Search

This paper introduces a practical approach for leveraging a real-time deep learning model to alternate between speech enhancement and joint speech enhancement and separation depending on whether the input mixture contains one or two active speakers. Scale-invariant signal-to-distortion ratio (SI-SDR) has shown to be a highly effective training measure in time-domain speech separation. However, the SI-SDR metric is ill-defined for zero-energy target signals, which is a problem when training a speech separation model using utterances with varying numbers of talkers. Unlike existing solutions that focus on modifying the loss function to accommodate zero-energy target signals, the proposed approach circumvents this problem by training the model to extract speech on both its output channels regardless if the input is a single or dual-talker mixture. A lightweight speaker overlap detection (SOD) module is also introduced to differentiate between single and dual-talker segments in real-time. The proposed module takes advantage of the new formulation by operating directly on the separated masks, given by the separation model, instead of the original mixture, thus effectively simplifying the detection task. Experimental results show that the proposed training approach outperforms existing solutions, and the SOD module exhibits high accuracy., Comment: 6 Pages, Accepted at IEEE Asilomar

This paper presents a method for real-time estimation of 2-dimensional direction of arrival (2D-DOA) of one or more sound sources using a nonlinear array of three microphones. 2D-DOA is estimated employing frame-level time difference of arrival (TDOA) measurements. Unlike conventional methods, which infer location parameters from TDOAs using a theoretical model, we propose a more practical approach based on supervised learning. The proposed model employs nearest neighbor search (NNS) applied to a spherical Fibonacci lattice consisting of TDOA to 2D-DOA mappings learned directly in the field. Filtering and clustering post-processors are also introduced for improved source detection and localization robustness., Comment: 5 pages, 6 figures

Invariance to microphone array configuration is a rare attribute in neural beamformers. Filter-and-sum (FS) methods in this class define the target signal with respect to a reference channel. However, this not only complicates formulation in reverberant conditions but also the network, which must have a mechanism to infer what the reference channel is. To address these issues, this study presents Delay Filter-and-Sum Network (DFSNet), a steerable neural beamformer invariant to microphone number and array geometry for causal speech enhancement. In DFSNet, acquired signals are first steered toward the speech source direction prior to the FS operation, which simplifies the task into the estimation of delay-and-summed reverberant clean speech. The proposed model is designed to incur low latency, distortion, and memory and computational burden, giving rise to high potential in hearing aid applications. Simulation results reveal comparable performance to noncausal state-of-the-art., Comment: 5 pages, 1 figure, 2 tables

This study presents a closed-form solution for localizing and synchronizing an acoustic sensor node with respect to a Wireless Acoustic Sensor Network (WASN). The aim is to allow efficient scaling of a WASN by individually calibrating newly joined sensor nodes instead of recalibrating the entire array. A key contribution is that the sensor to be calibrated does not need to include a built-in emitter. The proposed method uses signals emitted from spatially distributed sources to compute time difference of arrival (TDOA) measurements between the existing WASN and a new sensor. The problem is then modeled as a set of multivariate nonlinear TDOA equations. Through a simple transformation, the nonlinear TDOA equations are converted into a system of linear equations. Then, weighted least squares (WLS) is applied to find an accurate estimate of the calibration parameters. Signal sources can either be known emitters within the existing WASN or arbitrary sources in the environment, thus allowing for flexible applicability in both active and passive calibration scenarios. Simulation results under various conditions show high joint localization and synchronization performance, often comparable to the Cram\'er-Rao lower bound (CRLB)., Comment: To be submitted to the Journal of Acoustical Society of America for publication

This study presents UX-Net, a time-domain audio separation network (TasNet) based on a modified U-Net architecture. The proposed UX-Net works in real-time and handles either single or multi-microphone input. Inspired by the filter-and-process-based human auditory behavior, the proposed system introduces novel mixer and separation modules, which result in cost and memory efficient modeling of speech sources. The mixer module combines encoded input in a latent feature space and outputs a desired number of output streams. Then, in the separation module, a modified U-Net (UX) block is applied. The UX block first filters the encoded input at various resolutions followed by aggregating the filtered information and applying recurrent processing to estimate masks of separated sources. The letter 'X' in UX-Net is a name placeholder for the type of recurrent layer employed in the UX block. Empirical findings on the WSJ0-2mix benchmark dataset show that one of the UX-Net configurations outperforms the state-of-the-art Conv-TasNet system by 0.85 dB SI-SNR while using only 16% of the model parameters, 58% fewer computations, and maintaining low latency., Comment: Submitted to ICASSP 2023

In this paper, the coherence between speech and noise signals is used to obtain a Speech Enhancement (SE) gain function, in combination with a Super Gaussian Joint Maximum a Posteriori (SGJMAP) single microphone SE gain function. The proposed SE method can be implemented on a smartphone that works as an assistive device to hearing aids. Although coherence SE gain function suppresses the background noise well, it distorts the speech. In contrary, SE using SGJMAP improves speech quality with additional musical noise, which we contain by using a post filter. The weighted union of these two gain functions strikes a balance between noise suppression and speech distortion. A 'weighting' parameter is introduced in the derived gain function to allow the smartphone user to control the weighting factor based on different background noise and their comfort level of hearing. Objective and subjective measures of the proposed method show effective improvement in comparison to standard techniques considered in this paper for several noisy conditions at signal to noise ratio levels of -5 dB, 0 dB and 5 dB., Comment: 4 pages, 3 figures

Traditionally, Blind Speech Separation techniques are computationally expensive as they update the demixing matrix at every time frame index, making them impractical to use in many Real-Time applications. In this paper, a robust data-driven two-microphone sound source localization method is used as a criterion to reduce the computational complexity of the Independent Vector Analysis (IVA) Blind Speech Separation (BSS) method. IVA is used to separate convolutedly mixed speech and noise sources. The practical feasibility of the proposed method is proved by implementing it on a smartphone device to separate speech and noise in Real-World scenarios for Hearing-Aid applications. The experimental results with objective and subjective tests reveal the practical usability of the developed method in many real-world applications., Comment: 5 pages

In this letter, we derive a new super Gaussian Joint Maximum a Posteriori based single microphone speech enhancement gain function. The developed Speech Enhancement method is implemented on a smartphone, and this arrangement functions as an assistive device to hearing aids. We introduce a tradeoff parameter in the derived gain function that allows the smartphone user to customize their listening preference, by controlling the amount of noise suppression and speech distortion in real-time based on their level of hearing comfort perceived in noisy real world acoustic environment. Objective quality and intelligibility measures show the effectiveness of the proposed method in comparison to benchmark techniques considered in this paper. Subjective results reflect the usefulness of the developed Speech Enhancement application in real-world noisy conditions at signal to noise ratio levels of 0 dB and 5 dB., Comment: 5 pages