English

Direction of Arrival Correction through Speech Quality Feedback

Audio and Speech Processing 2025-01-08 v1 Artificial Intelligence

Abstract

Real-time speech enhancement has began to rise in performance, and the Demucs Denoiser model has recently demonstrated strong performance in multiple-speech-source scenarios when accompanied by a location-based speech target selection strategy. However, it has shown to be sensitive to errors in the direction-of-arrival (DOA) estimation. In this work, a DOA correction scheme is proposed that uses the real-time estimated speech quality of its enhanced output as the observed variable in an Adam-based optimization feedback loop to find the correct DOA. In spite of the high variability of the speech quality estimation, the proposed system is able to correct in real-time an error of up to 15o^o using only the speech quality as its guide. Several insights are provided for future versions of the proposed system to speed up convergence and further reduce the speech quality estimation variability.

Keywords

Cite

@article{arxiv.2408.07234,
  title  = {Direction of Arrival Correction through Speech Quality Feedback},
  author = {Caleb Rascon},
  journal= {arXiv preprint arXiv:2408.07234},
  year   = {2025}
}

Comments

Submitted to Digital Signal Processing

R2 v1 2026-06-28T18:12:21.863Z