Traditional Blind Source Separation Evaluation (BSS-Eval) metrics were originally designed to evaluate linear audio source separation models based on methods such as time-frequency masking. However, recent generative models may introduce nonlinear relationships between the separated and reference signals, limiting the reliability of these metrics for objective evaluation. To address this issue, we conduct a Degradation Category Rating listening test and analyze correlations between the obtained degradation mean opinion scores (DMOS) and a set of objective audio quality metrics for the task of singing voice separation. We evaluate three state-of-the-art discriminative models and two new competitive generative models. For both discriminative and generative models, intrusive embedding-based metrics show higher correlations with DMOS than conventional intrusive metrics such as BSS-Eval. For discriminative models, the highest correlation is achieved by the MSE computed on Music2Latent embeddings. When it comes to the evaluation of generative models, the strongest correlations are evident for the multi-resolution STFT loss and the MSE calculated on MERT-L12 embeddings, with the latter also providing the most balanced correlation across both model types. Our results highlight the limitations of BSS-Eval metrics for evaluating generative singing voice separation models and emphasize the need for careful selection and validation of alternative evaluation metrics for the task of singing voice separation.
This study introduces a novel unsupervised approach for separating overlapping heart and lung sounds using variational autoencoders (VAEs). In clinical settings, these sounds often interfere with each other, making manual separation difficult and error-prone. The proposed model learns to encode mixed signals into a structured latent space and reconstructs the individual components using a probabilistic decoder, all without requiring labeled data or prior knowledge of source characteristics. We apply this method to real recordings obtained from a clinical manikin using a digital stethoscope. Results demonstrate distinct latent clusters corresponding to heart and lung sources, as well as accurate reconstructions that preserve key spectral features of the original signals. The approach offers a robust and interpretable solution for blind source separation and has potential applications in portable diagnostic tools and intelligent stethoscope systems.
Imagine being in a crowded space where people speak a different language and having hearables that transform the auditory space into your native language, while preserving the spatial cues for all speakers. We introduce spatial speech translation, a novel concept for hearables that translate speakers in the wearer's environment, while maintaining the direction and unique voice characteristics of each speaker in the binaural output. To achieve this, we tackle several technical challenges spanning blind source separation, localization, real-time expressive translation, and binaural rendering to preserve the speaker directions in the translated audio, while achieving real-time inference on the Apple M2 silicon. Our proof-of-concept evaluation with a prototype binaural headset shows that, unlike existing models, which fail in the presence of interference, we achieve a BLEU score of up to 22.01 when translating between languages, despite strong interference from other speakers in the environment. User studies further confirm the system's effectiveness in spatially rendering the translated speech in previously unseen real-world reverberant environments. Taking a step back, this work marks the first step towards integrating spatial perception into speech translation.
Quantum machine intelligence starts showing its impact on satellite remote sensing (SRS). Also, recent literature exhibits that quantum generative intelligences encompass superior potential than their classical counterpart, motivating us to develop quantum generative adversarial networks (GANs) for SRS. However, existing quantum GANs are restricted by the limited quantum bit (qubit) resources of current quantum computers and process merely a small 2x2 grayscale image, far from being applicable to SRS. Recently, the novel concept of hybrid quantum-classical GAN, a quantum generator with a classical discriminator, has upgraded the order to 28x28 (still grayscale), whereas it is still insufficient for SRS. This motivates us to design a radically new hybrid framework, where both generator and discriminator are hybrid architectures. We demonstrate this feasibility, leading to a breakthrough of processing 128x128 hyperspectral images for SRS. Specifically, we design the quantum part with mathematically provable quantum full expressibility (FE) to address core signal processing tasks, wherein the FE property allows the quantum network to realize any valid quantum operator with appropriate training. The classical part, composed of convolutional layers, treats the read-in (compressing the optical information into limited qubits) and read-out (addressing the quantum collapse effect) procedures. The proposed innovative hybrid quantum GAN, named Hyperspectral Knot-like IntelligeNt dIscrimiNator and Generator (HyperKING), where knot partly symbolizes the quantum entanglement and partly the compressed quantum domain in the central part of the network architecture. HyperKING significantly surpasses the classical approaches in hyperspectral tensor completion, mixed noise removal (about 3dB improvement), and blind source separation results.
Biosignals can be viewed as mixtures measuring particular physiological events, and blind source separation (BSS) aims to extract underlying source signals from mixtures. This paper proposes a self-supervised multi-encoder autoencoder (MEAE) to separate heartbeat-related source signals from photoplethysmogram (PPG), enhancing heart rate (HR) detection in noisy PPG data. The MEAE is trained on PPG signals from a large open polysomnography database without any pre-processing or data selection. The trained network is then applied to a noisy PPG dataset collected during the daily activities of nine subjects. The extracted heartbeat-related source signal significantly improves HR detection as compared to the original PPG. The absence of pre-processing and the self-supervised nature of the proposed method, combined with its strong performance, highlight the potential of MEAE for BSS in biosignal analysis.
Separating sources is a common challenge in applications such as speech enhancement and telecommunications, where distinguishing between overlapping sounds helps reduce interference and improve signal quality. Additionally, in multichannel systems, correct calibration and synchronization are essential to separate and locate source signals accurately. This work introduces a method for blind source separation and estimation of the Time Difference of Arrival (TDOA) of signals in the time-frequency domain. Our proposed method effectively separates signal mixtures into their original source spectrograms while simultaneously estimating the relative delays between receivers, using Optimal Transport (OT) theory. By exploiting the structure of the OT problem, we combine the separation and delay estimation processes into a unified framework, optimizing the system through a block coordinate descent algorithm. We analyze the performance of the OT-based estimator under various noise conditions and compare it with conventional TDOA and source separation methods. Numerical simulation results demonstrate that our proposed approach can achieve a significant level of accuracy across diverse noise scenarios for physical speech signals in both TDOA and source separation tasks.
Single Image Reflection Removal (SIRR) is a canonical blind source separation problem and refers to the issue of separating a reflection-contaminated image into a transmission and a reflection image. The core challenge lies in minimizing the commonalities among different sources. Existing deep learning approaches either neglect the significance of feature interactions or rely on heuristically designed architectures. In this paper, we propose a novel Deep Exclusion unfolding Network (DExNet), a lightweight, interpretable, and effective network architecture for SIRR. DExNet is principally constructed by unfolding and parameterizing a simple iterative Sparse and Auxiliary Feature Update (i-SAFU) algorithm, which is specifically designed to solve a new model-based SIRR optimization formulation incorporating a general exclusion prior. This general exclusion prior enables the unfolded SAFU module to inherently identify and penalize commonalities between the transmission and reflection features, ensuring more accurate separation. The principled design of DExNet not only enhances its interpretability but also significantly improves its performance. Comprehensive experiments on four benchmark datasets demonstrate that DExNet achieves state-of-the-art visual and quantitative results while utilizing only approximately 8\% of the parameters required by leading methods.
Objective: Identifying the activity of motor neurons (MNs) non-invasively is possible by decomposing signals from muscles, e.g., surface electromyography (EMG) or ultrasound. The theoretical background of MN identification is convolutive blind source separation (cBSS), and different algorithms have been developed and validated. Yet, the existence and identifiability of inverse solutions and the corresponding estimation errors are not fully understood. Further, the guidelines for selecting appropriate parameters are often built on empirical observations, limiting the translation to clinical applications and other modalities. Approach: We revisited the cBSS model for MN identification, augmented it with new theoretical insights and derived a framework that can predict the existence of inverse solutions. This framework allows the quantification of estimation errors due to the imperfect inversion of the motor unit action potentials (MUAP), noise sources, and the ill-conditioning of the inverse problem. To bridge the gap between theory and practice, we used computer simulations. Main results: (1) Increasing the similarity of MUAPs or correlation between spike trains increases the bias for detecting high amplitude MUs. (2) The optimal objective function depends on the expected spike amplitude, spike amplitude statistics and the amplitude of background spikes. (3) There is some wiggle room for MN detection given non-stationary MUAPs. (4) There is no connection between MUAP duration and extension factor, in contrast to previous guidelines. (5) Source quality metrics like the silhouette score (SIL) or the pulse-to-noise ratio (PNR) are highly correlated with a source's objective function output. (6) SIL is superior to PNR. Significance: These findings will guide cBSS algorithm developments tailored to MN identification and clinical application translation.
Low-rank matrix factorizations are a class of linear models widely used in various fields such as machine learning, signal processing, and data analysis. These models approximate a matrix as the product of two smaller matrices, where the left matrix captures latent features while the right matrix linearly decomposes the data based on these features. There are many ways to define what makes a component "important." Standard LRMFs, such as the truncated singular value decomposition, focus on minimizing the distance between the original matrix and its low-rank approximation. In this thesis, the notion of "importance" is closely linked to interpretability and uniqueness, which are key to obtaining reliable and meaningful results. This thesis thus focuses on volume-based constraints and regularizations designed to enhance interpretability and uniqueness. We first introduce two new volume-constrained LRMFs designed to enhance these properties. The first assumes that data points are naturally bounded (e.g., movie ratings between 1 and 5 stars) and can be explained by convex combinations of features within the same bounds, allowing them to be interpreted in the same way as the data. The second model is more general, constraining the factors to belong to convex polytopes. Then, two variants of volume-regularized LRMFs are proposed. The first minimizes the volume of the latent features, encouraging them to cluster closely together, while the second maximizes the volume of the decompositions, promoting sparse representations. Across all these models, uniqueness is achieved under the core principle that the factors must be "sufficiently scattered" within their respective feasible sets. Motivated by applications such as blind source separation and missing data imputation, this thesis also proposes efficient algorithms that make these models practical for real-world applications.
Co-channel interference cancellation (CCI) is the process used to reduce interference from other signals using the same frequency channel, thereby enhancing the performance of wireless communication systems. An improvement to this approach is blind CCI, which reduces interference without relying on prior knowledge of the interfering signal characteristics. Recent work suggested using machine learning (ML) models for this purpose, but high-throughput ML solutions are still lacking, especially for edge devices with limited resources. This work explores the adaptation of U-Net Convolutional Neural Network models for high-throughput blind source separation. Our approach is established on architectural modifications, notably through quantization and the incorporation of depthwise separable convolution, to achieve a balance between computational efficiency and performance. Our results demonstrate that the proposed models achieve superior MSE scores when removing unknown interference sources from the signals while maintaining significantly lower computational complexity compared to baseline models. One of our proposed models is deeper and fully convolutional, while the other is shallower with a convolutional structure incorporating an LSTM. Depthwise separable convolution and quantization further reduce the memory footprint and computational demands, albeit with some performance trade-offs. Specifically, applying depthwise separable convolutions to the model with the LSTM results in only a 0.72% degradation in MSE score while reducing MACs by 58.66%. For the fully convolutional model, we observe a 0.63% improvement in MSE score with even 61.10% fewer MACs. Overall, our findings underscore the feasibility of using optimized machine-learning models for interference cancellation in devices with limited resources.
Sparse principal component analysis (sPCA) enhances the interpretability of principal components (PCs) by imposing sparsity constraints on loading vectors (LVs). However, when used as a precursor to independent component analysis (ICA) for blind source separation (BSS), sPCA may underperform due to its focus on simplicity, potentially disregarding some statistical information essential for effective ICA. To overcome this limitation, a sophisticated approach is proposed that preserves the interpretability advantages of sPCA while significantly enhancing its source extraction capabilities. This consists of two tailored algorithms, dissociative PCA (DPCA1 and DPCA2), which employ adaptive and firm thresholding alongside gradient and coordinate descent approaches to optimize the proposed model dynamically. These algorithms integrate left and right singular vectors from singular value decomposition (SVD) through dissociation matrices (DMs) that replace traditional singular values, thus capturing latent interdependencies effectively to model complex source relationships. This leads to refined PCs and LVs that more accurately represent the underlying data structure. The proposed approach avoids focusing on individual eigenvectors, instead, it collaboratively combines multiple eigenvectors to disentangle interdependencies within each SVD variate. The superior performance of the proposed DPCA algorithms is demonstrated across four varied imaging applications including functional magnetic resonance imaging (fMRI) source retrieval, foreground-background separation, image reconstruction, and image inpainting. They outperformed traditional methods such as PCA+ICA, PPCA+ICA, SPCA+ICA, PMD, and GPower.
With the emergence of wireless sensor networks (WSNs), many traditional signal processing tasks are required to be computed in a distributed fashion, without transmissions of the raw data to a centralized processing unit, due to the limited energy and bandwidth resources available to the sensors. In this paper, we propose a distributed independent component analysis (ICA) algorithm, which aims at identifying the original signal sources based on observations of their mixtures measured at various sensor nodes. One of the most commonly used ICA algorithms is known as FastICA, which requires a spatial pre-whitening operation in the first step of the algorithm. Such a pre-whitening across all nodes of a WSN is impossible in a bandwidth-constrained distributed setting as it requires to correlate each channel with each other channel in the WSN. We show that an explicit network-wide pre-whitening step can be circumvented by leveraging the properties of the so-called Distributed Adaptive Signal Fusion (DASF) framework. Despite the lack of such a network-wide pre-whitening, we can still obtain the $Q$ least Gaussian independent components of the centralized ICA solution, where $Q$ scales linearly with the required communication load.
In this paper, we introduce MotionLeaf , a novel mmWave base multi-point vibration frequency measurement system that can estimate plant stress by analyzing the surface vibrations of multiple leaves. MotionLeaf features a novel signal processing pipeline that accurately estimates fine-grained damped vibration frequencies based on noisy micro-displacement measurements from a mmWave radar. Specifically we explore the Interquartile Mean (IQM) of coherent phase differences from neighboring Frequency-Modulated Continuous Wave (FMCW) radar chirps to calculate micro-displacements. Furthermore, we use the measurements from multiple received antennas in the radar to estimate the vibration signals of different leaves via a Blind Source Separation (BSS) method. Experimental results demonstrate that MotionLeaf can accurately measure the frequency of multiple leaves in a plant with average error of 0.0176 Hz, which is less than 50% of that (0.0416 Hz) of the state-of-the-art approach (mmVib). Additionally, the estimated natural vibration frequencies from MotionLeaf are shown to be an excellent feature to detect the water stress in the plant during 7-day drought experiments.
Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate complex structures from simpler elements. In this paper, we focus on the problem of compositional representation learning for music data, specifically targeting the fully-unsupervised setting. We propose a simple and extensible framework that leverages an explicit compositional inductive bias, defined by a flexible auto-encoding objective that can leverage any of the current state-of-art generative models. We demonstrate that our framework, used with diffusion models, naturally addresses the task of unsupervised audio source separation, showing that our model is able to perform high-quality separation. Our findings reveal that our proposal achieves comparable or superior performance with respect to other blind source separation methods and, furthermore, it even surpasses current state-of-art supervised baselines on signal-to-interference ratio metrics. Additionally, by learning an a-posteriori masking diffusion model in the space of composable representations, we achieve a system capable of seamlessly performing unsupervised source separation, unconditional generation, and variation generation. Finally, as our proposal works in the latent space of pre-trained neural audio codecs, it also provides a lower computational cost with respect to other neural baselines.
Multispectral unmixing (MU) is critical due to the inevitable mixed pixel phenomenon caused by the limited spatial resolution of typical multispectral images in remote sensing. However, MU mathematically corresponds to the underdetermined blind source separation problem, thus highly challenging, preventing researchers from tackling it. Previous MU works all ignore the underdetermined issue, and merely consider scenarios with more bands than sources. This work attempts to resolve the underdetermined issue by further conducting the light-splitting task using a network-inspired virtual prism, and as this task is challenging, we achieve so by incorporating the very advanced quantum feature extraction techniques. We emphasize that the prism is virtual (allowing us to fix the spectral response as a simple deterministic matrix), so the virtual hyperspectral image (HSI) it generates has no need to correspond to some real hyperspectral sensor; in other words, it is good enough as long as the virtual HSI satisfies some fundamental properties of light splitting (e.g., non-negativity and continuity). With the above virtual quantum prism, we know that the virtual HSI is expected to possess some desired simplex structure. This allows us to adopt the convex geometry to unmix the spectra, followed by downsampling the pure spectra back to the multispectral domain, thereby achieving MU. Experimental evidence shows great potential of our MU algorithm, termed as prism-inspired multispectral endmember extraction (PRIME).
Topic models are useful tools for discovering latent semantic structures in large textual corpora. Recent efforts have been oriented at incorporating contextual representations in topic modeling and have been shown to outperform classical topic models. These approaches are typically slow, volatile, and require heavy preprocessing for optimal results. We present Semantic Signal Separation ($S^3$), a theory-driven topic modeling approach in neural embedding spaces. $S^3$ conceptualizes topics as independent axes of semantic space and uncovers these by decomposing contextualized document embeddings using Independent Component Analysis. Our approach provides diverse and highly coherent topics, requires no preprocessing, and is demonstrated to be the fastest contextual topic model, being, on average, 4.5x faster than the runner-up BERTopic. We offer an implementation of $S^3$, and all contextual baselines, in the Turftopic Python package.
This paper presents a neural method for distant speech recognition (DSR) that jointly separates and diarizes speech mixtures without supervision by isolated signals. A standard separation method for multi-talker DSR is a statistical multichannel method called guided source separation (GSS). While GSS does not require signal-level supervision, it relies on speaker diarization results to handle unknown numbers of active speakers. To overcome this limitation, we introduce and train a neural inference model in a weakly-supervised manner, employing the objective function of a statistical separation method. This training requires only multichannel mixtures and their temporal annotations of speaker activities. In contrast to GSS, the trained model can jointly separate and diarize speech mixtures without any auxiliary information. The experiments with the AMI corpus show that our method outperforms GSS with oracle diarization results regarding word error rates. The code is available online.
Independent Component Analysis (ICA) was introduced in the 1980's as a model for Blind Source Separation (BSS), which refers to the process of recovering the sources underlying a mixture of signals, with little knowledge about the source signals or the mixing process. While there are many sophisticated algorithms for estimation, different methods have different shortcomings. In this paper, we develop a nonparametric score to adaptively pick the right algorithm for ICA with arbitrary Gaussian noise. The novelty of this score stems from the fact that it just assumes a finite second moment of the data and uses the characteristic function to evaluate the quality of the estimated mixing matrix without any knowledge of the parameters of the noise distribution. In addition, we propose some new contrast functions and algorithms that enjoy the same fast computability as existing algorithms like FASTICA and JADE but work in domains where the former may fail. While these also may have weaknesses, our proposed diagnostic, as shown by our simulations, can remedy them. Finally, we propose a theoretical framework to analyze the local and global convergence properties of our algorithms.
This study introduces an online target sound extraction (TSE) process using the similarity-and-independence-aware beamformer (SIBF) derived from an iterative batch algorithm. The study aimed to reduce latency while maintaining extraction accuracy. The SIBF, which is a linear method, provides more accurate estimates of the target than an approximate magnitude spectrogram reference. The transition to an online algorithm reduces latency but presents challenges. First, contrary to the conventional assumption, deriving the online algorithm may degrade accuracy as compared to the batch algorithm using a sliding window. Second, conventional post-processing methods intended for scaling the estimated target may widen the accuracy gap between the two algorithms. This study adopts an approach that addresses these challenges and minimizes the accuracy gap during post-processing. It proposes a novel scaling method based on the single-channel Wiener filter (SWF-based scaling). To further improve accuracy, the study introduces a modified version of the time-frequency-varying variance generalized Gaussian distribution as a source model to represent the joint probability between the target and reference. Experimental results using the CHiME-3 dataset demonstrate several key findings: 1) SWF-based scaling effectively eliminates the gap between the two algorithms and improves accuracy. 2) The new source model achieves optimal accuracy, corresponding to the Laplacian model. 3) Our online SIBF outperforms conventional linear TSE methods, including independent vector extraction and minimum mean square error beamforming. These findings can contribute to the fields of beamforming and blind source separation.
While the semi-blind source separation-based acoustic echo cancellation (SBSS-AEC) has received much research attention due to its promising performance during double-talk compared to the traditional adaptive algorithms, it suffers from system latency and nonlinear distortions. To circumvent these drawbacks, the recently developed ideas on convolutive transfer function (CTF) approximation and nonlinear expansion have been used in the iterative projection (IP)-based semi-blind source separation (SBSS) algorithm. However, because of the introduction of CTF approximation and nonlinear expansion, this algorithm becomes computationally very expensive, which makes it difficult to implement in embedded systems. Thus, we attempt in this paper to improve this IP-based algorithm, thereby developing an element-wise iterative source steering (EISS) algorithm. In comparison with the IP-based SBSS algorithm, the proposed algorithm is computationally much more efficient, especially when the nonlinear expansion order is high and the length of the CTF filter is long. Meanwhile, its AEC performance is as good as that of IP-based SBSS.