arXiv subjects

Yabo Wang

Publications and source records attributed to Yabo Wang.

12 recordsLinked to original sources

arXiv2026

Towards Ultimate Accuracy in Quantum Multi-Class Classification: A Trace-Distance Binary Tree AdaBoost Classifier

We propose a Trace-distance binary Tree AdaBoost (TTA) multi-class quantum classifier, a practical pipeline for quantum multi-class classification that combines quantum-aware reductions with ensemble learning to improve trainability and resource efficiency. TTA builds a hierarchical binary tree by choosing, at each internal node, the bipartition that maximizes the trace distance between average quantum states; each node trains a binary AdaBoost ensemble of shallow variational quantum base learners. By confining intrinsically hard, small trace distance distinctions to small node-specific datasets and combining weak shallow learners via AdaBoost, TTA distributes capacity across many small submodels rather than one deep circuit, mitigating barren-plateau and optimization failures without sacrificing generalization. Empirically TTA achieves top test accuracy ($\approx $100\%) among quantum and classical baselines, is robust to common quantum errors, and realizes aggregate systems with 10000 cumulative layers and 0.2M parameters, implemented as many shallow circuits. Our results are empirical and implementable on near-term platforms, providing a resource-efficient route to scalable multi-class quantum machine learning.

quant-ph↗

arXiv2025

IPDnet2: an efficient and improved inter-channel phase difference estimation network for sound source localization

IPDnet is our recently proposed real-time sound source localization network. It employs alternating full-band and narrow-band (B)LSTMs to learn the full-band correlation and narrow-band extraction of DP-IPD, respectively, which achieves superior performance. However, processing narrow-band independently incurs high computational complexity and the limited scalability of LSTM layers constrains the localization accuracy. In this work, we extend IPDnet to IPDnet2, improving both localization accuracy and efficiency. IPDnet2 adapts the oSpatialNet as the backbone to enhance spatial cues extraction and provide superior scalability. Additionally, a simple yet effective frequency-time pooling mechanism is proposed to compress frequency and time resolutions and thus reduce computational cost, and meanwhile not losing localization capability. Experimental results show that IPDnet2 achieves comparable localization performance with IPDnet while only requiring less than 2\% of its computation cost. Moreover, the proposed network achieves state-of-the-art SSL performance by scaling up the model size while still maintaining relatively low complexity.

eess.AS↗

arXiv2025

The Manipulative Power of Voice Characteristics: Investigating Deceptive Patterns in Mandarin Chinese Female Synthetic Speech

Pervasive voice interaction enables deceptive patterns through subtle voice characteristics, yet empirical investigation into this manipulation lags behind, especially within major non-English language contexts. Addressing this gap, our study presents the first systematic investigation into voice characteristic-based dark patterns employing female synthetic voices in Mandarin Chinese. This focus is crucial given the prevalence of female personas in commercial assistants and the prosodic significance in the Chinese language. Guided by the conceptual framework identifying key influencing factors, we systematically evaluate effectiveness variations by manipulating voice characteristics (five characteristics, three intensities) across different scenarios (shopping vs. question-answering) with different commercial aims. A preliminary study (N=24) validated the experimental materials and the main study (N=36) revealed significant behavioral manipulation (up to +2027.6%). Crucially, the analysis showed that effectiveness varied significantly with voice characteristics and scenario, mediated by user perception (of tone, intonation, timbre) and user demographics (individual preferences, though limited demographic impact). These interconnected findings offer evidence-based insights for ethical design.

cs.HC↗

arXiv2025

Limitations of Amplitude Encoding on Quantum Classification

It remains unclear whether quantum machine learning (QML) has real advantages when dealing with practical and meaningful tasks. Encoding classical data into quantum states is one of the key steps in QML. Amplitude encoding has been widely used owing to its remarkable efficiency in encoding a number of $2^{n}$ classical data into $n$ qubits simultaneously. However, the theoretical impact of amplitude encoding on QML has not been thoroughly investigated. In this work we prove that under some broad and typical data assumptions, the average of encoded quantum states via amplitude encoding tends to concentrate towards a specific state. This concentration phenomenon severely constrains the capability of quantum classifiers as it leads to a loss barrier phenomenon, namely, the loss function has a lower bound that cannot be improved by any optimization algorithm. In addition, via numerical simulations, we reveal a counterintuitive phenomenon of amplitude encoding: as the amount of training data increases, the training error may increase rather than decrease, leading to reduced decrease in prediction accuracy on new data. Our results highlight the limitations of amplitude encoding in QML and indicate that more efforts should be devoted to finding more efficient encoding strategies to unlock the full potential of QML.

quant-ph↗

arXiv2024

RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization

The training of deep learning-based multichannel speech enhancement and source localization systems relies heavily on the simulation of room impulse response and multichannel diffuse noise, due to the lack of large-scale real-recorded datasets. However, the acoustic mismatch between simulated and real-world data could degrade the model performance when applying in real-world scenarios. To bridge this simulation-to-real gap, this paper presents a new relatively large-scale Real-recorded and annotated Microphone Array speech&Noise (RealMAN) dataset. The proposed dataset is valuable in two aspects: 1) benchmarking speech enhancement and localization algorithms in real scenarios; 2) offering a substantial amount of real-world training data for potentially improving the performance of real-world applications. Specifically, a 32-channel array with high-fidelity microphones is used for recording. A loudspeaker is used for playing source speech signals (about 35 hours of Mandarin speech). A total of 83.7 hours of speech signals (about 48.3 hours for static speaker and 35.4 hours for moving speaker) are recorded in 32 different scenes, and 144.5 hours of background noise are recorded in 31 different scenes. Both speech and noise recording scenes cover various common indoor, outdoor, semi-outdoor and transportation environments, which enables the training of general-purpose speech enhancement and source localization networks. To obtain the task-specific annotations, speaker location is annotated with an omni-directional fisheye camera by automatically detecting the loudspeaker. The direct-path signal is set as the target clean speech for speech enhancement, which is obtained by filtering the source speech signal with an estimated direct-path propagation filter.

cs.SD↗

arXiv2024

IPDnet: A Universal Direct-Path IPD Estimation Network for Sound Source Localization

Extracting direct-path spatial feature is crucial for sound source localization in adverse acoustic environments. This paper proposes the IPDnet, a neural network that estimates direct-path inter-channel phase difference (DP-IPD) of sound sources from microphone array signals. The estimated DP-IPD can be easily translated to source location based on the known microphone array geometry. First, a full-band and narrow-band fusion network is proposed for DP-IPD estimation, in which alternating narrow-band and full-band layers are responsible for estimating the rough DP-IPD information in one frequency band and capturing the frequency correlations of DP-IPD, respectively. Second, a new multi-track DP-IPD learning target is proposed for the localization of flexible number of sound sources. Third, the IPDnet is extend to handling variable microphone arrays, once trained which is able to process arbitrary microphone arrays with different number of channels and array topology. Experiments of multiple-moving-speaker localization are conducted on both simulated and real-world data, which show that the proposed full-band and narrow-band fusion network and the proposed multi-track DP-IPD learning target together achieves excellent sound source localization performance. Moreover, the proposed variable-array model generalizes well to unseen microphone arrays.

eess.AS↗

arXiv2024

Supervised Learning Guarantee for Quantum AdaBoost

In the noisy intermediate-scale quantum (NISQ) era, the capabilities of variational quantum algorithms are greatly constrained due to a limited number of qubits and the shallow depth of quantum circuits. We may view these variational quantum algorithms as weak learners in supervised learning. Ensemble methods are general approaches to combining weak learners to construct a strong one in machine learning. In this paper, by focusing on classification, we theoretically establish and numerically verify a learning guarantee for quantum adaptive boosting (AdaBoost). The supervised-learning risk bound describes how the prediction error of quantum AdaBoost on binary classification decreases as the number of boosting rounds and sample size increase. We further empirically demonstrate the advantages of quantum AdaBoost by focusing on a 4-class classification. The quantum AdaBoost not only outperforms several other ensemble methods, but in the presence of noise it can also surpass the ideally noiseless but unboosted primitive classifier after only a few boosting rounds. Our work indicates that in the current NISQ era, introducing appropriate ensemble methods is particularly valuable in improving the performance of quantum machine learning algorithms.

quant-ph↗

arXiv2024

Power Characterization of Noisy Quantum Kernels

Quantum kernel methods have been widely recognized as one of promising quantum machine learning algorithms that have potential to achieve quantum advantages. In this paper, we theoretically characterize the power of noisy quantum kernels and demonstrate that under global depolarization noise, for different input data the predictions of the optimal hypothesis inferred by the noisy quantum kernel approximately concentrate towards some fixed value. In particular, we depict the convergence rate in terms of the strength of quantum noise, the size of training samples, the number of qubits, the number of layers affected by quantum noises, as well as the number of measurement shots. Our results show that noises may make quantum kernel methods to only have poor prediction capability, even when the generalization error is small. Thus, we provide a crucial warning to employ noisy quantum kernel methods for quantum computation and the theoretical results can also serve as guidelines when developing practical quantum kernel algorithms for achieving quantum advantages.

quant-ph↗

arXiv2023

EHA: Entanglement-variational Hardware-efficient Ansatz for Eigensolvers

Variational quantum eigensolvers (VQEs) are one of the most important and effective applications of quantum computing, especially in the current noisy intermediate-scale quantum (NISQ) era. There are mainly two ways for VQEs: problem-agnostic and problem-specific. For problem-agnostic methods, they often suffer from trainability issues. For problem-specific methods, their performance usually relies upon choices of initial reference states which are often hard to determine. In this paper, we propose an Entanglement-variational Hardware-efficient Ansatz (EHA), and numerically compare it with some widely used ansatzes by solving benchmark problems in quantum many-body systems and quantum chemistry. Our EHA is problem-agnostic and hardware-efficient, especially suitable for NISQ devices and having potential for wide applications. EHA can achieve a higher level of accuracy in finding ground states and their energies in most cases even compared with problem-specific methods. The performance of EHA is robust to choices of initial states and parameters initialization and it has the ability to quickly adjust the entanglement to the required amount, which is also the fundamental reason for its superiority.

quant-ph↗

arXiv2023

FN-SSL: Full-Band and Narrow-Band Fusion for Sound Source Localization

Extracting direct-path spatial features is critical for sound source localization in adverse acoustic environments. This paper proposes a full-band and narrow-band fusion network for estimating direct-path inter-channel phase difference (DP-IPD) from microphone signals. The alternating full-band and narrow-band layers are responsible for learning the full-band correlation and narrow-band extraction of DP-IPD, respectively. Experiments show that the proposed network noticeably outperforms other advanced methods on both simulated and real-world data.

eess.AS↗

arXiv2023

Trainability Enhancement of Parameterized Quantum Circuits via Reduced-Domain Parameter Initialization

Parameterized quantum circuits (PQCs) have been widely used as a machine learning model to explore the potential of achieving quantum advantages for various tasks. However, training PQCs is notoriously challenging owing to the phenomenon of plateaus and/or the existence of (exponentially) many spurious local minima. To enhance trainability, in this work we propose an efficient parameter initialization strategy with theoretical guarantees. We prove that by reducing the initial domain of each parameter inversely proportional to the square root of circuit depth, the magnitude of the cost gradient decays at most polynomially with respect to qubit count and circuit depth. Our theoretical results are substantiated through numerical simulations of variational quantum eigensolver tasks. Moreover, we demonstrate that the reduced-domain initialization strategy can protect specific quantum neural networks from exponentially many spurious local minima. Our results highlight the significance of an appropriate parameter initialization strategy, offering insights to enhance the trainability and convergence of variational quantum algorithms.

quant-ph↗

arXiv2021

Physiological-Physical Feature Fusion for Automatic Voice Spoofing Detection

Speaker verification systems have been used in many production scenarios in recent years. Unfortunately, they are still highly prone to different kinds of spoofing attacks such as voice conversion and speech synthesis, etc. In this paper, we propose a new method base on physiological-physical feature fusion to deal with voice spoofing attacks. This method involves feature extraction, a densely connected convolutional neural network with squeeze and excitation block (SE-DenseNet), multi-scale residual neural network with squeeze and excitation block (SE-Res2Net) and feature fusion strategies. We first pre-trained a convolutional neural network using the speaker's voice and face in the video as surveillance signals. It can extract physiological features from speech. Then we use SE-DenseNet and SE-Res2Net to extract physical features. Such a densely connection pattern has high parameter efficiency and squeeze and excitation block can enhance the transmission of the feature. Finally, we integrate the two features into the SE-Densenet to identify the spoofing attacks. Experimental results on the ASVspoof 2019 data set show that our model is effective for voice spoofing detection. In the logical access scenario, our model improves the tandem decision cost function (t-DCF) and equal error rate (EER) scores by 4% and 7%, respectively, compared with other methods. In the physical access scenario, our model improved t-DCF and EER scores by 8% and 10%, respectively.

eess.AS↗