arXiv subjects

Pengcheng Zhu

Publications and source records attributed to Pengcheng Zhu.

At least 37 records · Page 2Linked to original sources

arXiv2026

VoiceSculptor: Your Voice, Designed By You

Despite rapid progress in text-to-speech (TTS), open-source systems still lack truly instruction-following, fine-grained control over core speech attributes (e.g., pitch, speaking rate, age, emotion, and style). We present VoiceSculptor, an open-source unified system that bridges this gap by integrating instruction-based voice design and high-fidelity voice cloning in a single framework. It generates controllable speaker timbre directly from natural-language descriptions, supports iterative refinement via Retrieval-Augmented Generation (RAG), and provides attribute-level edits across multiple dimensions. The designed voice is then rendered into a prompt waveform and fed into a cloning model to enable high-fidelity timbre transfer for downstream speech synthesis. VoiceSculptor achieves open-source state-of-the-art (SOTA) on InstructTTSEval-Zh, and is fully open-sourced, including code and pretrained models, to advance reproducible instruction-controlled TTS research.

eess.AS↗

arXiv2026

WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem

Speech processing for low-resource dialects remains a fundamental challenge in developing inclusive and robust speech technologies. Despite its linguistic significance and large speaker population, the Wu dialect of Chinese has long been hindered by the lack of large-scale speech data, standardized evaluation benchmarks, and publicly available models. In this work, we present WenetSpeech-Wu, the first large-scale, multi-dimensionally annotated open-source speech corpus for the Wu dialect, comprising approximately 8,000 hours of diverse speech data. Building upon this dataset, we introduce WenetSpeech-Wu-Bench, the first standardized and publicly accessible benchmark for systematic evaluation of Wu dialect speech processing, covering automatic speech recognition (ASR), Wu-to-Mandarin translation, speaker attribute prediction, speech emotion recognition, text-to-speech (TTS) synthesis, and instruction-following TTS (instruct TTS). Furthermore, we release a suite of strong open-source models trained on WenetSpeech-Wu, establishing competitive performance across multiple tasks and empirically validating the effectiveness of the proposed dataset. Together, these contributions lay the foundation for a comprehensive Wu dialect speech processing ecosystem, and we open-source proposed datasets, benchmarks, and models to support future research on dialectal speech intelligence.

cs.SD↗

arXiv2025

MeanVC: Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows

Zero-shot voice conversion (VC) aims to transfer timbre from a source speaker to any unseen target speaker while preserving linguistic content. Growing application scenarios demand models with streaming inference capabilities. This has created a pressing need for models that are simultaneously fast, lightweight, and high-fidelity. However, existing streaming methods typically rely on either autoregressive (AR) or non-autoregressive (NAR) frameworks, which either require large parameter sizes to achieve strong performance or struggle to generalize to unseen speakers. In this study, we propose MeanVC, a lightweight and streaming zero-shot VC approach. MeanVC introduces a diffusion transformer with a chunk-wise autoregressive denoising strategy, combining the strengths of both AR and NAR paradigms for efficient streaming processing. By introducing mean flows, MeanVC regresses the average velocity field during training, enabling zero-shot VC with superior speech quality and speaker similarity in a single sampling step by directly mapping from the start to the endpoint of the flow trajectory. Additionally, we incorporate diffusion adversarial post-training to mitigate over-smoothing and further enhance speech quality. Experimental results demonstrate that MeanVC significantly outperforms existing zero-shot streaming VC systems, achieving superior conversion quality with higher efficiency and significantly fewer parameters. Audio demos and code are publicly available at https://aslp-lab.github.io/MeanVC.

eess.AS↗

arXiv2025

Average Achievable Rate Analysis of Cell-Free Massive MIMO in the Finite Blocklength Regime with Imperfect CSI

Acquiring perfect channel state information (CSI) introduces substantial challenges in cell-free massive MIMO (CF-mMIMO) systems, primarily due to the large dimensionality of channel parameters, especially under ultra-reliable low-latency communication (uRLLC) constraints. Furthermore, the impact of imperfect CSI on the average achievable rate within the finite blocklength regime remains largely unexplored. Motivated by this gap, this paper proposes a novel analytical framework that provides a closed-form expression for the average achievable rate with imperfect CSI in the Laplace domain. We demonstrate analytically that both the channel dispersion and the expected channel capacity can be expressed explicitly in terms of the Laplace transform of the large-scale fading component. Numerical simulations confirm that the derived expressions match closely with Monte Carlo simulations, verifying their accuracy. Furthermore, we theoretically show that although imperfect CSI degrades performance in the finite blocklength regime, the inherent characteristics of CF-mMIMO architecture effectively mitigates this loss.

cs.IT↗

arXiv2025

REF-VC: Robust, Expressive and Fast Zero-Shot Voice Conversion with Diffusion Transformers

In real-world voice conversion applications, environmental noise in source speech and user demands for expressive output pose critical challenges. Traditional ASR-based methods ensure noise robustness but suppress prosody richness, while SSL-based models improve expressiveness but suffer from timbre leakage and noise sensitivity. This paper proposes REF-VC, a noise-robust expressive voice conversion system. Key innovations include: (1) A random erasing strategy to mitigate the information redundancy inherent in SSL features, enhancing noise robustness and expressiveness; (2) Implicit alignment inspired by E2TTS to suppress non-essential feature reconstruction; (3) Integration of Shortcut Models to accelerate flow matching inference, significantly reducing to 4 steps. Experimental results demonstrate that REF-VC outperforms baselines such as Seed-VC in zero-shot scenarios on the noisy set, while also performing comparably to Seed-VC on the clean set. In addition, REF-VC can be compatible with singing voice conversion within one model.

eess.AS↗

arXiv2025

Nearest neighbor synthesis of CNOT circuits on general quantum architectures

NISQ devices have inherent limitations in terms of connectivity and hardware noise. The synthesis of CNOT circuits considers the physical constraints and transforms quantum algorithms into low-level quantum circuits that can execute on physical chips correctly. In the current trend, quantum chip architectures without Hamiltonian paths are gradually replacing architectures with Hamiltonian paths due to their scalability and low-noise characteristics. To this end, this paper addresses the nearest neighbor synthesis of CNOT circuits in the architectures with and without Hamiltonian paths, aiming to enhance the fidelity of the circuits after execution. Firstly, a key-qubit priority mapping model for general quantum architectures is proposed. Secondly, the initial mapping is further improved by using tabu search to reduce the number of CNOT gates after circuit synthesis and enhance its fidelity. Finally, the noise-aware CNOT circuit nearest neighbor synthesis algorithm for the general architecture is proposed based on the key-qubit priority mapping model. The algorithm is demonstrated on several popular cloud quantum computing platforms and simulators, showing that it effectively optimizes the fidelity of CNOT circuits compared with mainstream methods. Moreover, the method can be extended to more general circuits, thereby improving the overall performance of quantum computing on NISQ devices.

quant-ph↗

arXiv2025

A Novel Massive Random Access in Cell-Free Massive MIMO Systems for High-Speed Mobility with OTFS Modulation

In the research of next-generation wireless communication technologies, orthogonal time frequency space (OTFS) modulation is emerging as a promising technique for high-speed mobile environments due to its superior efficiency and robustness in doubly selective channels. Additionally, the cell-free architecture, which eliminates the issues associated with cell boundaries, offers broader coverage for radio access networks. By combining cell-free network architecture with OTFS modulation, the system may meet the demands of massive random access required by machine-type communication devices in high-speed scenarios. This paper explores a massive random access scheme based on OTFS modulation within a cell-free architecture. A transceiver model for uplink OTFS signals involving multiple access points (APs) is developed, where channel estimation with fractional channel parameters is approximated as a block sparse matrix recovery problem. Building on existing superimposed and embedded preamble schemes, a hybrid preamble scheme is proposed. This scheme leverages superimposed and embedded preambles to respectively achieve rough and accurate active user equipment (UEs) detection (AUD), as well as precise channel estimation, under the condition of supporting a large number of access UEs. Moreover, this study introduces a generalized approximate message passing and pattern coupling sparse Bayesian learning with Laplacian prior (GAMP-PCSBL-La) algorithm, which effectively captures block sparse features after discrete cosine transform (DCT), delivering precise estimation results with reduced computational complexity. Simulation results demonstrate that the proposed scheme is effective and provides superior performance compared to other existing schemes.

eess.SP↗

arXiv2025

Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis. However, existing foundation models rely on multi-stage processing or complex architectures for predicting multiple codebooks, limiting efficiency and integration flexibility. To overcome these challenges, we introduce Spark-TTS, a novel system powered by BiCodec, a single-stream speech codec that decomposes speech into two complementary token types: low-bitrate semantic tokens for linguistic content and fixed-length global tokens for speaker attributes. This disentangled representation, combined with the Qwen2.5 LLM and a chain-of-thought (CoT) generation approach, enables both coarse-grained control (e.g., gender, speaking style) and fine-grained adjustments (e.g., precise pitch values, speaking rate). To facilitate research in controllable TTS, we introduce VoxBox, a meticulously curated 100,000-hour dataset with comprehensive attribute annotations. Extensive experiments demonstrate that Spark-TTS not only achieves state-of-the-art zero-shot voice cloning but also generates highly customizable voices that surpass the limitations of reference-based synthesis. Source code, pre-trained models, and audio samples are available at https://github.com/SparkAudio/Spark-TTS.

cs.SD↗

arXiv2025

Circuit Partitioning and Transmission Cost Optimization in Distributed Quantum Circuits

Given the limitations on the number of qubits in current noisy intermediate-scale quantum (NISQ) devices, the implementation of large-scale quantum algorithms on such devices is challenging, prompting research into distributed quantum computing. This paper focuses on the issue of excessive communication complexity in distributed quantum computing based on the quantum circuit model. To reduce the number of quantum state transmissions, i.e., the transmission cost, in distributed quantum circuits, a circuit partitioning method based on the Quadratic Unconstrained Binary Optimization (QUBO) model is proposed, coupled with the lookahead method for transmission cost optimization. Initially, the problem of distributed quantum circuit partitioning is transformed into a graph minimum cut problem. The QUBO model, which can be accelerated by quantum annealing algorithms, is introduced to minimize the number of quantum gates between quantum processing units (QPUs) and the transmission cost. Subsequently, the dynamic lookahead strategy for the selection of transmission qubits is proposed to optimize the transmission cost in distributed quantum circuits. Finally, through numerical simulations, the impact of different circuit partitioning indicators on the transmission cost is explored, and the proposed method is evaluated on benchmark circuits. Experimental results demonstrate that the proposed circuit partitioning method has a shorter runtime compared with current circuit partitioning methods. Additionally, the transmission cost optimized by the proposed method is significantly lower than that of current transmission cost optimization methods, achieving noticeable improvements across different numbers of partitions.

quant-ph↗

arXiv2025

Conditional Diffusion-based Parameter Generation for Quantum Approximate Optimization Algorithm

The Quantum Approximate Optimization Algorithm (QAOA) is a hybrid quantum-classical algorithm that shows promise in efficiently solving the MaxCut problem, a representative example of combinatorial optimization. However, its effectiveness heavily depends on the parameter optimization pipeline, where the parameter initialization strategy is nontrivial due to the non-convex and complex optimization landscapes characterized by issues with low-quality local minima. Recent inspiration comes from the diffusion of classical neural network parameters, which has demonstrated that neural network training can benefit from generating good initial parameters through diffusion models. Therefore, in this work, we formulate the problem of finding good initial parameters as a generative task and propose the initial parameter generation scheme through dataset-conditioned pre-trained parameter sampling. Concretely, the generative machine learning model, specifically the denoising diffusion probabilistic model (DDPM), is trained to learn the distribution of pretrained parameters conditioned on the graph dataset. Intuitively, our proposed framework aims at effectively distilling knowledge from pre-trained parameters to generate well-performing initial parameters for QAOA. Compared to random parameter initialization, experiments on various-sized Max-Cut problem instances consistently show that our conditional DDPM is capable of improving the approximation ratio by as much as 14.4%, 11.0%, 11.4% and 7.49%, 8.31%, 6.08% on average for random, regular, and Watts-Strogatz graphs, respectively. Additionally, the experimental results also indicate that the conditional DDPM trained on small problem instances can be extrapolated to larger ones, improving the approximation ratio by up to 28.4% and 12.1% on average.

quant-ph↗

arXiv2025

MacST: Multi-Accent Speech Synthesis via Text Transliteration for Accent Conversion

In accented voice conversion or accent conversion, we seek to convert the accent in speech from one another while preserving speaker identity and semantic content. In this study, we formulate a novel method for creating multi-accented speech samples, thus pairs of accented speech samples by the same speaker, through text transliteration for training accent conversion systems. We begin by generating transliterated text with Large Language Models (LLMs), which is then fed into multilingual TTS models to synthesize accented English speech. As a reference system, we built a sequence-to-sequence model on the synthetic parallel corpus for accent conversion. We validated the proposed method for both native and non-native English speakers. Subjective and objective evaluations further validate our dataset's effectiveness in accent conversion studies.

cs.SD↗

arXiv2024

Passive Integrated Sensing and Communication Scheme based on RF Fingerprint Information Extraction for Cell-Free RAN

This paper investigates how to achieve integrated sensing and communication (ISAC) based on a cell-free radio access network (CF-RAN) architecture with a minimum footprint of communication resources. We propose a new passive sensing scheme. The scheme is based on the radio frequency (RF) fingerprint learning of the RF radio unit (RRU) to build an RF fingerprint library of RRUs. The source RRU is identified by comparing the RF fingerprints carried by the signal at the receiver side. The receiver extracts the channel parameters from the signal and estimates the channel environment, thus locating the reflectors in the environment. The proposed scheme can effectively solve the problem of interference between signals in the same time-frequency domain but in different spatial domains when multiple RRUs jointly serve users in CF-RAN architecture. Simulation results show that the proposed passive ISAC scheme can effectively detect reflector location information in the environment without degrading the communication performance.

eess.SP↗

arXiv2024

Performance Analysis of Local Partial MMSE Precoding Based User-Centric Cell-Free Massive MIMO Systems and Deployment Optimization

Cell-free massive multiple-input multiple-output (MIMO) systems, leveraging tight cooperation among wireless access points, exhibit remarkable signal enhancement and interference suppression capabilities, demonstrating significant performance advantages over traditional cellular networks. This paper investigates the performance and deployment optimization of a user-centric scalable cell-free massive MIMO system with imperfect channel information over correlated Rayleigh fading channels. Based on the large-dimensional random matrix theory, this paper presents the deterministic equivalent of the ergodic sum rate for this system when applying the local partial minimum mean square error (LP-MMSE) precoding method, along with its derivative with respect to the channel correlation matrix. Furthermore, utilizing the derivative of the ergodic sum rate, this paper designs a Barzilai-Borwein based gradient descent method to improve system deployment. Simulation experiments demonstrate that under various parameter settings and large-scale antenna configurations, the deterministic equivalent of the ergodic sum rate accurately approximates the Monte Carlo ergodic sum rate of the system. Furthermore, the deployment optimization algorithm effectively enhances the ergodic sum rate of this system by optimizing the positions of access points.

eess.SP↗

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

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

MGS-SLAM: Monocular Sparse Tracking and Gaussian Mapping with Depth Smooth Regularization

This letter introduces a novel framework for dense Visual Simultaneous Localization and Mapping (VSLAM) based on Gaussian Splatting. Recently, SLAM based on Gaussian Splatting has shown promising results. However, in monocular scenarios, the Gaussian maps reconstructed lack geometric accuracy and exhibit weaker tracking capability. To address these limitations, we jointly optimize sparse visual odometry tracking and 3D Gaussian Splatting scene representation for the first time. We obtain depth maps on visual odometry keyframe windows using a fast Multi-View Stereo (MVS) network for the geometric supervision of Gaussian maps. Furthermore, we propose a depth smooth loss and Sparse-Dense Adjustment Ring (SDAR) to reduce the negative effect of estimated depth maps and preserve the consistency in scale between the visual odometry and Gaussian maps. We have evaluated our system across various synthetic and real-world datasets. The accuracy of our pose estimation surpasses existing methods and achieves state-of-the-art. Additionally, it outperforms previous monocular methods in terms of novel view synthesis and geometric reconstruction fidelities.

cs.CV↗

arXiv2024

Mini-Slot-Assisted Short Packet URLLC:Differential or Coherent Detection?

One of the primary challenges in short packet ultra-reliable and low-latency communications (URLLC) is to achieve reliable channel estimation and data detection while minimizing the impact on latency performance. Given the small packet size in mini-slot-assisted URLLC, relying solely on pilot-based coherent detection is almost impossible to meet the seemingly contradictory requirements of high channel estimation accuracy, high reliability, low training overhead, and low latency. In this paper, we explore differential modulation both in the frequency domain and in the time domain, and propose adopting an adaptive approach that integrates both differential and coherent detection to achieve mini-slot-assisted short packet URLLC, striking a balance among training overhead, system performance, and computational complexity. Specifically, differential (especially in the frequency domain) and coherent detection schemes can be dynamically activated based on application scenarios, channel statistics, information payloads, mini-slot deployment options, and service requirements. Furthermore, we derive the block error rate (BLER) for pilot-based, frequency domain, and time domain differential OFDM using non-asymptotic information-theoretic bounds. Simulation results validate the feasibility and effectiveness of adaptive differential and coherent detection.

cs.IT↗

arXiv2024

DualVC 3: Leveraging Language Model Generated Pseudo Context for End-to-end Low Latency Streaming Voice Conversion

Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms. Nonetheless, the recognition-synthesis framework hinders end-to-end optimization, and the instability of automatic speech recognition (ASR) model with short chunks makes it challenging to further reduce latency. To address these issues, we propose an end-to-end model, DualVC 3. With speaker-independent semantic tokens to guide the training of the content encoder, the dependency on ASR is removed and the model can operate under extremely small chunks, with cascading errors eliminated. A language model is trained on the content encoder output to produce pseudo context by iteratively predicting future frames, providing more contextual information for the decoder to improve conversion quality. Experimental results demonstrate that DualVC 3 achieves comparable performance to DualVC 2 in subjective and objective metrics, with a latency of only 50 ms.

eess.AS↗