Cross-Modal Simplex Center Learning for Speech-Face Association
Source abstract
Abstract
Speech-face association aims to achieve identity matching between facial images and voice segments by aligning cross-modal features. Existing research primarily focuses on learning shared-space representations and computing o... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Speech and Audio Processing · Face recognition and analysis · Face and Expression Recognition
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (44)
Show source-provided references
1. FairFace: face attribute dataset for balanced race, gender, and age for bias measurement and mitigation
2. Voxceleb enrichment for age and gender recognition
3. Putting the face to the voice: matching identity across modality10.1016/j.cub.2003.09.005 ↗
4. Electrocorticography reveals the dynamics of famous voice responses in human fusiform gyrus10.1152/jn.00459.2022 ↗
5. Learnable PINs: cross-modal embeddings for person identity
6. Seeing voices and hearing faces: cross-modal biometric matching
7. Face-voice matching using cross-modal embeddings
8. On learning associations of faces and voices
9. Triplet-center loss for multi-view 3D object retrieval
10. Yang S, Tantrawenith M, Zhuang H, Zhiyong W, Aolan S, Jianzong W, et al. Speech representation disentanglement with adversarial mutual information learning for one-shot voice conversion. doi:10.48550/arXiv.2208.08757.
11. Learnable pillar-based re-ranking for image-text retrieval
12. FaceFormer: speech-driven 3D facial animation with transformers
13. Image-text retrieval: a survey on recent research and development
14. Aligning cross-modal entities for image-text retrieval upon vision-language pre-trained models
15. Achieving cross modal generalization with multimodal unified representation
16. CDS: cross-domain self-supervised pre-training
17. Learning semantic relationship among instances for image-text matching
18. Learning visual representation from modality-shared contrastive language-image pre-training
19. Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval
20. Deep cross-modal projection learning for image-text matching
21. CM-GANs: cross-modal generative adversarial networks for common representation learning10.1145/3284750 ↗
22. Supervised cross-modal contrastive learning for audio-visual coding
23. Causality-invariant interactive mining for cross-modal similarity learning10.1109/TPAMI.2024.3379752 ↗
24. Cross-modal discrete representation learning
25. Cross-modal center loss for 3D cross-modal retrieval
26. Cross-modal embeddings for video and audio retrieval
27. Masking modalities for cross-modal video retrieval
28. Listen and look: multi-modal aggregation and co-attention network for video-audio retrieval
29. Video and audio are images: a cross-modal mixer for original data on video-audio retrieval10.1016/j.knosys.2024.112076 ↗
30. Deep latent space learning for cross-modal mapping of audio and visual signals
31. Seeking the shape of sound: an adaptive framework for learning voice-face association
32. Wen Y, Al Ismail M, Liu W, Raj B, Singh R. Disjoint mapping network for cross-modal matching of voices and faces. In: ICLR 2019; 2019 [cited 2024 Nov 11]. p. 1–17. Available from: https://api.semanticscholar.org/Corpus.
33. Adversarial-metric learning for audio-visual cross-modal matching10.1109/TMM.2021.3050089 ↗
34. Deep face recognition
35. CNN architectures for large-scale audio classification
36. A discriminative feature learning approach for deep face recognition
37. Regular polytope networks10.1109/TNNLS.2021.3056762 ↗
38. Prototype softmax cross entropy: a new perspective on softmax cross entropy
39. Deep simplex classifier for maximizing the margin in both Euclidean and angular spaces
40. Geometric representation of high dimension, low sample size data10.1111/j.1467-9868.2005.00510.x ↗
41. FaceNet: a unified embedding for face recognition and clustering
42. ARTriViT: automatic face recognition system using ViT-based siamese neural networks with a triplet loss
43. Learning discriminative joint embeddings for efficient face and voice association
44. Nagrani A, Chung JS, Zisserman A. VoxCeleb: a Large-Scale Speaker Identification Dataset. 2017. doi:10.48550/arXiv.1706.08612.10.21437/Interspeech.2017-950 ↗