Enhancing Intelligibility for Generative Target Speech Extraction via Joint Optimization with Target Speaker ASR

Target speech extraction (TSE) isolates the speech of a specific speaker from a multi-talker overlapped speech mixture. Most existing TSE models rely on discriminative methods, typically predicting a time-frequency spectrogram mask for the target speech. However, imperfections in these masks often result in over-/under-suppression of target/non-target speech, degrading perceptual quality. Generative methods, by contrast, re-synthesize target speech based on the mixture and target speaker cues, achieving superior perceptual quality. Nevertheless, these methods often overlook speech intelligibility, leading to alterations or loss of semantic content in the re-synthesized speech. Inspired by the Whisper model's success in target speaker ASR, we propose a generative TSE framework based on the pre-trained Whisper model to address the above issues. This framework integrates semantic modeling with flow-based acoustic modeling to achieve both high intelligibility and perceptual quality. Results from multiple benchmarks demonstrate that the proposed method outperforms existing generative and discriminative baselines. We present speech samples on our demo page.

Language-Queried Target Sound Extraction Without Parallel Training Data

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a language-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the multi-modal representation alignment nature of the contrastive language-audio pre-trained model (CLAP). In a vanilla language-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding for the TSE model, while during inference, user language queries are encoded by CLAP text encoder. This straightforward approach faces challenges due to the modality gap between training and inference queries and information leakage from direct exposure to target audio during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and inference and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability.

An Efficient Algorithm for Sum-Rate Maximization in Fluid Antenna-Assisted ISAC System

In this letter, we investigate the fluid antenna (FA)-assisted integrated sensing and communication (ISAC) system, where communication and radar sensing employ the co-waveform design. Specifically, we focus on the beamformer design and antenna position configuration to realize a higher communication rate while guaranteeing the minimum radar probing power. Different from existing beamformer algorithms, we propose an efficient proximal distance algorithm (PDA) to solve the multiuser sum-rate maximization problem with radar sensing constraint to obtain the closed-form beamforming vector. In addition, we develop an extrapolated projected gradient (EPG) algorithm to obtain a better antenna location configuration for FA to enhance the ISAC performance. Numerical results show that the considered FA-assisted ISAC system enjoys a higher sum-rate by the proposed algorithm, compared with that in existing non-FA ISAC systems.

CLAPSep: Leveraging Contrastive Pre-trained Models for Multi-Modal Query-Conditioned Target Sound Extraction

Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world sound recordings. Language-queried target sound extraction (TSE) is an effective approach to achieving USS. Such systems consist of two components: a query network that converts user queries into conditional embeddings, and a separation network that extracts the target sound based on conditional embeddings. Existing methods mainly suffer from two issues: firstly, they require training a randomly initialized model from scratch, lacking the utilization of pre-trained models, and substantial data and computational resources are needed to ensure model convergence; secondly, existing methods need to jointly train a query network and a separation network, which tends to lead to overfitting. To address these issues, we build the CLAPSep model based on contrastive language-audio pre-trained model (CLAP). We achieve this by using a pre-trained text encoder of CLAP as the query network and introducing pre-trained audio encoder weights of CLAP into the separation network to fully utilize the prior knowledge embedded in the pre-trained model to assist in target sound extraction tasks. Extensive experimental results demonstrate that the proposed method saves training resources while ensuring the model's performance and generalizability. Additionally, we explore the model's ability to comprehensively utilize language/audio multi-modal and positive/negative multi-valent user queries, enhancing system performance while providing diversified application modes.

MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical World

Recent investigations demonstrate that adversarial patches can be utilized to manipulate the result of object detection models. However, the conspicuous patterns on these patches may draw more attention and raise suspicions among humans. Moreover, existing works have primarily focused on enhancing the efficacy of attacks in the physical domain, rather than seeking to optimize their stealth attributes and transferability potential. To address these issues, we introduce a dual-perception-based attack framework that generates an adversarial patch known as the More Vivid Patch (MVPatch). The framework consists of a model-perception degradation method and a human-perception improvement method. To derive the MVPatch, we formulate an iterative process that simultaneously constrains the efficacy of multiple object detectors and refines the visual correlation between the generated adversarial patch and a realistic image. Our method employs a model-perception-based approach that reduces the object confidence scores of several object detectors to boost the transferability of adversarial patches. Further, within the human-perception-based framework, we put forward a lightweight technique for visual similarity measurement that facilitates the development of inconspicuous and natural adversarial patches and eliminates the reliance on additional generative models. Additionally, we introduce the naturalness score and transferability score as metrics for an unbiased assessment of various adversarial patches' natural appearance and transferability capacity. Extensive experiments demonstrate that the proposed MVPatch algorithm achieves superior attack transferability compared to similar algorithms in both digital and physical domains while also exhibiting a more natural appearance. These findings emphasize the remarkable stealthiness and transferability of the proposed MVPatch attack algorithm.

An efficient algorithm for multiuser sum-rate maximization of large-scale active RIS-aided MIMO system

Active reconfigurable intelligent surface (RIS) is a new RIS architecture that can reflect and amplify communication signals. It can provide enhanced performance gain compared to the conventional passive RIS systems that can only reflect the signals. On the other hand, the design problem of active RIS-aided systems is more challenging than the passive RIS-aided systems and its efficient algorithms are less studied. In this paper, we consider the sum rate maximization problem in the multiuser massive multiple-input single-output (MISO) downlink with the aid of a large-scale active RIS. Existing approaches usually resort to general optimization solvers and can be computationally prohibitive in the considered settings. We propose an efficient block successive upper bound minimization (BSUM) method, of which each step has a (semi) closed-form update. Thus, the proposed algorithm has an attractive low per-iteration complexity. By simulation, our proposed algorithm consumes much less computation than the existing approaches. In particular, when the MIMO and/or RIS sizes are large, our proposed algorithm can be orders-of-magnitude faster than existing approaches.

Extending Whisper with prompt tuning to target-speaker ASR

Target-speaker automatic speech recognition (ASR) aims to transcribe the desired speech of a target speaker from multi-talker overlapped utterances. Most of the existing target-speaker ASR (TS-ASR) methods involve either training from scratch or fully fine-tuning a pre-trained model, leading to significant training costs and becoming inapplicable to large foundation models. This work leverages prompt tuning, a parameter-efficient fine-tuning approach, to extend Whisper, a large-scale single-talker ASR model, to TS-ASR. Experimental results show that prompt tuning can achieve performance comparable to state-of-the-art full fine-tuning approaches while only requiring about 1% of task-specific model parameters. Notably, the original Whisper's features, such as inverse text normalization and timestamp prediction, are retained in target-speaker ASR, keeping the generated transcriptions natural and informative.

Nonlinear Kernel Support Vector Machine with 0-1 Soft Margin Loss

Recent advance on linear support vector machine with the 0-1 soft margin loss ($L_{0/1}$-SVM) shows that the 0-1 loss problem can be solved directly. However, its theoretical and algorithmic requirements restrict us extending the linear solving framework to its nonlinear kernel form directly, the absence of explicit expression of Lagrangian dual function of $L_{0/1}$-SVM is one big deficiency among of them. In this paper, by applying the nonparametric representation theorem, we propose a nonlinear model for support vector machine with 0-1 soft margin loss, called $L_{0/1}$-KSVM, which cunningly involves the kernel technique into it and more importantly, follows the success on systematically solving its linear task. Its optimal condition is explored theoretically and a working set selection alternating direction method of multipliers (ADMM) algorithm is introduced to acquire its numerical solution. Moreover, we firstly present a closed-form definition to the support vector (SV) of $L_{0/1}$-KSVM. Theoretically, we prove that all SVs of $L_{0/1}$-KSVM are only located on the parallel decision surfaces. The experiment part also shows that $L_{0/1}$-KSVM has much fewer SVs, simultaneously with a decent predicting accuracy, when comparing to its linear peer $L_{0/1}$-SVM and the other six nonlinear benchmark SVM classifiers.

Non-Cooperative Game Theory Based Rate Adaptation for Dynamic Video Streaming over HTTP

Dynamic Adaptive Streaming over HTTP (DASH) has demonstrated to be an emerging and promising multimedia streaming technique, owing to its capability of dealing with the variability of networks. Rate adaptation mechanism, a challenging and open issue, plays an important role in DASH based systems since it affects Quality of Experience (QoE) of users, network utilization, etc. In this paper, based on non-cooperative game theory, we propose a novel algorithm to optimally allocate the limited export bandwidth of the server to multi-users to maximize their QoE with fairness guaranteed. The proposed algorithm is proxy-free. Specifically, a novel user QoE model is derived by taking a variety of factors into account, like the received video quality, the reference buffer length, and user accumulated buffer lengths, etc. Then, the bandwidth competing problem is formulated as a non-cooperation game with the existence of Nash Equilibrium that is theoretically proven. Finally, a distributed iterative algorithm with stability analysis is proposed to find the Nash Equilibrium. Compared with state-of-the-art methods, extensive experimental results in terms of both simulated and realistic networking scenarios demonstrate that the proposed algorithm can produce higher QoE, and the actual buffer lengths of all users keep nearly optimal states, i.e., moving around the reference buffer all the time. Besides, the proposed algorithm produces no playback interruption.

A Comprehensive Study and Comparison of Core Technologies for MPEG 3D Point Cloud Compression

Point cloud based 3D visual representation is becoming popular due to its ability to exhibit the real world in a more comprehensive and immersive way. However, under a limited network bandwidth, it is very challenging to communicate this kind of media due to its huge data volume. Therefore, the MPEG have launched the standardization for point cloud compression (PCC), and proposed three model categories, i.e., TMC1, TMC2, and TMC3. Because the 3D geometry compression methods of TMC1 and TMC3 are similar, TMC1 and TMC3 are further merged into a new platform namely TMC13. In this paper, we first introduce some basic technologies that are usually used in 3D point cloud compression, then review the encoder architectures of these test models in detail, and finally analyze their rate distortion performance as well as complexity quantitatively for different cases (i.e., lossless geometry and lossless color, lossless geometry and lossy color, lossy geometry and lossy color) by using 16 benchmark 3D point clouds that are recommended by MPEG. Experimental results demonstrate that the coding efficiency of TMC2 is the best on average (especially for lossy geometry and lossy color compression) for dense point clouds while TMC13 achieves the optimal coding performance for sparse and noisy point clouds with lower time complexity.