TY - GEN
T1 - Frequency bin-wise single channel speech presence probability estimation using multiple DNNs
AU - Tao, Shuai
AU - Reddy, Himavanth
AU - Jensen, Jesper Rindom
AU - Christensen, Mads Græsbøll
PY - 2023/6/4
Y1 - 2023/6/4
N2 - 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.
AB - 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.
KW - a posteriori probability
KW - frequency bin-wise
KW - gated recurrent units
KW - speech presence probability
U2 - 10.1109/ICASSP49357.2023.10096321
DO - 10.1109/ICASSP49357.2023.10096321
M3 - Article in proceeding
SN - 978-1-7281-6328-4
T3 - I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
SP - 1
EP - 5
BT - ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PB - IEEE
T2 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, ICASSPW 2023
Y2 - 4 June 2023 through 10 June 2023
ER -