Hybrid Dictionary Based Incoherent Speech Separation Using Sparse Bayesian Learning

DOI

10.2991/978-94-6463-852-3_24How to use a DOI?

Keywords

Underdetermined Source Separation; Compressed Sensing; Non-Negative Sparse Bayesian Learning; Speech Signal Separation; K-means Clustering; Basis Vectors

Abstract

Undetermined source separation problem using compressed sensing technique is the emerging data reconstruction algorithms. This paper develops the advanced basis vector based Non-negative sparse Bayesian learning (NNSBL) algorithm for speech separation. The manifold matrix that is developed for sparse Bayesian learning framework is made more stochastic by introducing the combination of basis vectors to obtain better source separation efficiency. Autocalibration sparse Bayesian learning algorithm is applied after applying the K-means clustering algorithm on the speech signal to estimate speech mixtures. Performance metrics for the proposed algorithm is detailed in the discussions that follow.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ramjan Khatik
AU  - Afzal Shaikh
PY  - 2025
DA  - 2025/10/07
TI  - Hybrid Dictionary Based Incoherent Speech Separation Using Sparse Bayesian Learning
BT  - Proceedings of the MULTINOVA: First International Conference on Artificial Intelligence in Engineering, Healthcare and Sciences (ICAIEHS- 2025)
PB  - Atlantis Press
SP  - 386
EP  - 397
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-852-3_24
DO  - 10.2991/978-94-6463-852-3_24
ID  - Khatik2025
ER  -