# Frequency bin-wise single channel speech presence probability estimation using multiple DNNs

## TL;DR

This paper introduces a frequency bin-wise speech presence probability estimation method using multiple DNNs, reducing model complexity and improving detection accuracy over traditional methods.

## Contribution

It proposes a novel frequency bin-wise approach with separate DNNs, lowering complexity and data requirements compared to conventional all-bin models.

## Key findings

- Improved speech detection accuracy with the bin-wise model
- Outperforms state-of-the-art SPP methods in accuracy
- Reduces model complexity significantly

## Abstract

In this work, we propose a frequency bin-wise method to estimate the single-channel speech presence probability (SPP) with multiple deep neural networks (DNNs) in the short-time Fourier transform domain. Since all frequency bins are typically considered simultaneously as input features for conventional DNN-based SPP estimators, high model complexity is inevitable. To reduce the model complexity and the requirements on the training data, we take a single frequency bin and some of its neighboring frequency bins into account to train separate gate recurrent units. In addition, the noisy speech and the a posteriori probability SPP representation are used to train our model. The experiments were performed on the Deep Noise Suppression challenge dataset. The experimental results show that the speech detection accuracy can be improved when we employ the frequency bin-wise model. Finally, we also demonstrate that our proposed method outperforms most of the state-of-the-art SPP estimation methods in terms of speech detection accuracy and model complexity.