English

Deep neural network Based Low-latency Speech Separation with Asymmetric analysis-Synthesis Window Pair

Audio and Speech Processing 2021-06-23 v1 Sound

Abstract

Time-frequency masking or spectrum prediction computed via short symmetric windows are commonly used in low-latency deep neural network (DNN) based source separation. In this paper, we propose the usage of an asymmetric analysis-synthesis window pair which allows for training with targets with better frequency resolution, while retaining the low-latency during inference suitable for real-time speech enhancement or assisted hearing applications. In order to assess our approach across various model types and datasets, we evaluate it with both speaker-independent deep clustering (DC) model and a speaker-dependent mask inference (MI) model. We report an improvement in separation performance of up to 1.5 dB in terms of source-to-distortion ratio (SDR) while maintaining an algorithmic latency of 8 ms.

Keywords

Cite

@article{arxiv.2106.11794,
  title  = {Deep neural network Based Low-latency Speech Separation with Asymmetric analysis-Synthesis Window Pair},
  author = {Shanshan Wang and Gaurav Naithani and Archontis Politis and Tuomas Virtanen},
  journal= {arXiv preprint arXiv:2106.11794},
  year   = {2021}
}

Comments

Accepted to EUSIPCO-2021

R2 v1 2026-06-24T03:28:12.316Z