arXiv subjects

Shuai Wang

Publications and source records attributed to Shuai Wang.

At least 451 records · Page 25Linked to original sources

arXiv2024

M-Vec: Matryoshka Speaker Embeddings with Flexible Dimensions

Fixed-dimensional speaker embeddings have become the dominant approach in speaker modeling, typically spanning hundreds to thousands of dimensions. These dimensions are hyperparameters that are not specifically picked, nor are they hierarchically ordered in terms of importance. In large-scale speaker representation databases, reducing the dimensionality of embeddings can significantly lower storage and computational costs. However, directly training low-dimensional representations often yields suboptimal performance. In this paper, we introduce the Matryoshka speaker embedding, a method that allows dynamic extraction of sub-dimensions from the embedding while maintaining performance. Our approach is validated on the VoxCeleb dataset, demonstrating that it can achieve extremely low-dimensional embeddings, such as 8 dimensions, while preserving high speaker verification performance.

eess.AS↗

arXiv2024

WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction

Target speaker extraction (TSE) focuses on isolating the speech of a specific target speaker from overlapped multi-talker speech, which is a typical setup in the cocktail party problem. In recent years, TSE draws increasing attention due to its potential for various applications such as user-customized interfaces and hearing aids, or as a crutial front-end processing technologies for subsequential tasks such as speech recognition and speaker recongtion. However, there are currently few open-source toolkits or available pre-trained models for off-the-shelf usage. In this work, we introduce WeSep, a toolkit designed for research and practical applications in TSE. WeSep is featured with flexible target speaker modeling, scalable data management, effective on-the-fly data simulation, structured recipes and deployment support. The toolkit is publicly avaliable at \url{https://github.com/wenet-e2e/WeSep.}

eess.AS↗

arXiv2024

Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching

Speaker diarization is typically considered a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore the use of neural network-based generative methods for speaker diarization for the first time. We implement a Flow-Matching (FM) based generative algorithm within the sequence-to-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, we propose mapping the binary label sequence into a dense latent space before applying the generative algorithm and our proposed Flow-TSVAD method outperforms the Seq2Seq-TSVAD system. Additionally, we observe that the FM algorithm converges rapidly during the inference stage, requiring only two inference steps to achieve promising results. As a generative model, Flow-TSVAD allows for sampling different diarization results by running the model multiple times. Moreover, ensembling results from various sampling instances further enhances diarization performance.

cs.SD↗

arXiv2024

Privacy-Preserving Federated Learning with Consistency via Knowledge Distillation Using Conditional Generator

Federated Learning (FL) is gaining popularity as a distributed learning framework that only shares model parameters or gradient updates and keeps private data locally. However, FL is at risk of privacy leakage caused by privacy inference attacks. And most existing privacy-preserving mechanisms in FL conflict with achieving high performance and efficiency. Therefore, we propose FedMD-CG, a novel FL method with highly competitive performance and high-level privacy preservation, which decouples each client's local model into a feature extractor and a classifier, and utilizes a conditional generator instead of the feature extractor to perform server-side model aggregation. To ensure the consistency of local generators and classifiers, FedMD-CG leverages knowledge distillation to train local models and generators at both the latent feature level and the logit level. Also, we construct additional classification losses and design new diversity losses to enhance client-side training. FedMD-CG is robust to data heterogeneity and does not require training extra discriminators (like cGAN). We conduct extensive experiments on various image classification tasks to validate the superiority of FedMD-CG.

cs.LG↗

arXiv2024

DFDG: Data-Free Dual-Generator Adversarial Distillation for One-Shot Federated Learning

Federated Learning (FL) is a distributed machine learning scheme in which clients jointly participate in the collaborative training of a global model by sharing model information rather than their private datasets. In light of concerns associated with communication and privacy, one-shot FL with a single communication round has emerged as a de facto promising solution. However, existing one-shot FL methods either require public datasets, focus on model homogeneous settings, or distill limited knowledge from local models, making it difficult or even impractical to train a robust global model. To address these limitations, we propose a new data-free dual-generator adversarial distillation method (namely DFDG) for one-shot FL, which can explore a broader local models' training space via training dual generators. DFDG is executed in an adversarial manner and comprises two parts: dual-generator training and dual-model distillation. In dual-generator training, we delve into each generator concerning fidelity, transferability and diversity to ensure its utility, and additionally tailor the cross-divergence loss to lessen the overlap of dual generators' output spaces. In dual-model distillation, the trained dual generators work together to provide the training data for updates of the global model. At last, our extensive experiments on various image classification tasks show that DFDG achieves significant performance gains in accuracy compared to SOTA baselines.

cs.DC↗

arXiv2024

On the effectiveness of enrollment speech augmentation for Target Speaker Extraction

Deep learning technologies have significantly advanced the performance of target speaker extraction (TSE) tasks. To enhance the generalization and robustness of these algorithms when training data is insufficient, data augmentation is a commonly adopted technique. Unlike typical data augmentation applied to speech mixtures, this work thoroughly investigates the effectiveness of augmenting the enrollment speech space. We found that for both pretrained and jointly optimized speaker encoders, directly augmenting the enrollment speech leads to consistent performance improvement. In addition to conventional methods such as noise and reverberation addition, we propose a novel augmentation method called self-estimated speech augmentation (SSA). Experimental results on the Libri2Mix test set show that our proposed method can achieve an improvement of up to 2.5 dB.

cs.SD↗

arXiv2024

E1 TTS: Simple and Fast Non-Autoregressive TTS

This paper introduces Easy One-Step Text-to-Speech (E1 TTS), an efficient non-autoregressive zero-shot text-to-speech system based on denoising diffusion pretraining and distribution matching distillation. The training of E1 TTS is straightforward; it does not require explicit monotonic alignment between the text and audio pairs. The inference of E1 TTS is efficient, requiring only one neural network evaluation for each utterance. Despite its sampling efficiency, E1 TTS achieves naturalness and speaker similarity comparable to various strong baseline models. Audio samples are available at http://e1tts.github.io/ .

eess.AS↗

arXiv2024

Disentangling the Prosody and Semantic Information with Pre-trained Model for In-Context Learning based Zero-Shot Voice Conversion

Voice conversion (VC) aims to modify the speaker's timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens, facilitating disentanglement of speech content information. Recently, in-context learning (ICL) has emerged in text-to-speech (TTS) systems for effectively modeling specific characteristics such as timbre through context conditioning. This paper proposes an ICL capability enhanced VC system (ICL-VC) employing a mask and reconstruction training strategy based on flow-matching generative models. Augmented with semantic tokens, our experiments on the LibriTTS dataset demonstrate that ICL-VC improves speaker similarity. Additionally, we find that k-means is a versatile tokenization method applicable to various pre-trained models. However, the ICL-VC system faces challenges in preserving the prosody of the source speech. To mitigate this issue, we propose incorporating prosody embeddings extracted from a pre-trained emotion recognition model into our system. Integration of prosody embeddings notably enhances the system's capability to preserve source speech prosody, as validated on the Emotional Speech Database.

cs.SD↗

arXiv2024

Joint Input and Output Coordination for Class-Incremental Learning

Incremental learning is nontrivial due to severe catastrophic forgetting. Although storing a small amount of data on old tasks during incremental learning is a feasible solution, current strategies still do not 1) adequately address the class bias problem, and 2) alleviate the mutual interference between new and old tasks, and 3) consider the problem of class bias within tasks. This motivates us to propose a joint input and output coordination (JIOC) mechanism to address these issues. This mechanism assigns different weights to different categories of data according to the gradient of the output score, and uses knowledge distillation (KD) to reduce the mutual interference between the outputs of old and new tasks. The proposed mechanism is general and flexible, and can be incorporated into different incremental learning approaches that use memory storage. Extensive experiments show that our mechanism can significantly improve their performance.

cs.LG↗

arXiv2024

$\mathbb{USCD}$: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decoding

Large language models (LLMs) have shown remarkable capabilities in code generation. However, the effects of hallucinations (e.g., output noise) make it particularly challenging for LLMs to generate high-quality code in one pass. In this work, we propose a simple and effective \textbf{u}ncertainty-aware \textbf{s}elective \textbf{c}ontrastive \textbf{d}ecoding ($\mathbb{USCD}$) mechanism to improve the quality of one-pass code generation in LLMs and reduce the impact of output noise. To be specific, we first elaborately designed a negative prompt (namely lame prompt) to output noise by removing input-output examples from the standard few-shot prompt. Our preliminary study shows that the Jensen-Shannon divergence (JS divergence) between token distribution uncertainty and the output noise is relatively low (approximately $0.25$), indicating their high relevance. Then, we selectively eliminate output noise induced by lame prompts based on the uncertainty of the prediction distribution from the standard prompt. Notably, our proposed plug-and-play mechanism is an inference-only method, enjoying appealing flexibility. Extensive experiments on widely used benchmarks, e.g., HumanEval, MBPP, and MultiPL-E, upon several LLMs (i.e., Inocder-6b, CodeLlama-7b, WizardCoder-15b, StarCoder, and Llama2-7b), demonstrate that our proposed USCD significantly improves one-pass code generation, with an average \textit{pass@$1$} scores increase of 16.59\%. We will release code and data on GitHub.

cs.SE↗

arXiv2024

DECAN: A Denoising Encoder via Contrastive Alignment Network for Dry Electrode EEG Emotion Recognition

EEG signal is important for brain-computer interfaces (BCI). Nevertheless, existing dry and wet electrodes are difficult to balance between high signal-to-noise ratio and portability in EEG recording, which limits the practical use of BCI. In this study, we propose a Denoising Encoder via Contrastive Alignment Network (DECAN) for dry electrode EEG, under the assumption of the EEG representation consistency between wet and dry electrodes during the same task. Specifically, DECAN employs two parameter-sharing deep neural networks to extract task-relevant representations of dry and wet electrode signals, and then integrates a representation-consistent contrastive loss to minimize the distance between representations from the same timestamp and category but different devices. To assess the feasibility of our approach, we construct an emotion dataset consisting of paired dry and wet electrode EEG signals from 16 subjects with 5 emotions, named PaDWEED. Results on PaDWEED show that DECAN achieves an average accuracy increase of 6.94$\%$ comparing to state-of-the art performance in emotion recognition of dry electrodes. Ablation studies demonstrate a decrease in inter-class aliasing along with noteworthy accuracy enhancements in the delta and beta frequency bands. Moreover, an inter-subject feature alignment can obtain an accuracy improvement of 5.99$\%$ and 5.14$\%$ in intra- and inter-dataset scenarios, respectively. Our proposed method may open up new avenues for BCI with dry electrodes. PaDWEED dataset used in this study is freely available at https://huggingface.co/datasets/peiyu999/PaDWEED.

cs.HC↗

arXiv2024

Revisiting the Time Cost Model of AllReduce

AllReduce is an important and popular collective communication primitive, which has been widely used in areas such as distributed machine learning and high performance computing. To design, analyze, and choose from various algorithms and implementations of AllReduce, the time cost model plays a crucial role, and the predominant one is the $(α,β,γ)$ model. In this paper, we revisit this model, and reveal that it cannot well characterize the time cost of AllReduce on modern clusters; thus must be updated. We perform extensive measurements to identify two additional terms contributing to the time cost: the incast term and the memory access term. We augment the $(α,β,γ)$ model with these two terms, and present GenModel as a result. Using GenModel, we discover two new optimalities for AllReduce algorithms, and prove that they cannot be achieved simultaneously. Finally, striking the balance between the two new optimalities, we design GenTree, an AllReduce plan generation algorithm specialized for tree-like topologies. Experiments on a real testbed with 64 GPUs show that GenTree can achieve 1.22$\times$ to 1.65$\times$ speed-up against NCCL. Large-scale simulations also confirm that GenTree can improve the state-of-the-art AllReduce algorithm by a factor of $1.2$ to $7.4$ in scenarios where the two new terms dominate.

cs.DC↗

arXiv2024

FDNet: Feature Decoupled Segmentation Network for Tooth CBCT Image

Precise Tooth Cone Beam Computed Tomography (CBCT) image segmentation is crucial for orthodontic treatment planning. In this paper, we propose FDNet, a Feature Decoupled Segmentation Network, to excel in the face of the variable dental conditions encountered in CBCT scans, such as complex artifacts and indistinct tooth boundaries. The Low-Frequency Wavelet Transform (LF-Wavelet) is employed to enrich the semantic content by emphasizing the global structural integrity of the teeth, while the SAM encoder is leveraged to refine the boundary delineation, thus improving the contrast between adjacent dental structures. By integrating these dual aspects, FDNet adeptly addresses the semantic gap, providing a detailed and accurate segmentation. The framework's effectiveness is validated through rigorous benchmarks, achieving the top Dice and IoU scores of 85.28% and 75.23%, respectively. This innovative decoupling of semantic and boundary features capitalizes on the unique strengths of each element to elevate the quality of segmentation performance.

cs.CV↗

arXiv2024

ESP-PCT: Enhanced VR Semantic Performance through Efficient Compression of Temporal and Spatial Redundancies in Point Cloud Transformers

Semantic recognition is pivotal in virtual reality (VR) applications, enabling immersive and interactive experiences. A promising approach is utilizing millimeter-wave (mmWave) signals to generate point clouds. However, the high computational and memory demands of current mmWave point cloud models hinder their efficiency and reliability. To address this limitation, our paper introduces ESP-PCT, a novel Enhanced Semantic Performance Point Cloud Transformer with a two-stage semantic recognition framework tailored for VR applications. ESP-PCT takes advantage of the accuracy of sensory point cloud data and optimizes the semantic recognition process, where the localization and focus stages are trained jointly in an end-to-end manner. We evaluate ESP-PCT on various VR semantic recognition conditions, demonstrating substantial enhancements in recognition efficiency. Notably, ESP-PCT achieves a remarkable accuracy of 93.2% while reducing the computational requirements (FLOPs) by 76.9% and memory usage by 78.2% compared to the existing Point Transformer model simultaneously. These underscore ESP-PCT's potential in VR semantic recognition by achieving high accuracy and reducing redundancy. The code and data of this project are available at \url{https://github.com/lymei-SEU/ESP-PCT}.

cs.CV↗

arXiv2024

Drop the beat! Freestyler for Accompaniment Conditioned Rapping Voice Generation

Rap, a prominent genre of vocal performance, remains underexplored in vocal generation. General vocal synthesis depends on precise note and duration inputs, requiring users to have related musical knowledge, which limits flexibility. In contrast, rap typically features simpler melodies, with a core focus on a strong rhythmic sense that harmonizes with accompanying beats. In this paper, we propose Freestyler, the first system that generates rapping vocals directly from lyrics and accompaniment inputs. Freestyler utilizes language model-based token generation, followed by a conditional flow matching model to produce spectrograms and a neural vocoder to restore audio. It allows a 3-second prompt to enable zero-shot timbre control. Due to the scarcity of publicly available rap datasets, we also present RapBank, a rap song dataset collected from the internet, alongside a meticulously designed processing pipeline. Experimental results show that Freestyler produces high-quality rapping voice generation with enhanced naturalness and strong alignment with accompanying beats, both stylistically and rhythmically.

eess.AS↗

arXiv2024

Whisper-PMFA: Partial Multi-Scale Feature Aggregation for Speaker Verification using Whisper Models

In this paper, Whisper, a large-scale pre-trained model for automatic speech recognition, is proposed to apply to speaker verification. A partial multi-scale feature aggregation (PMFA) approach is proposed based on a subset of Whisper encoder blocks to derive highly discriminative speaker embeddings.Experimental results demonstrate that using the middle to later blocks of the Whisper encoder keeps more speaker information. On the VoxCeleb1 and CN-Celeb1 datasets, our system achieves 1.42% and 8.23% equal error rates (EERs) respectively, receiving 0.58% and 1.81% absolute EER reductions over the ECAPA-TDNN baseline, and 0.46% and 0.97% over the ResNet34 baseline. Furthermore, our results indicate that using Whisper models trained on multilingual data can effectively enhance the model's robustness across languages. Finally, the low-rank adaptation approach is evaluated, which reduces the trainable model parameters by approximately 45 times while only slightly increasing EER by 0.2%.

cs.SD↗

arXiv2024

Multi-modal Intermediate Feature Interaction AutoEncoder for Overall Survival Prediction of Esophageal Squamous Cell Cancer

Survival prediction for esophageal squamous cell cancer (ESCC) is crucial for doctors to assess a patient's condition and tailor treatment plans. The application and development of multi-modal deep learning in this field have attracted attention in recent years. However, the prognostically relevant features between cross-modalities have not been further explored in previous studies, which could hinder the performance of the model. Furthermore, the inherent semantic gap between different modal feature representations is also ignored. In this work, we propose a novel autoencoder-based deep learning model to predict the overall survival of the ESCC. Two novel modules were designed for multi-modal prognosis-related feature reinforcement and modeling ability enhancement. In addition, a novel joint loss was proposed to make the multi-modal feature representations more aligned. Comparison and ablation experiments demonstrated that our model can achieve satisfactory results in terms of discriminative ability, risk stratification, and the effectiveness of the proposed modules.

eess.IV↗

arXiv2024

API-guided Dataset Synthesis to Finetune Large Code Models

Large code models (LCMs), pre-trained on vast code corpora, have demonstrated remarkable performance across a wide array of code-related tasks. Supervised fine-tuning (SFT) plays a vital role in aligning these models with specific requirements and enhancing their performance in particular domains. However, synthesizing high-quality SFT datasets poses a significant challenge due to the uneven quality of datasets and the scarcity of domain-specific datasets. Inspired by APIs as high-level abstractions of code that encapsulate rich semantic information in a concise structure, we propose DataScope, an API-guided dataset synthesis framework designed to enhance the SFT process for LCMs in both general and domain-specific scenarios. DataScope comprises two main components: Dsel and Dgen. On one hand, Dsel employs API coverage as a core metric, enabling efficient dataset synthesis in general scenarios by selecting subsets of existing (uneven-quality) datasets with higher API coverage. On the other hand, Dgen recasts domain dataset synthesis as a process of using API-specified high-level functionality and deliberately-constituted code skeletons to synthesize concrete code. Extensive experiments demonstrate DataScope's effectiveness, with models fine-tuned on its synthesized datasets outperforming those tuned on unoptimized datasets five times larger. Furthermore, a series of analyses on model internals, relevant hyperparameters, and case studies provide additional evidence for the efficacy of our proposed methods. These findings underscore the significance of dataset quality in SFT and advance the field of LCMs by providing an efficient, cost-effective framework for constructing high-quality datasets. This contribution enhances performance across both general and domain-specific scenarios, paving the way for more powerful and tailored LCMs.

cs.SE↗