Contextual Metric Learning for Cross-Singer Timbre Retrieval under Recording Mismatch

Authors

  • Irfan Rashid Rashid

DOI:

https://doi.org/10.66421/int.j.datasci.intell.syst58

Keywords:

mbre Retrieval, Metric Learning, Domain Adaptation, Recording Mismatch, Music InforTimation Retrieval

Abstract

The accurate retrieval of vocal timbre across different singers remains a formidable challenge in the field of music information retrieval, primarily due to the complex entanglement of intrinsic vocal characteristics and extrinsic environmental factors. When vocal performances are captured across heterogeneous acoustic environments using diverse recording equipment, the resulting recording mismatches significantly degrade the performance of traditional retrieval systems. This paper introduces a novel framework termed Contextual Metric Learning designed explicitly to address cross-singer timbre retrieval under severe recording mismatches. By fundamentally rethinking the representation of acoustic space, the proposed methodology separates the singer identity and fundamental timbre properties from microphone frequency responses, room reverberation, and dynamic processing artifacts. We construct a multi-dimensional continuous embedding space where contextual information acts as a conditioning variable rather than a confounding factor. Through an extensive theoretical and empirical analysis, this study demonstrates that integrating environmental context into the metric learning objective allows the system to establish a domain-invariant timbre representation. The paper systematically details the progression of deep metric paradigms, introduces a highly specialized context-aware contrastive mechanism, and evaluates the framework against established baselines using synthetically mismatched and real-world audio datasets. The findings suggest a substantial improvement in retrieval precision and generalizability, offering a robust solution for large-scale audio database management, virtual singing synthesis, and advanced music production workflows.

References

1. Yu, H., Zhang, J., Chen, C., Xiang, T., Fang, Y., Niebles, J. C., & Adeli, E. (2026, March). Socialgen: Modeling multi-human social interaction with language models. In 2026 International Conference on 3D Vision (3DV) (pp. 1-17). IEEE.

2. Zhang, B., Wang, S., Jiang, Y., Sui, D., Tu, Z., & Chu, D. (2025, July). Ask and Retrieve Knowledge: Towards Proactive Asking with Imperfect Information in Medical Multi-turn Dialogues. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 1055-1065).

3. Yao, J., Jia, Y., Wang, X., & Khan, A. N. (2026). The digital gaze in retail encounters: AI face dialogues and consumer preference in the circular economy. Journal of Retailing and Consumer Services, 93, 104915.

4. Zhou, J., Xiong, H., Lu, J., Lin, Z., & Feng, B. (2025, September). Cgtgait: Collaborative graph and transformer for gait emotion recognition. In 2025 IEEE International Joint Conference on Biometrics (IJCB) (pp. 1-11). IEEE.

5. Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., et al. (2016). Deep Speech 2: End-to-end speech recognition in English and Mandarin. In Proceedings of ICML.

6. Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2023). Robust speech recognition via large-scale weak supervision. In Proceedings of ICML.

7. Zhao, R., Tang, J., Zeng, W., Guo, Y., & Zhao, X. (2025). Towards human-like questioning: Knowledge base question generation with bias-corrected reinforcement learning from human feedback. Information Processing & Management, 62(3), 104044.

8. Zhao, R., Zeng, W., Tang, J., Li, Y., Ye, G., Du, J., & Zhao, X. (2025, May). Towards unsupervised entity alignment for highly heterogeneous knowledge graphs. In 2025 IEEE 41St international conference on data engineering (ICDE) (pp. 3792-3806). IEEE.

9. Wang, Y., Wang, L., Li, V., & Tu, Z. (2020, November). On the sparsity of neural machine translation models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1060-1066).

10. Zhang, Z., Gao, S., Su, S., Sun, L., & Chen, R. (2023). MINING: Multi-granularity network alignment based on contrastive learning. IEEE Transactions on Knowledge and Data Engineering, 35(12), 12785-12798.

11. Yao, Y., Zhu, Z., Miao, P., Cheng, X., Shu, F., & Wang, J. (2025). Optimizing hybrid RIS-aided ISAC systems in V2X networks: A deep reinforcement learning method for anti-eavesdropping techniques. IEEE Transactions on Vehicular Technology, 74 (6), 9224-9239.

12. Wei, M., Li, R., Wang, L., Chang, Z., Xu, L., & Han, Z. (2026). Toward Adaptive Tracking and Communication via an Airborne Maneuverable Bi-Static ISAC System. IEEE Transactions on Vehicular Technology.

13. Li, Q., Ye, Q., Zhang, N., Zhang, W., & Hu, F. (2025). Digital-twin-enabled industrial IoT: Vision, framework, and future directions. IEEE Wireless Communications, 32(6), 173-181.

14. Li, S. (2025). Momentum, volume and investor sentiment study for us technology sector stocks—A hidden markov model based principal component analysis. PloS one, 20(9), e0331658.

15. Wang, S., Zhang, X., Wang, P., & Li, X. (2026). Design of Magnetic Sensor Array-Based PUFs for IoT Security. IEEE Transactions on Instrumentation and Measurement, 75, 1-9.

16. Li, X., Wang, P., Li, G., Ni, L., & Zhang, Y. (2023). Design of interface circuits and lightweight PUF for TMR sensors. IEEE Sensors Journal, 23(11), 11754-11761.

17. Qu, W., Shao, Y., Meng, L., Huang, X., & Xiao, L. (2024, June). A conditional denoising diffusion probabilistic model for point cloud upsampling. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 20786-20795). IEEE.

18. Lin, C. C., Li, G., Hung, C. C., Kuo, Y. C., & Peng, W. C. (2026). Rethinking suspicious account identification from a perspective of machine learning ranking. International Journal of Machine Learning and Cybernetics, 17(3), 84.

19. Yang, Z., Ji, W., & Wang, Z. (2024). Adaptive joint configuration optimization for collaborative inference in edge-cloud systems. Science China Information Sciences, 67(4), 149103.

20. Prescribed-time tracking control of MIMO nonlinear systems with nonvanishing uncertainties

21. Jia, Y., Wang, T., Xiao, K., & Guo, C. (2020). How to reduce opportunism through contractual governance in the cross-cultural supply chain context: evidence from Chinese exporters. Industrial Marketing Management, 91, 323-337.

22. Yang, R., & Gupta, R. (2025). DREAM: Distributed Regional Efficient Agent Management with LLMs for Online Multi-Agent Pathfinding. ACM SIGOPS Operating Systems Review, 59(1), 24-33.

Downloads

Published

2026-08-29