PyTorchKR Papers

최신 논문

총 65편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2503.03593

A Comparative Analysis of Generalised Echo and Interference Cancelling and Extended Multichannel Wiener Filtering for Combined Noise Reduction and Acoustic Echo Cancellation

Two algorithms for combined acoustic echo cancellation (AEC) and noise reduction (NR) are analysed, namely the generalised echo and interference canceller (GEIC) and the extended multichannel Wiener filter (MWFext). Previously, these algorithms have been examined for linear echo paths, and assuming access to voice activity detectors (VADs) that separately detect desired speech and echo activity. However, algorithms implementing VADs may introduce detection errors. Therefore, in this paper, the previous analyses are extended by 1) modelling general nonlinear echo paths by means of the generalised Bussgang decomposition, and 2) modelling VAD error effects in each specific algorithm, thereby also allowing to model specific VAD assumptions. It is found and verified with simulations that, generally, the MWFext achieves a higher NR performance, while the GEIC achieves a more robust AEC performance.

arXiv:2501.16367

Neural Kalman Filters for Acoustic Echo Cancellation

Kalman filtering is a powerful approach to adaptive filtering for various problems in signal processing. The frequency-domain adaptive Kalman filter (FDKF), based on the concept of the acoustic state space, provides a unifying solution to the adaptive filter update and the related stepsize control. It was conceived for the problem of acoustic echo cancellation and, as such, is frequently applied in hands-free systems. This article motivates and briefly recapitulates the linear FDKF and investigates how it can be further supported by deep neural networks (DNNs) in various ways, specifically to overcome the challenges and limitations related to the usually required estimation of process and observation noise covariances for the Kalman filter. While the mere FDKF comes with very low computational complexity, its neural Kalman filter variants may deliver faster (re)convergence, better echo cancellation, and even exceed the FDKF in its excellent double-talk near-end speech preservation both under linear and nonlinear loudspeaker conditions. To provide a synopsis of the state of the art, this article contributes a comparison of a range of DNN-based extensions of FDKF in the same training framework and using the same data.

arXiv:2412.04267

Integrated Minimum Mean Squared Error Algorithms for Combined Acoustic Echo Cancellation and Noise Reduction

In many speech recording applications, noise and acoustic echo corrupt the desired speech. Consequently, combined noise reduction (NR) and acoustic echo cancellation (AEC) is required. Generally, a cascade approach is followed, i.e., the AEC and NR are designed in isolation by selecting a separate signal model, formulating a separate cost function, and using a separate solution strategy. The AEC and NR are then cascaded one after the other, not accounting for their interaction. In this paper, however, an integrated approach is proposed to consider this interaction in a general multi-microphone/multi-loudspeaker setup. Therefore, a single signal model of either the microphone signal vector or the extended signal vector, obtained by stacking microphone and loudspeaker signals, is selected, a single mean squared error cost function is formulated, and a common solution strategy is used. Using this microphone signal model, a multi channel Wiener filter (MWF) is derived. Using the extended signal model, an extended MWF (MWFext) is derived, and several equivalent expressions are found, which nevertheless are interpretable as cascade algorithms. Specifically, the MWFext is shown to be equivalent to algorithms where the AEC precedes the NR (AEC NR), the NR precedes the AEC (NR-AEC), and the extended NR (NRext) precedes the AEC and post-filter (PF) (NRext-AECPF). Under rank-deficiency conditions the MWFext is non-unique, such that this equivalence amounts to the expressions being specific, not necessarily minimum-norm solutions for this MWFext. The practical performances nonetheless differ due to non-stationarities and imperfect correlation matrix estimation, resulting in the AEC-NR and NRext-AEC-PF attaining best overall performance.

arXiv:2409.05281

Exact equality of the MSEs for two types of nonlinear adaptive systems: Saturation and dead-zone types

Adaptive signal processing systems, commonly utilized in applications such as active noise control and acoustic echo cancellation, often encompass nonlinearities due to hardware components such as loudspeakers, microphones, and amplifiers. Examining the impact of these nonlinearities on the overall performance of adaptive systems is critically important. In this study, we employ a statistical-mechanical method to investigate the behaviors of adaptive systems, each containing an unknown system with a nonlinearity in its output. We specifically address two types of nonlinearity: saturation and dead-zone types. We analyze both the dynamic and steady-state behaviors of these systems under the effect of such nonlinearities. Our findings indicate that when the saturation value is equal to the dead-zone width, the mean square errors (MSEs) in steady states are identical for both nonlinearity types. Furthermore, we derive a self-consistent equation to obtain the saturation value and dead-zone width that maximize the steady-state MSE. We theoretically clarify that these values depend on neither the step size nor the variance of background noise.

arXiv:2406.08974

Cascaded noise reduction and acoustic echo cancellation based on an extended noise reduction

In many speech recording applications, the recorded desired speech is corrupted by both noise and acoustic echo, such that combined noise reduction (NR) and acoustic echo cancellation (AEC) is called for. A common cascaded design corresponds to NR filters preceding AEC filters. These NR filters aim at reducing the near-end room noise (and possibly partially the echo) and operate on the microphones only, consequently requiring the AEC filters to model both the echo paths and the NR filters. In this paper, however, we propose a design with extended NR (NRext) filters preceding AEC filters under the assumption of the echo paths being additive maps, thus preserving the addition operation. Here, the NRext filters aim at reducing both the near-end room noise and the far-end room noise component in the echo, and operate on both the microphones and loudspeakers. We show that the succeeding AEC filters remarkably become independent of the NRext filters, such that the AEC filters are only required to model the echo paths, improving the AEC performance. Further, the degrees of freedom in the NRext filters scale with the number of loudspeakers, which is not the case for the NR filters, resulting in an improved NR performance.

arXiv:2401.04283

FADI-AEC: Fast Score Based Diffusion Model Guided by Far-end Signal for Acoustic Echo Cancellation

Despite the potential of diffusion models in speech enhancement, their deployment in Acoustic Echo Cancellation (AEC) has been restricted. In this paper, we propose DI-AEC, pioneering a diffusion-based stochastic regeneration approach dedicated to AEC. Further, we propose FADI-AEC, fast score-based diffusion AEC framework to save computational demands, making it favorable for edge devices. It stands out by running the score model once per frame, achieving a significant surge in processing efficiency. Apart from that, we introduce a novel noise generation technique where far-end signals are utilized, incorporating both far-end and near-end signals to refine the score model's accuracy. We test our proposed method on the ICASSP2023 Microsoft deep echo cancellation challenge evaluation dataset, where our method outperforms some of the end-to-end methods and other diffusion based echo cancellation methods.

arXiv:2312.08610

A computationally efficient semi-blind source separation based approach for nonlinear echo cancellation based on an element-wise iterative source steering

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.

arXiv:2310.07032

Neural Harmonium: An Interpretable Deep Structure for Nonlinear Dynamic System Identification with Application to Audio Processing

Improving the interpretability of deep neural networks has recently gained increased attention, especially when the power of deep learning is leveraged to solve problems in physics. Interpretability helps us understand a model's ability to generalize and reveal its limitations. In this paper, we introduce a causal interpretable deep structure for modeling dynamic systems. Our proposed model makes use of the harmonic analysis by modeling the system in a time-frequency domain while maintaining high temporal and spectral resolution. Moreover, the model is built in an order recursive manner which allows for fast, robust, and exact second order optimization without the need for an explicit Hessian calculation. To circumvent the resulting high dimensionality of the building blocks of our system, a neural network is designed to identify the frequency interdependencies. The proposed model is illustrated and validated on nonlinear system identification problems as required for audio signal processing tasks. Crowd-sourced experimentation contrasting the performance of the proposed approach to other state-of-the-art solutions on an acoustic echo cancellation scenario confirms the effectiveness of our method for real-life applications.

arXiv:2310.04715

An Exploration of Task-decoupling on Two-stage Neural Post Filter for Real-time Personalized Acoustic Echo Cancellation

Deep learning based techniques have been popularly adopted in acoustic echo cancellation (AEC). Utilization of speaker representation has extended the frontier of AEC, thus attracting many researchers' interest in personalized acoustic echo cancellation (PAEC). Meanwhile, task-decoupling strategies are widely adopted in speech enhancement. To further explore the task-decoupling approach, we propose to use a two-stage task-decoupling post-filter (TDPF) in PAEC. Furthermore, a multi-scale local-global speaker representation is applied to improve speaker extraction in PAEC. Experimental results indicate that the task-decoupling model can yield better performance than a single joint network. The optimal approach is to decouple the echo cancellation from noise and interference speech suppression. Based on the task-decoupling sequence, optimal training strategies for the two-stage model are explored afterwards.

arXiv:2309.16048

Advancing Acoustic Howling Suppression through Recursive Training of Neural Networks

In this paper, we introduce a novel training framework designed to comprehensively address the acoustic howling issue by examining its fundamental formation process. This framework integrates a neural network (NN) module into the closed-loop system during training with signals generated recursively on the fly to closely mimic the streaming process of acoustic howling suppression (AHS). The proposed recursive training strategy bridges the gap between training and real-world inference scenarios, marking a departure from previous NN-based methods that typically approach AHS as either noise suppression or acoustic echo cancellation. Within this framework, we explore two methodologies: one exclusively relying on NN and the other combining NN with the traditional Kalman filter. Additionally, we propose strategies, including howling detection and initialization using pre-trained offline models, to bolster trainability and expedite the training process. Experimental results validate that this framework offers a substantial improvement over previous methodologies for acoustic howling suppression.

arXiv:2309.12553공식 코드 · Papers with Code

ICASSP 2023 Acoustic Echo Cancellation Challenge

The ICASSP 2023 Acoustic Echo Cancellation Challenge is intended to stimulate research in acoustic echo cancellation (AEC), which is an important area of speech enhancement and is still a top issue in audio communication. This is the fourth AEC challenge and it is enhanced by adding a second track for personalized acoustic echo cancellation, reducing the algorithmic + buffering latency to 20ms, as well as including a full-band version of AECMOS. We open source two large datasets to train AEC models under both single talk and double talk scenarios. These datasets consist of recordings from more than 10,000 real audio devices and human speakers in real environments, as well as a synthetic dataset. We open source an online subjective test framework and provide an objective metric for researchers to quickly test their results. The winners of this challenge were selected based on the average mean opinion score (MOS) achieved across all scenarios and the word accuracy (WAcc) rate.

arXiv:2309.06096

iPhonMatchNet: Zero-Shot User-Defined Keyword Spotting Using Implicit Acoustic Echo Cancellation

In response to the increasing interest in human--machine communication across various domains, this paper introduces a novel approach called iPhonMatchNet, which addresses the challenge of barge-in scenarios, wherein user speech overlaps with device playback audio, thereby creating a self-referencing problem. The proposed model leverages implicit acoustic echo cancellation (iAEC) techniques to increase the efficiency of user-defined keyword spotting models, achieving a remarkable 95% reduction in mean absolute error with a minimal increase in model size (0.13%) compared to the baseline model, PhonMatchNet. We also present an efficient model structure and demonstrate its capability to learn iAEC functionality without requiring a clean signal. The findings of our study indicate that the proposed model achieves competitive performance in real-world deployment conditions of smart devices.

arXiv:2309.04670

Generalized Minimum Error with Fiducial Points Criterion for Robust Learning

The conventional Minimum Error Entropy criterion (MEE) has its limitations, showing reduced sensitivity to error mean values and uncertainty regarding error probability density function locations. To overcome this, a MEE with fiducial points criterion (MEEF), was presented. However, the efficacy of the MEEF is not consistent due to its reliance on a fixed Gaussian kernel. In this paper, a generalized minimum error with fiducial points criterion (GMEEF) is presented by adopting the Generalized Gaussian Density (GGD) function as kernel. The GGD extends the Gaussian distribution by introducing a shape parameter that provides more control over the tail behavior and peakedness. In addition, due to the high computational complexity of GMEEF criterion, the quantized idea is introduced to notably lower the computational load of the GMEEF-type algorithm. Finally, the proposed criterions are introduced to the domains of adaptive filter, kernel recursive algorithm, and multilayer perceptron. Several numerical simulations, which contain system identification, acoustic echo cancellation, times series prediction, and supervised classification, indicate that the novel algorithms' performance performs excellently.

arXiv:2307.13888

Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation

Acoustic echo cancellation (AEC) aims to remove interference signals while leaving near-end speech least distorted. As the indistinguishable patterns between near-end speech and interference signals, near-end speech can't be separated completely, causing speech distortion and interference signals residual. We observe that besides target positive information, e.g., ground-truth speech and features, the target negative information, such as interference signals and features, helps make pattern of target speech and interference signals more discriminative. Therefore, we present a novel AEC model encoder-decoder architecture with the guidance of negative information termed as CMNet. A collaboration module (CM) is designed to establish the correlation between the target positive and negative information in a learnable manner via three blocks: target positive, target negative, and interactive block. Experimental results demonstrate our CMNet achieves superior performance than recent methods.

arXiv:2306.03177

DeepVQE: Real Time Deep Voice Quality Enhancement for Joint Acoustic Echo Cancellation, Noise Suppression and Dereverberation

Acoustic echo cancellation (AEC), noise suppression (NS) and dereverberation (DR) are an integral part of modern full-duplex communication systems. As the demand for teleconferencing systems increases, addressing these tasks is required for an effective and efficient online meeting experience. Most prior research proposes solutions for these tasks separately, combining them with digital signal processing (DSP) based components, resulting in complex pipelines that are often impractical to deploy in real-world applications. This paper proposes a real-time cross-attention deep model, named DeepVQE, based on residual convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to simultaneously address AEC, NS, and DR. We conduct several ablation studies to analyze the contributions of different components of our model to the overall performance. DeepVQE achieves state-of-the-art performance on non-personalized tracks from the ICASSP 2023 Acoustic Echo Cancellation Challenge and ICASSP 2023 Deep Noise Suppression Challenge test sets, showing that a single model can handle multiple tasks with excellent performance. Moreover, the model runs in real-time and has been successfully tested for the Microsoft Teams platform.

arXiv:2306.02450공식 코드 · Papers with Code

End-To-End Deep Learning-based Adaptation Control for Linear Acoustic Echo Cancellation

The attenuation of acoustic loudspeaker echoes remains to be one of the open challenges to achieve pleasant full-duplex hands free speech communication. In many modern signal enhancement interfaces, this problem is addressed by a linear acoustic echo canceler which subtracts a loudspeaker echo estimate from the recorded microphone signal. To obtain precise echo estimates, the parameters of the echo canceler, i.e., the filter coefficients, need to be estimated quickly and precisely from the observed loudspeaker and microphone signals. For this a sophisticated adaptation control is required to deal with high-power double-talk and rapidly track time-varying acoustic environments which are often faced with portable devices. In this paper, we address this problem by end-to-end deep learning. In particular, we suggest to infer the step-size for a least mean squares frequency-domain adaptive filter update by a Deep Neural Network (DNN). Two different step-size inference approaches are investigated. On the one hand broadband approaches, which use a single DNN to jointly infer step-sizes for all frequency bands, and on the other hand narrowband methods, which exploit individual DNNs per frequency band. The discussion of benefits and disadvantages of both approaches leads to a novel hybrid approach which shows improved echo cancellation while requiring only small DNN architectures. Furthermore, we investigate the effect of different loss functions, signal feature vectors, and DNN output layer architectures on the echo cancellation performance from which we obtain valuable insights into the general design and functionality of DNN-based adaptation control algorithms.

arXiv:2303.06828

Two-step Band-split Neural Network Approach for Full-band Residual Echo Suppression

This paper describes a Two-step Band-split Neural Network (TBNN) approach for full-band acoustic echo cancellation. Specifically, after linear filtering, we split the full-band signal into wide-band (16KHz) and high-band (16-48KHz) for residual echo removal with lower modeling difficulty. The wide-band signal is processed by an updated gated convolutional recurrent network (GCRN) with U$^2$ encoder while the high-band signal is processed by a high-band post-filter net with lower complexity. Our approach submitted to ICASSP 2023 AEC Challenge has achieved an overall mean opinion score (MOS) of 4.344 and a word accuracy (WAcc) ratio of 0.795, leading to the 2$^{nd}$ (tied) in the ranking of the non-personalized track.

arXiv:2303.00692

Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition

To achieve robust far-field automatic speech recognition (ASR), existing techniques typically employ an acoustic front end (AFE) cascaded with a neural transducer (NT) ASR model. The AFE output, however, could be unreliable, as the beamforming output in AFE is steered to a wrong direction. A promising way to address this issue is to exploit the microphone signals before the beamforming stage and after the acoustic echo cancellation (post-AEC) in AFE. We argue that both, post-AEC and AFE outputs, are complementary and it is possible to leverage the redundancy between these signals to compensate for potential AFE processing errors. We present two fusion networks to explore this redundancy and aggregate these multi-channel (MC) signals: (1) Frequency-LSTM based, and (2) Convolutional Neural Network based fusion networks. We augment the MC fusion networks to a conformer transducer model and train it in an end-to-end fashion. Our experimental results on commercial virtual assistant tasks demonstrate that using the AFE output and two post-AEC signals with fusion networks offers up to 25.9% word error rate (WER) relative improvement over the model using the AFE output only, at the cost of <= 2% parameter increase.

arXiv:2302.13063

Time-Variance Aware Real-Time Speech Enhancement

Time-variant factors often occur in real-world full-duplex communication applications. Some of them are caused by the complex environment such as non-stationary environmental noises and varying acoustic path while some are caused by the communication system such as the dynamic delay between the far-end and near-end signals. Current end-to-end deep neural network (DNN) based methods usually model the time-variant components implicitly and can hardly handle the unpredictable time-variance in real-time speech enhancement. To explicitly capture the time-variant components, we propose a dynamic kernel generation (DKG) module that can be introduced as a learnable plug-in to a DNN-based end-to-end pipeline. Specifically, the DKG module generates a convolutional kernel regarding to each input audio frame, so that the DNN model is able to dynamically adjust its weights according to the input signal during inference. Experimental results verify that DKG module improves the performance of the model under time-variant scenarios, in the joint acoustic echo cancellation (AEC) and deep noise suppression (DNS) tasks.

arXiv:2302.10377

Real-time speech enhancement with dynamic attention span

For real-time speech enhancement (SE) including noise suppression, dereverberation and acoustic echo cancellation, the time-variance of the audio signals becomes a severe challenge. The causality and memory usage limit that only the historical information can be used for the system to capture the time-variant characteristics. We propose to adaptively change the receptive field according to the input signal in deep neural network based SE model. Specifically, in an encoder-decoder framework, a dynamic attention span mechanism is introduced to all the attention modules for controlling the size of historical content used for processing the current frame. Experimental results verify that this dynamic mechanism can better track time-variant factors and capture speech-related characteristics, benefiting to both interference removing and speech quality retaining.