Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained With Noise Signals

By Soumitro Chakrabarty, Emanuël Habets. IEEE Journal on Selected Topics in Signal Processing, 2018

305 citations recorded by the source corpus.

Supervised learning-based methods for source localization, being data driven, can be adapted to different acoustic conditions via training and have been shown to be robust to adverse acoustic environments. In this paper, a convolutional neural network (CNN) based supervised learning method for estimating the direction of arrival (DOA) of multiple speakers is proposed. Multi-speaker DOA estimation is formulated as a multi-class multi-label classification problem, where the assignment of each DOA label to the input feature is treated as a separate binary classification problem. The phase component of the short-time Fourier transform (STFT) coefficients of the received microphone signals are directly fed into the CNN, and the features for DOA estimation are learnt during training. Utilizing the assumption of disjoint speaker activity in the STFT domain, a novel method is proposed to train the CNN with synthesized noise signals. Through experimental evaluation with both simulated and measured acoustic impulse responses, the ability of the proposed DOA estimation approach to adapt to unseen acoustic conditions and its robustness to unseen noise type is demonstrated. Through additional empirical investigation, it is also shown that with an array of M microphone our proposed framework yields the best localization performance with M-1 convolution layers. The ability of the proposed method to accurately localize speakers in a dynamic acoustic scenario with varying number of sources is also shown.

Subfields: Oceanography, Signal Processing

View Paper: https://www.semanticscholar.org/paper/a640c1ecd2a55931f7d5c71f24ba2bee7400d21e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Oceanography

In Signal Processing

Citations in the corpus

Deep Networks for Direction-of-Arrival Estimation in Low SNR (2020, methodology): “A CNN for broadband DoA estimation in the context of speech processing was proposed in [23], [24].”
A Survey of Sound Source Localization with Deep Learning Methods (2021, methodology): “In [136], Chakrabarty and Habets showed that, for a M microphone array, the optimal number of convolutional layers (which was M−1 in the conventional convolution framework, as proved in [39]) can be reduced by incorporating dilated convolutions with gradually increasing dilation factors.”
Machine learning in acoustics: Theory and applications. (2019, background): “107,116,128 We expect this trend to continue, with an emphasis on meth-ods that do not require a large set of labeled data.”