072
author Lee, Jaejun
Oh, Yoori
Lee, Kyogu
author_facet Lee, Jaejun
Oh, Yoori
Lee, Kyogu
contents Lip-to-speech synthesis aims to generate speech audio directly from silent facial video by reconstructing linguistic content from lip movements, providing valuable applications in situations where audio signals are unavailable or degraded. While recent diffusion-based models such as LipVoicer have demonstrated impressive performance in reconstructing linguistic content, they often lack prosodic consistency. In this work, we propose LipSody, a lip-to-speech framework enhanced for prosody consistency. LipSody introduces a prosody-guiding strategy that leverages three complementary cues: speaker identity extracted from facial images, linguistic content derived from lip movements, and emotional context inferred from face video. Experimental results demonstrate that LipSody substantially improves prosody-related metrics, including global and local pitch deviations, energy consistency, and speaker similarity, compared to prior approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2602_01908
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LipSody: Lip-to-Speech Synthesis with Enhanced Prosody Consistency
Lee, Jaejun
Oh, Yoori
Lee, Kyogu
Sound
Lip-to-speech synthesis aims to generate speech audio directly from silent facial video by reconstructing linguistic content from lip movements, providing valuable applications in situations where audio signals are unavailable or degraded. While recent diffusion-based models such as LipVoicer have demonstrated impressive performance in reconstructing linguistic content, they often lack prosodic consistency. In this work, we propose LipSody, a lip-to-speech framework enhanced for prosody consistency. LipSody introduces a prosody-guiding strategy that leverages three complementary cues: speaker identity extracted from facial images, linguistic content derived from lip movements, and emotional context inferred from face video. Experimental results demonstrate that LipSody substantially improves prosody-related metrics, including global and local pitch deviations, energy consistency, and speaker similarity, compared to prior approaches.
title LipSody: Lip-to-Speech Synthesis with Enhanced Prosody Consistency
topic Sound
url https://arxiv.org/abs/2602.01908