Perfect Match: Improved Cross-modal Embeddings For Audio-visual Synchronisation

Abstract

This paper proposes a new strategy for learning powerful cross-modal embeddings for audio-to-video synchronization. Here, we set up the problem as one of cross-modal retrieval, where the objective is to find the most relevant audio segment given a short video clip. The method builds on the recent advances in learning representations from cross-modal self-supervision. The main contributions of this paper are as follows: (1) we propose a new learning strategy where the embeddings are learnt via a multi-way matching problem, as opposed to a binary classification (matching or non-matching) problem as proposed by recent papers; (2) we demonstrate that performance of this method far exceeds the existing baselines on the synchronization task; (3) we use the learnt embeddings for visual speech recognition in self-supervision, and show that the performance matches the representations learnt end-to-end in a fully-supervised manner.

Stats

• citations77
• S2 citations—
• github stars0
• HF likes0
• heat score14.19
• arxiv keychung2018perfect

Related papers

• Cross-modal Embeddings For Video And Audio Retrieval (2018)11.08
• Cross-modal Audio-visual Co-learning For Text-independent Speaker Verification (2023)9.23
• Looking Into Your Speech: Learning Cross-modal Affinity For Audio-visual Speech Separation (2021)11.67
• Improving Audio-visual Speech Recognition By Lip-subword Correlation Based Visual Pre-training And Cross-modal Fusion Encoder (2023)6.34
• Syncvsr: Data-efficient Visual Speech Recognition With End-to-end Crossmodal Audio Token Synchronization (2024)8.35
• Unified Video-language Pre-training With Synchronized Audio (2024)0.00
• Mmaudio: Taming Multimodal Joint Training For High-quality Video-to-audio Synthesis (2024)0.00
• Multi-modal Multi-correlation Learning For Audio-visual Speech Separation (2022)5.84