arXiv subjects

Chengshi Zheng

Publications and source records attributed to Chengshi Zheng.

At least 19 recordsLinked to original sources

arXiv2026

Gaussian-trigonometric functional link artificial neural network: design and analysis

This paper proposes a Gaussian function-based trigonometric functional link artificial neural network (GTFLN) filter for linear-in-the-parameters nonlinear filtering. Compared with the adaptive exponential TFLN (AETFLN) filter, the GTFLN filter provides smooth and localized basis functions with reduced computational complexity, where modeling advantages are theoretically established through the smoothness, reproducing kernel Hilbert space, approximation error, and operator theory properties. To maximize the modeling performance, an optimized scaling parameter for the GTFLN filter is derived, yielding the optimized GTFLN (OGTFLN) filter. Least mean square (LMS) adaptation is applied to the GTFLN and OGTFLN filters for nonlinear system identification, resulting in the GTFLMS and OGTFLMS algorithms, respectively. Moreover, the theoretical steady-state excess mean-square error of the GTFLN filter is analyzed. Simulations validate the effectiveness of the theoretical analysis and demonstrate the improved performance of the GTFLN and OGTFLN filters over the linear-in-the-parameters benchmarks in nonlinear system identification and nonlinear acoustic echo cancellation. Based on the GTFLN filter, the filtered-g LMS (FgLMS) algorithm is proposed for nonlinear active noise control. Simulations demonstrate improved stability and noise reduction performance compared to the benchmarks.

eess.SP↗

arXiv2026

Scalable Neural Vocoder from Range-Null Space Decomposition

Although deep neural networks have facilitated significant progress of neural vocoders in recent years, they usually suffer from intrinsic challenges like opaque modeling, inflexible retraining under different input configurations, and parameter-performance trade-off. These inherent hurdles can heavily impede the development of this field. To resolve these problems, in this paper, we propose a novel neural vocoder in the time-frequency (T-F) domain. Specifically, we bridge the connection between the classical range-null decomposition (RND) theory and the vocoder task, where the reconstruction of the target spectrogram is formulated into the superimposition between range-space and null-space. The former aims to project the representation in the original mel-domain into the target linear-scale domain, and the latter can be instantiated via neural networks to further infill the spectral details. To fully leverage the spectrum prior, an elaborate dual-path framework is devised, where the spectrum is hierarchically encoded and decoded, and the cross- and narrow-band modules are leveraged for effectively modeling along sub-band and time dimensions. To enable inference under various configurations, we propose a simple yet effective strategy, which transforms the multi-condition adaption in the inference stage into the data augmentation in the training stage. Comprehensive experiments are conducted on various benchmarks. Quantitative and qualitative results show that while enjoying lightweight network structure and scalable inference paradigm, the proposed framework achieves state-ofthe-art performance among existing advanced methods. Code is available at https://github.com/Andong-Li-speech/RNDVoC.

cs.SD↗

arXiv2026

DBMIF: a deep balanced multimodal iterative fusion framework for air- and bone-conduction speech enhancement

The performance of conventional speech enhancement systems degrades sharply in extremely low signal-to-noise ratio (SNR) environments where air-conduction (AC) microphones are overwhelmed by ambient noise. Although bone-conduction (BC) sensors offer complementary, noise-tolerant information, existing fusion approaches struggle to maintain consistent performance across a wide range of SNR conditions. To address this limitation, we propose the Deep Balanced Multimodal Iterative Fusion Framework (DBMIF), a three-branch architecture designed to reconstruct high-fidelity speech through rigorous cross-modal interaction. Specifically, grounded in a multi-scale interactive encoder-decoder backbone, the framework orchestrates an iterative attention module and a cross-branch gated module to facilitate adaptive weighting and bidirectional exchange. To complement this dynamic interaction, a balanced-interaction bottleneck is further integrated to learn a compact, stable fused representation. Extensive experiments demonstrate that DBMIF achieves competitive performance compared with recent unimodal and multimodal baselines in both speech quality and intelligibility across diverse noise types. In downstream ASR tasks, the proposed method reduces the character error rate by at least 2.5 percent compared to competing approaches. These results confirm that DBMIF effectively harnesses the robustness of BC speech while preserving the naturalness of AC speech, ensuring reliability in real-world scenarios. The source code is publicly available at github.com/wyl516w/dbmif.

eess.AS↗

arXiv2026

SLD-L2S: Hierarchical Subspace Latent Diffusion for High-Fidelity Lip to Speech Synthesis

Although lip-to-speech synthesis (L2S) has achieved significant progress in recent years, current state-of-the-art methods typically rely on intermediate representations such as mel-spectrograms or discrete self-supervised learning (SSL) tokens. The potential of latent diffusion models (LDMs) in this task remains largely unexplored. In this paper, we introduce SLD-L2S, a novel L2S framework built upon a hierarchical subspace latent diffusion model. Our method aims to directly map visual lip movements to the continuous latent space of a pre-trained neural audio codec, thereby avoiding the information loss inherent in traditional intermediate representations. The core of our method is a hierarchical architecture that processes visual representations through multiple parallel subspaces, initiated by a subspace decomposition module. To efficiently enhance interactions within and between these subspaces, we design the diffusion convolution block (DiCB) as our network backbone. Furthermore, we employ a reparameterized flow matching technique to directly generate the target latent vectors. This enables a principled inclusion of speech language model (SLM) and semantic losses during training, moving beyond conventional flow matching objectives and improving synthesized speech quality. Our experiments show that SLD-L2S achieves state-of-the-art generation quality on multiple benchmark datasets, surpassing existing methods in both objective and subjective evaluations.

eess.AS↗

arXiv2026

GOMPSNR: Reflourish the Signal-to-Noise Ratio Metric for Audio Generation Tasks

In the field of audio generation, signal-to-noise ratio (SNR) has long served as an objective metric for evaluating audio quality. Nevertheless, recent studies have shown that SNR and its variants are not always highly correlated with human perception, prompting us to raise the questions: Why does SNR fail in measuring audio quality? And how to improve its reliability as an objective metric? In this paper, we identify the inadequate measurement of phase distance as a pivotal factor and propose to reformulate SNR with specially designed phase-distance terms, yielding an improved metric named GOMPSNR. We further extend the newly proposed formulation to derive two novel categories of loss function, corresponding to magnitude-guided phase refinement and joint magnitude-phase optimization, respectively. Besides, extensive experiments are conducted for an optimal combination of different loss functions. Experimental results on advanced neural vocoders demonstrate that our proposed GOMPSNR exhibits more reliable error measurement than SNR. Meanwhile, our proposed loss functions yield substantial improvements in model performance, and our wellchosen combination of different loss functions further optimizes the overall model capability.

cs.SD↗

arXiv2025

BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspective

This paper revisits the neural vocoder task through the lens of audio restoration and propose a novel diffusion vocoder called BridgeVoC. Specifically, by rank analysis, we compare the rank characteristics of Mel-spectrum with other common acoustic degradation factors, and cast the vocoder task as a specialized case of audio restoration, where the range-space spectral (RSS) surrogate of the target spectrum acts as the degraded input. Based on that, we introduce the Schrodinger bridge framework for diffusion modeling, which defines the RSS and target spectrum as dual endpoints of the stochastic generation trajectory. Further, to fully utilize the hierarchical prior of subbands in the time-frequency (T-F) domain, we elaborately devise a novel subband-aware convolutional diffusion network as the data predictor, where subbands are divided following an uneven strategy, and convolutional-style attention module is employed with large kernels for efficient T-F contextual modeling. To enable single-step inference, we propose an omnidirectional distillation loss to facilitate effective information transfer from the teacher model to the student model, and the performance is improved by combining target-related and bijective consistency losses. Comprehensive experiments are conducted on various benchmarks and out-of-distribution datasets. Quantitative and qualitative results show that while enjoying fewer parameters, lower computational cost, and competitive inference speed, the proposed BridgeVoC yields stateof-the-art performance over existing advanced GAN-, DDPMand flow-matching-based baselines with only 4 sampling steps. And consistent superiority is still achieved with single-step inference.

cs.SD↗

arXiv2025

LTA-L2S: Lexical Tone-Aware Lip-to-Speech Synthesis for Mandarin with Cross-Lingual Transfer Learning

Lip-to-speech (L2S) synthesis for Mandarin is a significant challenge, hindered by complex viseme-to-phoneme mappings and the critical role of lexical tones in intelligibility. To address this issue, we propose Lexical Tone-Aware Lip-to-Speech (LTA-L2S). To tackle viseme-to-phoneme complexity, our model adapts an English pre-trained audio-visual self-supervised learning (SSL) model via a cross-lingual transfer learning strategy. This strategy not only transfers universal knowledge learned from extensive English data to the Mandarin domain but also circumvents the prohibitive cost of training such a model from scratch. To specifically model lexical tones and enhance intelligibility, we further employ a flow-matching model to generate the F0 contour. This generation process is guided by ASR-fine-tuned SSL speech units, which contain crucial suprasegmental information. The overall speech quality is then elevated through a two-stage training paradigm, where a flow-matching postnet refines the coarse spectrogram from the first stage. Extensive experiments demonstrate that LTA-L2S significantly outperforms existing methods in both speech intelligibility and tonal accuracy.

cs.SD↗

arXiv2025

Rethinking the joint estimation of magnitude and phase for time-frequency domain neural vocoders

Time-frequency (T-F) domain-based neural vocoders have shown promising results in synthesizing high-fidelity audio. Nevertheless, it remains unclear on the mechanism of effectively predicting magnitude and phase targets jointly. In this paper, we start from two representative T-F domain vocoders, namely Vocos and APNet2, which belong to the single-stream and dual-stream modes for magnitude and phase estimation, respectively. When evaluating their performance on a large-scale dataset, we accidentally observe severe performance collapse of APNet2. To stabilize its performance, in this paper, we introduce three simple yet effective strategies, each targeting the topological space, the source space, and the output space, respectively. Specifically, we modify the architectural topology for better information exchange in the topological space, introduce prior knowledge to facilitate the generation process in the source space, and optimize the backpropagation process for parameter updates with an improved output format in the output space. Experimental results demonstrate that our proposed method effectively facilitates the joint estimation of magnitude and phase in APNet2, thus bridging the performance disparities between the single-stream and dual-stream vocoders.

eess.AS↗

arXiv2025

Deep Learning for Personalized Binaural Audio Reproduction

Personalized binaural audio reproduction is the basis of realistic spatial localization, sound externalization, and immersive listening, directly shaping user experience and listening effort. This survey reviews recent advances in deep learning for this task and organizes them by generation mechanism into two paradigms: explicit personalized filtering and end-to-end rendering. Explicit methods predict personalized head-related transfer functions (HRTFs) from sparse measurements, morphological features, or environmental cues, and then use them in the conventional rendering pipeline. End-to-end methods map source signals directly to binaural signals, aided by other inputs such as visual, textual, or parametric guidance, and they learn personalization within the model. We also summarize the field's main datasets and evaluation metrics to support fair and repeatable comparison. Finally, we conclude with a discussion of key applications enabled by these technologies, current technical limitations, and potential research directions for deep learning-based spatial audio systems.

eess.AS↗

arXiv2025

Learning Neural Vocoder from Range-Null Space Decomposition

Despite the rapid development of neural vocoders in recent years, they usually suffer from some intrinsic challenges like opaque modeling, and parameter-performance trade-off. In this study, we propose an innovative time-frequency (T-F) domain-based neural vocoder to resolve the above-mentioned challenges. To be specific, we bridge the connection between the classical signal range-null decomposition (RND) theory and vocoder task, and the reconstruction of target spectrogram can be decomposed into the superimposition between the range-space and null-space, where the former is enabled by a linear domain shift from the original mel-scale domain to the target linear-scale domain, and the latter is instantiated via a learnable network for further spectral detail generation. Accordingly, we propose a novel dual-path framework, where the spectrum is hierarchically encoded/decoded, and the cross- and narrow-band modules are elaborately devised for efficient sub-band and sequential modeling. Comprehensive experiments are conducted on the LJSpeech and LibriTTS benchmarks. Quantitative and qualitative results show that while enjoying lightweight network parameters, the proposed approach yields state-of-the-art performance among existing advanced methods. Our code and the pretrained model weights are available at https://github.com/Andong-Li-speech/RNDVoC.

cs.SD↗

arXiv2025

End-to-end multi-channel speaker extraction and binaural speech synthesis

Speech clarity and spatial audio immersion are the two most critical factors in enhancing remote conferencing experiences. Existing methods are often limited: either due to the lack of spatial information when using only one microphone, or because their performance is highly dependent on the accuracy of direction-of-arrival estimation when using microphone array. To overcome this issue, we introduce an end-to-end deep learning framework that has the capacity of mapping multi-channel noisy and reverberant signals to clean and spatialized binaural speech directly. This framework unifies source extraction, noise suppression, and binaural rendering into one network. In this framework, a novel magnitude-weighted interaural level difference loss function is proposed that aims to improve the accuracy of spatial rendering. Extensive evaluations show that our method outperforms established baselines in terms of both speech quality and spatial fidelity.

cs.SD↗

arXiv2025

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/.

cs.SD↗

arXiv2025

Neural Vocoders as Speech Enhancers

Speech enhancement (SE) and neural vocoding are traditionally viewed as separate tasks. In this work, we observe them under a common thread: the rank behavior of these processes. This observation prompts two key questions: \textit{Can a model designed for one task's rank degradation be adapted for the other?} and \textit{Is it possible to address both tasks using a unified model?} Our empirical findings demonstrate that existing speech enhancement models can be successfully trained to perform vocoding tasks, and a single model, when jointly trained, can effectively handle both tasks with performance comparable to separately trained models. These results suggest that speech enhancement and neural vocoding can be unified under a broader framework of speech restoration. Code: https://github.com/Andong-Li-speech/Neural-Vocoders-as-Speech-Enhancers.

cs.SD↗

arXiv2024

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.

cs.SD↗

arXiv2024

Spatial Reconstructed Local Attention Res2Net with F0 Subband for Fake Speech Detection

The rhythm of bonafide speech is often difficult to replicate, which causes that the fundamental frequency (F0) of synthetic speech is significantly different from that of real speech. It is expected that the F0 feature contains the discriminative information for the fake speech detection (FSD) task. In this paper, we propose a novel F0 subband for FSD. In addition, to effectively model the F0 subband so as to improve the performance of FSD, the spatial reconstructed local attention Res2Net (SR-LA Res2Net) is proposed. Specifically, Res2Net is used as a backbone network to obtain multiscale information, and enhanced with a spatial reconstruction mechanism to avoid losing important information when the channel group is constantly superimposed. In addition, local attention is designed to make the model focus on the local information of the F0 subband. Experimental results on the ASVspoof 2019 LA dataset show that our proposed method obtains an equal error rate (EER) of 0.47% and a minimum tandem detection cost function (min t-DCF) of 0.0159, achieving the state-of-the-art performance among all of the single systems.

cs.SD↗

arXiv2023

BAE-Net: A Low complexity and high fidelity Bandwidth-Adaptive neural network for speech super-resolution

Speech bandwidth extension (BWE) has demonstrated promising performance in enhancing the perceptual speech quality in real communication systems. Most existing BWE researches primarily focus on fixed upsampling ratios, disregarding the fact that the effective bandwidth of captured audio may fluctuate frequently due to various capturing devices and transmission conditions. In this paper, we propose a novel streaming adaptive bandwidth extension solution dubbed BAE-Net, which is suitable to handle the low-resolution speech with unknown and varying effective bandwidth. To address the challenges of recovering both the high-frequency magnitude and phase speech content blindly, we devise a dual-stream architecture that incorporates the magnitude inpainting and phase refinement. For potential applications on edge devices, this paper also introduces BAE-NET-lite, which is a lightweight, streaming and efficient framework. Quantitative results demonstrate the superiority of BAE-Net in terms of both performance and computational efficiency when compared with existing state-of-the-art BWE methods.

cs.SD↗

arXiv2023

A General Unfolding Speech Enhancement Method Motivated by Taylor's Theorem

While deep neural networks have facilitated significant advancements in the field of speech enhancement, most existing methods are developed following either empirical or relatively blind criteria, lacking adequate guidelines in pipeline design. 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 neighborhood space of the noisy mixture, in which an unknown sparse term is introduced and applied 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 terms 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. Given that the proposed framework is devised based on Taylor's theorem, it possesses improved internal flexibility. Extensive experiments are conducted on WSJ0-SI84, DNS-Challenge, Voicebank+Demand, spatialized Librispeech, and L3DAS22 multi-channel speech enhancement challenge datasets. Quantitative results show that the proposed approach yields competitive performance over existing top-performing approaches in terms of multiple objective metrics.

cs.SD↗

arXiv2022

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.

cs.SD↗