Deep learning-based speech enhancement (SE) methods often face significant computational challenges when needing to meet low-latency requirements because of the increased number of frames to be processed. This paper introduces the SlowFast framework which aims to reduce computation costs specifically when low-latency enhancement is needed. The framework consists of a slow branch that analyzes the acoustic environment at a low frame rate, and a fast branch that performs SE in the time domain at the needed higher frame rate to match the required latency. Specifically, the fast branch employs a state space model where its state transition process is dynamically modulated by the slow branch. Experiments on a SE task with a 2 ms algorithmic latency requirement using the Voice Bank + Demand dataset show that our approach reduces computation cost by 70% compared to a baseline single-branch network with equivalent parameters, without compromising enhancement performance. Furthermore, by leveraging the SlowFast framework, we implemented a network that achieves an algorithmic latency of just 62.5 {\mu}s (one sample point at 16 kHz sample rate) with a computation cost of 100 M MACs/s, while scoring a PESQ-NB of 3.12 and SISNR of 16.62.

Adding visual cues to audio-based speech separation can improve separation performance. This paper introduces AV-CrossNet, an audiovisual (AV) system for speech enhancement, target speaker extraction, and multi-talker speaker separation. AV-CrossNet is extended from the CrossNet architecture, which is a recently proposed network that performs complex spectral mapping for speech separation by leveraging global attention and positional encoding. To effectively utilize visual cues, the proposed system incorporates pre-extracted visual embeddings and employs a visual encoder comprising temporal convolutional layers. Audio and visual features are fused in an early fusion layer before feeding to AV-CrossNet blocks. We evaluate AV-CrossNet on multiple datasets, including LRS, VoxCeleb, and COG-MHEAR challenge. Evaluation results demonstrate that AV-CrossNet advances the state-of-the-art performance in all audiovisual tasks, even on untrained and mismatched datasets.

Self-supervised learned models have been found to be very effective for certain speech tasks such as automatic speech recognition, speaker identification, keyword spotting and others. While the features are undeniably useful in speech recognition and associated tasks, their utility in speech enhancement systems is yet to be firmly established, and perhaps not properly understood. In this paper, we investigate the uses of SSL representations for single-channel speech enhancement in challenging conditions and find that they add very little value for the enhancement task. Our constraints are designed around on-device real-time speech enhancement -- model is causal, the compute footprint is small. Additionally, we focus on low SNR conditions where such models struggle to provide good enhancement. In order to systematically examine how SSL representations impact performance of such enhancement models, we propose a variety of techniques to utilize these embeddings which include different forms of knowledge-distillation and pre-training.

Audio-visual speech enhancement aims to extract clean speech from a noisy environment by leveraging not only the audio itself but also the target speaker's lip movements. This approach has been shown to yield improvements over audio-only speech enhancement, particularly for the removal of interfering speech. Despite recent advances in speech synthesis, most audio-visual approaches continue to use spectral mapping/masking to reproduce the clean audio, often resulting in visual backbones added to existing speech enhancement architectures. In this work, we propose LA-VocE, a new two-stage approach that predicts mel-spectrograms from noisy audio-visual speech via a transformer-based architecture, and then converts them into waveform audio using a neural vocoder (HiFi-GAN). We train and evaluate our framework on thousands of speakers and 11+ different languages, and study our model's ability to adapt to different levels of background noise and speech interference. Our experiments show that LA-VocE outperforms existing methods according to multiple metrics, particularly under very noisy scenarios.

Most speech enhancement (SE) models learn a point estimate and do not make use of uncertainty estimation in the learning process. In this paper, we show that modeling heteroscedastic uncertainty by minimizing a multivariate Gaussian negative log-likelihood (NLL) improves SE performance at no extra cost. During training, our approach augments a model learning complex spectral mapping with a temporary submodel to predict the covariance of the enhancement error at each time-frequency bin. Due to unrestricted heteroscedastic uncertainty, the covariance introduces an undersampling effect, detrimental to SE performance. To mitigate undersampling, our approach inflates the uncertainty lower bound and weights each loss component with their uncertainty, effectively compensating severely undersampled components with more penalties. Our multivariate setting reveals common covariance assumptions such as scalar and diagonal matrices. By weakening these assumptions, we show that the NLL achieves superior performance compared to popular loss functions including the mean squared error (MSE), mean absolute error (MAE), and scale-invariant signal-to-distortion ratio (SI-SDR).

Despite multiple efforts made towards adopting complex-valued deep neural networks (DNNs), it remains an open question whether complex-valued DNNs are generally more effective than real-valued DNNs for monaural speech enhancement. This work is devoted to presenting a critical assessment by systematically examining complex-valued DNNs against their real-valued counterparts. Specifically, we investigate complex-valued DNN atomic units, including linear layers, convolutional layers, long short-term memory (LSTM), and gated linear units. By comparing complex- and real-valued versions of fundamental building blocks in the recently developed gated convolutional recurrent network (GCRN), we show how different mechanisms for basic blocks affect the performance. We also find that the use of complex-valued operations hinders the model capacity when the model size is small. In addition, we examine two recent complex-valued DNNs, i.e. deep complex convolutional recurrent network (DCCRN) and deep complex U-Net (DCUNET). Evaluation results show that both DNNs produce identical performance to their real-valued counterparts while requiring much more computation. Based on these comprehensive comparisons, we conclude that complex-valued DNNs do not provide a performance gain over their real-valued counterparts for monaural speech enhancement, and thus are less desirable due to their higher computational costs.

We propose RemixIT, a simple and novel self-supervised training method for speech enhancement. The proposed method is based on a continuously self-training scheme that overcomes limitations from previous studies including assumptions for the in-domain noise distribution and having access to clean target signals. Specifically, a separation teacher model is pre-trained on an out-of-domain dataset and is used to infer estimated target signals for a batch of in-domain mixtures. Next, we bootstrap the mixing process by generating artificial mixtures using permuted estimated clean and noise signals. Finally, the student model is trained using the permuted estimated sources as targets while we periodically update teacher's weights using the latest student model. Our experiments show that RemixIT outperforms several previous state-of-the-art self-supervised methods under multiple speech enhancement tasks. Additionally, RemixIT provides a seamless alternative for semi-supervised and unsupervised domain adaptation for speech enhancement tasks, while being general enough to be applied to any separation task and paired with any separation model.

Deep neural networks have recently shown great success in the task of blind source separation, both under monaural and binaural settings. Although these methods were shown to produce high-quality separations, they were mainly applied under offline settings, in which the model has access to the full input signal while separating the signal. In this study, we convert a non-causal state-of-the-art separation model into a causal and real-time model and evaluate its performance under both online and offline settings. We compare the performance of the proposed model to several baseline methods under anechoic, noisy, and noisy-reverberant recording conditions while exploring both monaural and binaural inputs and outputs. Our findings shed light on the relative difference between causal and non-causal models when performing separation. Our stateful implementation for online separation leads to a minor drop in performance compared to the offline model; 0.8dB for monaural inputs and 0.3dB for binaural inputs while reaching a real-time factor of 0.65. Samples can be found under the following link: https://kwanum.github.io/sagrnnc-stream-results/.