• Corpus ID: 238583328

Direct source and early reflections localization using deep deconvolution network under reverbrate environment

@article{Gao2021DirectSA,
  title={Direct source and early reflections localization using deep deconvolution network under reverbrate environment},
  author={Shan Gao and Xihong Wu and Tianshu Qu},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.04850}
}
  • Shan Gao, Xihong Wu, T. Qu
  • Published 10 October 2021
  • Computer Science, Engineering
  • ArXiv
This paper proposes a deconvolution-based network (DCNN) model for DOA estimation of direct source and early reflections under reverberant scenarios. Considering that the firstorder reflections of the sound source also contain spatial directivity like the direct source, we treat both of them as the sources in the learning process. We use the covariance matrix of high order Ambisonics (HOA) signals in time domain as the input feature of the network, which is concise while contains precise… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 20 REFERENCES
Direction of Arrival Estimation for Multiple Sound Sources Using Convolutional Recurrent Neural Network
TLDR
The results show that the proposed DOAnet is capable of estimating the number of sources and their respective DOAs with good precision and generate SPS with high signal-to-noise ratio.
A learning-based approach to direction of arrival estimation in noisy and reverberant environments
TLDR
A learning-based approach that can learn from a large amount of simulated noisy and reverberant microphone array inputs for robust DOA estimation and uses a multilayer perceptron neural network to learn the nonlinear mapping from such features to the DOA.
Sound source localization based on deep neural networks with directional activate function exploiting phase information
  • Ryu Takeda, Kazunori Komatani
  • Computer Science
    2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2016
TLDR
This paper describes sound source localization (SSL) based on deep neural networks (DNNs) using discriminative training and indicates that the method outperformed the naive DNN-based SSL by 20 points in terms of the block-level accuracy.
Room geometry inference based on spherical microphone array eigenbeam processing.
TLDR
A novel method for three-dimensional room geometry inference based on robust and high-resolution beamforming techniques for spherical microphone arrays is presented and high accuracy is confirmed by experimental evaluations based on both simulated and measured data.
Signal enhancement using beamforming and nonstationarity with applications to speech
TLDR
This paper considers a sensor array located in an enclosure, where arbitrary transfer functions (TFs) relate the source signal and the sensors, and derives a suboptimal algorithm that can be implemented by estimating theTFs ratios, instead of estimating the TFs.
Localization of distinct reflections in rooms using spherical microphone array eigenbeam processing.
This paper presents an experimental and comparative study of several spherical microphone array eigenbeam (EB) processing techniques for localization of early reflections in room acoustic
A neural network based algorithm for speaker localization in a multi-room environment
TLDR
A Speaker Localization algorithm based on Neural Networks for multi-room domestic scenarios is proposed and outperforms the reference one, providing an average localization error, expressed in terms of RMSE, equal to 525 mm against 1465 mm.
Broadband doa estimation using convolutional neural networks trained with noise signals
  • Soumitro Chakrabarty, E. Habets
  • Computer Science, Mathematics
    2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)
  • 2017
TLDR
Through experimental evaluation, the ability of the proposed noise trained CNN framework to generalize to speech sources is demonstrated and the robustness of the system to noise, small perturbations in microphone positions, as well as its ability to adapt to different acoustic conditions is investigated.
Multiple emitter location and signal Parameter estimation
TLDR
The multiple signal classification (MUSIC) algorithm is described, which provides asymptotically unbiased estimates of number of incident wavefronts present and directions of arrival (DOA) (or emitter locations) and strengths and cross correlations among the incident waveforms.
Robust time delay estimation for sound source localization in noisy environments
This paper addresses the problem of robust localization of a sound source in a wide range of operating environments. We use fractional lower order statistics in the frequency domain of two-sensor
...
1
2
...