UniFlow: Unifying Speech Front-End Tasks via Continuous Generative Modeling

Generative modeling has recently achieved remarkable success across image, video, and audio domains, demonstrating powerful capabilities for unified representation learning. Yet speech front-end tasks such as speech enhancement (SE), target speaker extraction (TSE), acoustic echo cancellation (AEC), and language-queried source separation (LASS) remain largely tackled by disparate, task-specific solutions. This fragmentation leads to redundant engineering effort, inconsistent performance, and limited extensibility. To address this gap, we introduce UniFlow, a unified framework that employs continuous generative modeling to tackle diverse speech front-end tasks in a shared latent space. Specifically, UniFlow utilizes a waveform variational autoencoder (VAE) to learn a compact latent representation of raw audio, coupled with a Diffusion Transformer (DiT) that predicts latent updates. To differentiate the speech processing task during the training, learnable condition embeddings indexed by a task ID are employed to enable maximal parameter sharing while preserving task-specific adaptability. To balance model performance and computational efficiency, we investigate and compare three generative objectives: denoising diffusion, flow matching, and mean flow within the latent domain. We validate UniFlow on multiple public benchmarks, demonstrating consistent gains over state-of-the-art baselines. UniFlow's unified latent formulation and conditional design make it readily extensible to new tasks, providing an integrated foundation for building and scaling generative speech processing pipelines. To foster future research, we will open-source our codebase.

EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation

In recent years, neural networks (NNs) have been widely applied in acoustic echo cancellation (AEC). However, existing approaches struggle to meet real-world low-latency and computational requirements while maintaining performance. To address this challenge, we propose EchoFree, an ultra lightweight neural AEC framework that combines linear filtering with a neural post filter. Specifically, we design a neural post-filter operating on Bark-scale spectral features. Furthermore, we introduce a two-stage optimization strategy utilizing self-supervised learning (SSL) models to improve model performance. We evaluate our method on the blind test set of the ICASSP 2023 AEC Challenge. The results demonstrate that our model, with only 278K parameters and 30 MMACs computational complexity, outperforms existing low-complexity AEC models and achieves performance comparable to that of state-of-the-art lightweight model DeepVQE-S. The audio examples are available.

FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching

Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods suffer from quantization loss, leading to compromised speaker similarity and intelligibility, while diffusion models require complex training and high inference latency. To address these challenges, we propose FlowSE, a flow-matching-based model for SE. Flow matching learns a continuous transformation between noisy and clean speech distributions in a single pass, significantly reducing inference latency while maintaining high-quality reconstruction. Specifically, FlowSE trains on noisy mel spectrograms and optional character sequences, optimizing a conditional flow matching loss with ground-truth mel spectrograms as supervision. It implicitly learns speech's temporal-spectral structure and text-speech alignment. During inference, FlowSE can operate with or without textual information, achieving impressive results in both scenarios, with further improvements when transcripts are available. Extensive experiments demonstrate that FlowSE significantly outperforms state-of-the-art generative methods, establishing a new paradigm for generative-based SE and demonstrating the potential of flow matching to advance the field. Our code, pre-trained checkpoints, and audio samples are available.

U-SAM: An audio language Model for Unified Speech, Audio, and Music Understanding

The text generation paradigm for audio tasks has opened new possibilities for unified audio understanding. However, existing models face significant challenges in achieving a comprehensive understanding across diverse audio types, such as speech, general audio events, and music. Furthermore, their exclusive reliance on cross-entropy loss for alignment often falls short, as it treats all tokens equally and fails to account for redundant audio features, leading to weaker cross-modal alignment. To deal with the above challenges, this paper introduces U-SAM, an advanced audio language model that integrates specialized encoders for speech, audio, and music with a pre-trained large language model (LLM). U-SAM employs a Mixture of Experts (MoE) projector for task-aware feature fusion, dynamically routing and integrating the domain-specific encoder outputs. Additionally, U-SAM incorporates a Semantic-Aware Contrastive Loss Module, which explicitly identifies redundant audio features under language supervision and rectifies their semantic and spectral representations to enhance cross-modal alignment. Extensive experiments demonstrate that U-SAM consistently outperforms both specialized models and existing audio language models across multiple benchmarks. Moreover, it exhibits emergent capabilities on unseen tasks, showcasing its generalization potential. Code is available (https://github.com/Honee-W/U-SAM/).

Causally-informed Deep Learning towards Explainable and Generalizable Outcomes Prediction in Critical Care

Recent advances in deep learning (DL) have prompted the development of high-performing early warning score (EWS) systems, predicting clinical deteriorations such as acute kidney injury, acute myocardial infarction, or circulatory failure. DL models have proven to be powerful tools for various tasks but come with the cost of lacking interpretability and limited generalizability, hindering their clinical applications. To develop a practical EWS system applicable to various outcomes, we propose causally-informed explainable early prediction model, which leverages causal discovery to identify the underlying causal relationships of prediction and thus owns two unique advantages: demonstrating the explicit interpretation of the prediction while exhibiting decent performance when applied to unfamiliar environments. Benefiting from these features, our approach achieves superior accuracy for 6 different critical deteriorations and achieves better generalizability across different patient groups, compared to various baseline algorithms. Besides, we provide explicit causal pathways to serve as references for assistant clinical diagnosis and potential interventions. The proposed approach enhances the practical application of deep learning in various medical scenarios.

Dynamic Programming-Based Redundancy Resolution for Path Planning of Redundant Manipulators Considering Breakpoints

This paper proposes a redundancy resolution algorithm for a redundant manipulator based on dynamic programming. This algorithm can compute the desired joint angles at each point on a pre-planned discrete path in Cartesian space, while ensuring that the angles, velocities, and accelerations of each joint do not exceed the manipulator's constraints. We obtain the analytical solution to the inverse kinematics problem of the manipulator using a parameterization method, transforming the redundancy resolution problem into an optimization problem of determining the parameters at each path point. The constraints on joint velocity and acceleration serve as constraints for the optimization problem. Then all feasible inverse kinematic solutions for each pose under the joint angle constraints of the manipulator are obtained through parameterization methods, and the globally optimal solution to this problem is obtained through the dynamic programming algorithm. On the other hand, if a feasible joint-space path satisfying the constraints does not exist, the proposed algorithm can compute the minimum number of breakpoints required for the path and partition the path with as few breakpoints as possible to facilitate the manipulator's operation along the path. The algorithm can also determine the optimal selection of breakpoints to minimize the global cost function, rather than simply interrupting when the manipulator is unable to continue operating. The proposed algorithm is tested using a manipulator produced by a certain manufacturer, demonstrating the effectiveness of the algorithm.

Dynamic Programming-Based Offline Redundancy Resolution of Redundant Manipulators Along Prescribed Paths with Real-Time Adjustment

Traditional offline redundancy resolution of trajectories for redundant manipulators involves computing inverse kinematic solutions for Cartesian space paths, constraining the manipulator to a fixed path without real-time adjustments. Online redundancy resolution can achieve real-time adjustment of paths, but it cannot consider subsequent path points, leading to the possibility of the manipulator being forced to stop mid-motion due to joint constraints. To address this, this paper introduces a dynamic programming-based offline redundancy resolution for redundant manipulators along prescribed paths with real-time adjustment. The proposed method allows the manipulator to move along a prescribed path while implementing real-time adjustment along the normal to the path. Using Dynamic Programming, the proposed approach computes a global maximum for the variation of adjustment coefficients. As long as the coefficient variation between adjacent sampling path points does not exceed this limit, the algorithm provides the next path point's joint angles based on the current joint angles, enabling the end-effector to achieve the adjusted Cartesian pose. The main innovation of this paper lies in augmenting traditional offline optimal planning with real-time adjustment capabilities, achieving a fusion of offline planning and online planning.

DualSep: A Light-weight dual-encoder convolutional recurrent network for real-time in-car speech separation

Advancements in deep learning and voice-activated technologies have driven the development of human-vehicle interaction. Distributed microphone arrays are widely used in in-car scenarios because they can accurately capture the voices of passengers from different speech zones. However, the increase in the number of audio channels, coupled with the limited computational resources and low latency requirements of in-car systems, presents challenges for in-car multi-channel speech separation. To migrate the problems, we propose a lightweight framework that cascades digital signal processing (DSP) and neural networks (NN). We utilize fixed beamforming (BF) to reduce computational costs and independent vector analysis (IVA) to provide spatial prior. We employ dual encoders for dual-branch modeling, with spatial encoder capturing spatial cues and spectral encoder preserving spectral information, facilitating spatial-spectral fusion. Our proposed system supports both streaming and non-streaming modes. Experimental results demonstrate the superiority of the proposed system across various metrics. With only 0.83M parameters and 0.39 real-time factor (RTF) on an Intel Core i7 (2.6GHz) CPU, it effectively separates speech into distinct speech zones. Our demos are available at https://honee-w.github.io/DualSep/.

Vec-Tok-VC+: Residual-enhanced Robust Zero-shot Voice Conversion with Progressive Constraints in a Dual-mode Training Strategy

Zero-shot voice conversion (VC) aims to transform source speech into arbitrary unseen target voice while keeping the linguistic content unchanged. Recent VC methods have made significant progress, but semantic losses in the decoupling process as well as training-inference mismatch still hinder conversion performance. In this paper, we propose Vec-Tok-VC+, a novel prompt-based zero-shot VC model improved from Vec-Tok Codec, achieving voice conversion given only a 3s target speaker prompt. We design a residual-enhanced K-Means decoupler to enhance the semantic content extraction with a two-layer clustering process. Besides, we employ teacher-guided refinement to simulate the conversion process to eliminate the training-inference mismatch, forming a dual-mode training strategy. Furthermore, we design a multi-codebook progressive loss function to constrain the layer-wise output of the model from coarse to fine to improve speaker similarity and content accuracy. Objective and subjective evaluations demonstrate that Vec-Tok-VC+ outperforms the strong baselines in naturalness, intelligibility, and speaker similarity.

SELM: Speech Enhancement Using Discrete Tokens and Language Models

Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech enhancement, harnessing semantic information holds potential advantages for speech enhancement tasks. In light of this, we propose SELM, a novel paradigm for speech enhancement, which integrates discrete tokens and leverages language models. SELM comprises three stages: encoding, modeling, and decoding. We transform continuous waveform signals into discrete tokens using pre-trained self-supervised learning (SSL) models and a k-means tokenizer. Language models then capture comprehensive contextual information within these tokens. Finally, a detokenizer and HiFi-GAN restore them into enhanced speech. Experimental results demonstrate that SELM achieves comparable performance in objective metrics alongside superior results in subjective perception. Our demos are available https://honee-w.github.io/SELM/.