Speech-to-image generation method based on a single-stage framework
CSTR:
Author:
Affiliation:

(School of Air Traffic Control and Navigation, Air Force Engineering University, Xian 710051, China)

Clc Number:

V247

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    To address the challenges in multi-stage speech-to-image generation process, such as the generators lack of integration and refinement of images, as well as the increased complexity and training costs associated with training multiple adversarial networks, we propose a single-stage speech-to-image generative adversarial network framework (Single-S2IGAN). This framework builds upon conditional generative adversarial networks by introducing a visual speech fusion module (VSFM), which consists of batch normalization (BN), a pixel-attention module (MPA), a speech modulation module (MSM), and a weighted fusion module (MWF). BN is used to stabilize the training of the network; MPA models the semantic relationships between spatial pixel regions and assigns higher weights to key positions. MSM modulates visual feature maps using fine-grained linguistic cues from the speech vector; and MWF adaptively captures the semantic importance of MPA and MSM at the channel level. A series of experiments were conducted on four benchmark datasets: CUB bird, Oxford-102, Flickr8k, and Places-subset. The results indicate that Single-S2IGAN can generate high-resolution images that are semantically consistent with the input speech descriptions. Compared to both single-stage and multi-stage frameworks, Single-S2IGAN demonstrates superior performance, with levels of effectiveness approaching those of text-to-image generation methods. The proposed Single-S2IGAN framework offers a new perspective for research into speech-to-image generation tasks.

    Reference
    Related
    Cited by
Get Citation
Related Videos

Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:March 25,2024
  • Revised:
  • Adopted:
  • Online: October 11,2026
  • Published:
Article QR Code