FNSE-SBGAN: Far-field Speech Enhancement with Schrodinger Bridge and Generative Adversarial Networks

The current dominant approach for neural speech enhancement relies on purely-supervised deep learning using simulated pairs of far-field noisy-reverberant speech (mixtures) and clean speech. However, these trained models often exhibit limited generalizability to real-recorded mixtures. To address this issue, this study investigates training enhancement models directly on real mixtures. Specifically, we revisit the single-channel far-field to near-field speech enhancement (FNSE) task, focusing on real-world data characterized by low signal-to-noise ratio (SNR), high reverberation, and mid-to-high frequency attenuation. We propose FNSE-SBGAN, a novel framework that integrates a Schrodinger Bridge (SB)-based diffusion model with generative adversarial networks (GANs). Our approach achieves state-of-the-art performance across various metrics and subjective evaluations, significantly reducing the character error rate (CER) by up to 14.58% compared to far-field signals. Experimental results demonstrate that FNSE-SBGAN preserves superior subjective quality and establishes a new benchmark for real-world far-field speech enhancement. Additionally, we introduce a novel evaluation framework leveraging matrix rank analysis in the time-frequency domain, providing systematic insights into model performance and revealing the strengths and weaknesses of different generative methods.

NaturalL2S: End-to-End High-quality Multispeaker Lip-to-Speech Synthesis with Differential Digital Signal Processing

Recent advancements in visual speech recognition (VSR) have promoted progress in lip-to-speech synthesis, where pre-trained VSR models enhance the intelligibility of synthesized speech by providing valuable semantic information. The success achieved by cascade frameworks, which combine pseudo-VSR with pseudo-text-to-speech (TTS) or implicitly utilize the transcribed text, highlights the benefits of leveraging VSR models. However, these methods typically rely on mel-spectrograms as an intermediate representation, which may introduce a key bottleneck: the domain gap between synthetic mel-spectrograms, generated from inherently error-prone lip-to-speech mappings, and real mel-spectrograms used to train vocoders. This mismatch inevitably degrades synthesis quality. To bridge this gap, we propose Natural Lip-to-Speech (NaturalL2S), an end-to-end framework integrating acoustic inductive biases with differentiable speech generation components. Specifically, we introduce a fundamental frequency (F0) predictor to capture prosodic variations in synthesized speech. The predicted F0 then drives a Differentiable Digital Signal Processing (DDSP) synthesizer to generate a coarse signal which serves as prior information for subsequent speech synthesis. Additionally, instead of relying on a reference speaker embedding as an auxiliary input, our approach achieves satisfactory performance on speaker similarity without explicitly modelling speaker characteristics. Both objective and subjective evaluation results demonstrate that NaturalL2S can effectively enhance the quality of the synthesized speech when compared to state-of-the-art methods. Our demonstration page is accessible at https://yifan-liang.github.io/NaturalL2S/.

BSDB-Net: Band-Split Dual-Branch Network with Selective State Spaces Mechanism for Monaural Speech Enhancement

Although the complex spectrum-based speech enhancement(SE) methods have achieved significant performance, coupling amplitude and phase can lead to a compensation effect, where amplitude information is sacrificed to compensate for the phase that is harmful to SE. In addition, to further improve the performance of SE, many modules are stacked onto SE, resulting in increased model complexity that limits the application of SE. To address these problems, we proposed a dual-path network based on compressed frequency using Mamba. First, we extract amplitude and phase information through parallel dual branches. This approach leverages structured complex spectra to implicitly capture phase information and solves the compensation effect by decoupling amplitude and phase, and the network incorporates an interaction module to suppress unnecessary parts and recover missing components from the other branch. Second, to reduce network complexity, the network introduces a band-split strategy to compress the frequency dimension. To further reduce complexity while maintaining good performance, we designed a Mamba-based module that models the time and frequency dimensions under linear complexity. Finally, compared to baselines, our model achieves an average 8.3 times reduction in computational complexity while maintaining superior performance. Furthermore, it achieves a 25 times reduction in complexity compared to transformer-based models.

Array2BR: An End-to-End Noise-immune Binaural Audio Synthesis from Microphone-array Signals

Telepresence technology aims to provide an immersive virtual presence for remote conference applications, and it is extremely important to synthesize high-quality binaural audio signals for this aim. Because the ambient noise is often inevitable in practical application scenarios, it is highly desired that binaural audio signals without noise can be obtained from microphone-array signals directly. For this purpose, this paper proposes a new end-to-end noise-immune binaural audio synthesis framework from microphone-array signals, abbreviated as Array2BR, and experimental results show that binaural cues can be correctly mapped and noise can be well suppressed simultaneously using the proposed framework. Compared with existing methods, the proposed method achieved better performance in terms of both objective and subjective metric scores.

SMRU: Split-and-Merge Recurrent-based UNet for Acoustic Echo Cancellation and Noise Suppression

The proliferation of deep neural networks has spawned the rapid development of acoustic echo cancellation and noise suppression, and plenty of prior arts have been proposed, which yield promising performance. Nevertheless, they rarely consider the deployment generality in different processing scenarios, such as edge devices, and cloud processing. To this end, this paper proposes a general model, termed SMRU, to cover different application scenarios. The novelty lies in two-fold. First, a multi-scale band split layer and band merge layer are proposed to effectively fuse local frequency bands for lower complexity modeling. Besides, by simulating the multi-resolution feature modeling characteristic of the classical UNet structure, a novel recurrent-dominated UNet is devised. It consists of multiple variable frame rate blocks, each of which involves the causal time down-/up-sampling layer with varying compression ratios and the dual-path structure for inter- and intra-band modeling. The model is configured from 50 M/s to 6.8 G/s in terms of MACs, and the experimental results show that the proposed approach yields competitive or even better performance over existing baselines, and has the full potential to adapt to more general scenarios with varying complexity requirements.

Gesper: A Restoration-Enhancement Framework for General Speech Reconstruction

This paper describes a real-time General Speech Reconstruction (Gesper) system submitted to the ICASSP 2023 Speech Signal Improvement (SSI) Challenge. This novel proposed system is a two-stage architecture, in which the speech restoration is performed, and then cascaded by speech enhancement. We propose a complex spectral mapping-based generative adversarial network (CSM-GAN) as the speech restoration module for the first time. For noise suppression and dereverberation, the enhancement module is performed with fullband-wideband parallel processing. On the blind test set of ICASSP 2023 SSI Challenge, the proposed Gesper system, which satisfies the real-time condition, achieves 3.27 P.804 overall mean opinion score (MOS) and 3.35 P.835 overall MOS, ranked 1st in both track 1 and track 2.

A General Deep Learning Speech Enhancement Framework Motivated by Taylor's Theorem

While deep neural networks greatly facilitate the proliferation of the speech enhancement field, most of the existing methods are developed following either heuristic or blind optimization criteria, which severely hampers interpretability and transparency. Inspired by Taylor's theorem, we propose a general unfolding framework for both single- and multi-channel speech enhancement tasks. Concretely, we formulate the complex spectrum recovery into the spectral magnitude mapping in the neighboring space of the noisy mixture, in which the sparse prior is introduced for phase modification in advance. Based on that, the mapping function is decomposed into the superimposition of the 0th-order and high-order polynomials in Taylor's series, where the former coarsely removes the interference in the magnitude domain and the latter progressively complements the remaining spectral detail in the complex spectrum domain. In addition, we study the relation between adjacent order term and reveal that each high-order term can be recursively estimated with its lower-order term, and each high-order term is then proposed to evaluate using a surrogate function with trainable weights, so that the whole system can be trained in an end-to-end manner. Extensive experiments are conducted on WSJ0-SI84, DNS-Challenge, Voicebank+Demand, and spatialized Librispeech datasets. Quantitative results show that the proposed approach not only yields competitive performance over existing top-performed approaches, but also enjoys decent internal transparency and flexibility.

TaylorBeamixer: Learning Taylor-Inspired All-Neural Multi-Channel Speech Enhancement from Beam-Space Dictionary Perspective

Despite the promising performance of existing frame-wise all-neural beamformers in the speech enhancement field, it remains unclear what the underlying mechanism exists. In this paper, we revisit the beamforming behavior from the beam-space dictionary perspective and formulate it into the learning and mixing of different beam-space components. Based on that, we propose an all-neural beamformer called TaylorBM to simulate Taylor's series expansion operation in which the 0th-order term serves as a spatial filter to conduct the beam mixing, and several high-order terms are tasked with residual noise cancellation for post-processing. The whole system is devised to work in an end-to-end manner. Experiments are conducted on the spatialized LibriSpeech corpus and results show that the proposed approach outperforms existing advanced baselines in terms of evaluation metrics.

TMGAN-PLC: Audio Packet Loss Concealment using Temporal Memory Generative Adversarial Network

Real-time communications in packet-switched networks have become widely used in daily communication, while they inevitably suffer from network delays and data losses in constrained real-time conditions. To solve these problems, audio packet loss concealment (PLC) algorithms have been developed to mitigate voice transmission failures by reconstructing the lost information. Limited by the transmission latency and device memory, it is still intractable for PLC to accomplish high-quality voice reconstruction using a relatively small packet buffer. In this paper, we propose a temporal memory generative adversarial network for audio PLC, dubbed TMGAN-PLC, which is comprised of a novel nested-UNet generator and the time-domain/frequency-domain discriminators. Specifically, a combination of the nested-UNet and temporal feature-wise linear modulation is elaborately devised in the generator to finely adjust the intra-frame information and establish inter-frame temporal dependencies. To complement the missing speech content caused by longer loss bursts, we employ multi-stage gated vector quantizers to capture the correct content and reconstruct the near-real smooth audio. Extensive experiments on the PLC Challenge dataset demonstrate that the proposed method yields promising performance in terms of speech quality, intelligibility, and PLCMOS.

Taylor, Can You Hear Me Now? A Taylor-Unfolding Framework for Monaural Speech Enhancement

While the deep learning techniques promote the rapid development of the speech enhancement (SE) community, most schemes only pursue the performance in a black-box manner and lack adequate model interpretability. Inspired by Taylor's approximation theory, we propose an interpretable decoupling-style SE framework, which disentangles the complex spectrum recovery into two separate optimization problems \emph{i.e.}, magnitude and complex residual estimation. Specifically, serving as the 0th-order term in Taylor's series, a filter network is delicately devised to suppress the noise component only in the magnitude domain and obtain a coarse spectrum. To refine the phase distribution, we estimate the sparse complex residual, which is defined as the difference between target and coarse spectra, and measures the phase gap. In this study, we formulate the residual component as the combination of various high-order Taylor terms and propose a lightweight trainable module to replace the complicated derivative operator between adjacent terms. Finally, following Taylor's formula, we can reconstruct the target spectrum by the superimposition between 0th-order and high-order terms. Experimental results on two benchmark datasets show that our framework achieves state-of-the-art performance over previous competing baselines in various evaluation metrics. The source code is available at github.com/Andong-Lispeech/TaylorSENet.