A High SIR Low-overhead Implementation of Single-channel Speech Source Separation

Lawrence Nwaogo*, Jerker Björkqvist

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedingConference contributionScientificpeer-review

19 Downloads (Pure)


In the field of speech signal processing, speech source mixture separation is a known challenge. It is addressed by finding the closest estimate of the original speech source from the speech mixture. Source separation solutions can be based on multiple channels or single channel model. In multiple channels, multiple speakers and microphones are assumed while in single channel multiple speakers and a single microphone are assumed. One of the most widely used algorithms in the single-channel model is the Ideal Ratio Mask (IRM). Although IRM is efficient, it has a major drawback; the high memory footprint as it stores all frequency components of the Short-time Fourier transform (STFT). This makes it less suitable for embedded applications. We propose a solution based on the optimization of Mel-frequency Cepstrum Coefficient (MFCC) and Non-centroid K-nearest neighbor (Nk-nn) algorithms that minimizes memory utilization and achieves high Signal-to-Interference Ratio (SIR). Our experimental results show that the proposed solution improves SIR while minimizing memory requirements compared to the reference IRM.
Original languageEnglish
Title of host publication2022 IEEE 12th Sensor Array and Multichannel Signal Processing Workshop (SAM)
ISBN (Electronic)9781665406338
ISBN (Print)978-1-6654-0634-5
Publication statusPublished - 22 Jul 2022
MoE publication typeA4 Article in a conference publication
EventSensor Array and Multichannel Signal Processing Workshop -
Duration: 20 Jun 2022 → …


ConferenceSensor Array and Multichannel Signal Processing Workshop
Period20/06/22 → …


  • Source separation
  • Memory management
  • Signal processing algorithms
  • Cepstrum
  • Production facilities
  • Speech processing
  • Mel frequency cepstral coefficient


Dive into the research topics of 'A High SIR Low-overhead Implementation of Single-channel Speech Source Separation'. Together they form a unique fingerprint.

Cite this