Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{178119,
        author = {Priya Shetty and Vaibhavi Dongare and Samruddhi Bhandare and Aliza Sayyad and Mrs. Asharani Chadchankar},
        title = {Deep Attractor Models for Audio Source Separation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {2839-2843},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178119},
        abstract = {Audio source separation has seen substantial advancements with deep learning techniques, yet separating unknown speakers in real-world environments remains challenging. This study proposes a deep learning-based approach using attractor models, which map audio signals into a high-dimensional feature space for improved clustering of individual audio sources. Through the introduction of attractor points, our approach creates a robust, speaker-independent separation system that distinguishes multiple audio sources with high precision. By clustering audio features around defined centroids, this model enables applications in automatic speech recognition (ASR), speaker identification, audio enhancement, and more.},
        keywords = {},
        month = {May},
        }