Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhou, Lifeng, Li, Yuke, Deng, Rui, Yang, Yuting, Zhu, Haoqi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2408.13705
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909311197773824
author Zhou, Lifeng
Li, Yuke
Deng, Rui
Yang, Yuting
Zhu, Haoqi
author_facet Zhou, Lifeng
Li, Yuke
Deng, Rui
Yang, Yuting
Zhu, Haoqi
contents The success of speech-image retrieval relies on establishing an effective alignment between speech and image. Existing methods often model cross-modal interaction through simple cosine similarity of the global feature of each modality, which fall short in capturing fine-grained details within modalities. To address this issue, we introduce an effective framework and a novel learning task named cross-modal denoising (CMD) to enhance cross-modal interaction to achieve finer-level cross-modal alignment. Specifically, CMD is a denoising task designed to reconstruct semantic features from noisy features within one modality by interacting features from another modality. Notably, CMD operates exclusively during model training and can be removed during inference without adding extra inference time. The experimental results demonstrate that our framework outperforms the state-of-the-art method by 2.0% in mean R@1 on the Flickr8k dataset and by 1.7% in mean R@1 on the SpokenCOCO dataset for the speech-image retrieval tasks, respectively. These experimental results validate the efficiency and effectiveness of our framework.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13705
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cross-Modal Denoising: A Novel Training Paradigm for Enhancing Speech-Image Retrieval
Zhou, Lifeng
Li, Yuke
Deng, Rui
Yang, Yuting
Zhu, Haoqi
Computation and Language
Sound
Audio and Speech Processing
The success of speech-image retrieval relies on establishing an effective alignment between speech and image. Existing methods often model cross-modal interaction through simple cosine similarity of the global feature of each modality, which fall short in capturing fine-grained details within modalities. To address this issue, we introduce an effective framework and a novel learning task named cross-modal denoising (CMD) to enhance cross-modal interaction to achieve finer-level cross-modal alignment. Specifically, CMD is a denoising task designed to reconstruct semantic features from noisy features within one modality by interacting features from another modality. Notably, CMD operates exclusively during model training and can be removed during inference without adding extra inference time. The experimental results demonstrate that our framework outperforms the state-of-the-art method by 2.0% in mean R@1 on the Flickr8k dataset and by 1.7% in mean R@1 on the SpokenCOCO dataset for the speech-image retrieval tasks, respectively. These experimental results validate the efficiency and effectiveness of our framework.
title Cross-Modal Denoising: A Novel Training Paradigm for Enhancing Speech-Image Retrieval
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2408.13705