arXiv subjects

Yuhong Yang

Publications and source records attributed to Yuhong Yang.

At least 55 records · Page 3Linked to original sources

arXiv2024

Exploring Sentence Type Effects on the Lombard Effect and Intelligibility Enhancement: A Comparative Study of Natural and Grid Sentences

This study explores how sentence types affect the Lombard effect and intelligibility enhancement, focusing on comparisons between natural and grid sentences. Using the Lombard Chinese-TIMIT (LCT) corpus and the Enhanced MAndarin Lombard Grid (EMALG) corpus, we analyze changes in phonetic and acoustic features across different noise levels. Our results show that grid sentences produce more pronounced Lombard effects than natural sentences. Then, we develop and test a normal-to-Lombard conversion model, trained separately on LCT and EMALG corpora. Through subjective and objective evaluations, natural sentences are superior in maintaining speech quality in intelligibility enhancement. In contrast, grid sentences could provide superior intelligibility due to the more pronounced Lombard effect. This study provides a valuable perspective on enhancing speech communication in noisy environments.

cs.SD↗

arXiv2024

Additive-Effect Assisted Learning

It is quite popular nowadays for researchers and data analysts holding different datasets to seek assistance from each other to enhance their modeling performance. We consider a scenario where different learners hold datasets with potentially distinct variables, and their observations can be aligned by a nonprivate identifier. Their collaboration faces the following difficulties: First, learners may need to keep data values or even variable names undisclosed due to, e.g., commercial interest or privacy regulations; second, there are restrictions on the number of transmission rounds between them due to e.g., communication costs. To address these challenges, we develop a two-stage assisted learning architecture for an agent, Alice, to seek assistance from another agent, Bob. In the first stage, we propose a privacy-aware hypothesis testing-based screening method for Alice to decide on the usefulness of the data from Bob, in a way that only requires Bob to transmit sketchy data. Once Alice recognizes Bob's usefulness, Alice and Bob move to the second stage, where they jointly apply a synergistic iterative model training procedure. With limited transmissions of summary statistics, we show that Alice can achieve the oracle performance as if the training were from centralized data, both theoretically and numerically.

stat.ML↗

arXiv2024

On optimality of Mallows model averaging

In the past decades, model averaging (MA) has attracted much attention as it has emerged as an alternative tool to the model selection (MS) statistical approach. Hansen [Econometrica 75 (2007) 1175--1189] introduced a Mallows model averaging (MMA) method with model weights selected by minimizing a Mallows' $C_p$ criterion. The main theoretical justification for MMA is an asymptotic optimality (AOP), which states that the risk/loss of the resulting MA estimator is asymptotically equivalent to that of the best but infeasible averaged model. MMA's AOP is proved in the literature by either constraining weights in a special discrete weight set or limiting the number of candidate models. In this work, it is first shown that under these restrictions, however, the optimal risk of MA becomes an unreachable target, and MMA may converge more slowly than MS. In this background, a foundational issue that has not been addressed is: When a suitably large set of candidate models is considered, and the model weights are not harmfully constrained, can the MMA estimator perform asymptotically as well as the optimal convex combination of the candidate models? We answer this question in both nested and non-nested settings. In the nested setting, we provide finite sample inequalities for the risk of MMA and show that without unnatural restrictions on the candidate models, MMA's AOP holds in a general continuous weight set under certain mild conditions. In the non-nested setting, a sufficient condition and a negative result are established for the achievability of the optimal MA risk. Implications on minimax adaptivity are given as well. The results from simulations back up our theoretical findings.

math.ST↗

arXiv2024

One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications

The prevalent use of commercial and open-source diffusion models (DMs) for text-to-image generation prompts risk mitigation to prevent undesired behaviors. Existing concept erasing methods in academia are all based on full parameter or specification-based fine-tuning, from which we observe the following issues: 1) Generation alternation towards erosion: Parameter drift during target elimination causes alternations and potential deformations across all generations, even eroding other concepts at varying degrees, which is more evident with multi-concept erased; 2) Transfer inability & deployment inefficiency: Previous model-specific erasure impedes the flexible combination of concepts and the training-free transfer towards other models, resulting in linear cost growth as the deployment scenarios increase. To achieve non-invasive, precise, customizable, and transferable elimination, we ground our erasing framework on one-dimensional adapters to erase multiple concepts from most DMs at once across versatile erasing applications. The concept-SemiPermeable structure is injected as a Membrane (SPM) into any DM to learn targeted erasing, and meantime the alteration and erosion phenomenon is effectively mitigated via a novel Latent Anchoring fine-tuning strategy. Once obtained, SPMs can be flexibly combined and plug-and-play for other DMs without specific re-tuning, enabling timely and efficient adaptation to diverse scenarios. During generation, our Facilitated Transport mechanism dynamically regulates the permeability of each SPM to respond to different input prompts, further minimizing the impact on other concepts. Quantitative and qualitative results across ~40 concepts, 7 DMs and 4 erasing applications have demonstrated the superior erasing of SPM. Our code and pre-tuned SPMs are available on the project page https://lyumengyao.github.io/projects/spm.

cs.CV↗

arXiv2024

SE Territory: Monaural Speech Enhancement Meets the Fixed Virtual Perceptual Space Mapping

Monaural speech enhancement has achieved remarkable progress recently. However, its performance has been constrained by the limited spatial cues available at a single microphone. To overcome this limitation, we introduce a strategy to map monaural speech into a fixed simulation space for better differentiation between target speech and noise. Concretely, we propose SE-TerrNet, a novel monaural speech enhancement model featuring a virtual binaural speech mapping network via a two-stage multi-task learning framework. In the first stage, monaural noisy input is projected into a virtual space using supervised speech mapping blocks, creating binaural representations. These blocks synthesize binaural noisy speech from monaural input via an ideal binaural room impulse response. The synthesized output assigns speech and noise sources to fixed directions within the perceptual space. In the second stage, the obtained binaural features from the first stage are aggregated. This aggregation aims to decrease pattern discrepancies between the mapped binaural and original monaural features, achieved by implementing an intermediate fusion module. Furthermore, this stage incorporates the utilization of cross-attention to capture the injected virtual spatial information to improve the extraction of the target speech. Empirical studies highlight the effectiveness of virtual spatial cues in enhancing monaural speech enhancement. As a result, the proposed SE-TerrNet significantly surpasses the recent monaural speech enhancement methods in terms of both speech quality and intelligibility.

eess.AS↗

arXiv2024

Debiased Novel Category Discovering and Localization

In recent years, object detection in deep learning has experienced rapid development. However, most existing object detection models perform well only on closed-set datasets, ignoring a large number of potential objects whose categories are not defined in the training set. These objects are often identified as background or incorrectly classified as pre-defined categories by the detectors. In this paper, we focus on the challenging problem of Novel Class Discovery and Localization (NCDL), aiming to train detectors that can detect the categories present in the training data, while also actively discover, localize, and cluster new categories. We analyze existing NCDL methods and identify the core issue: object detectors tend to be biased towards seen objects, and this leads to the neglect of unseen targets. To address this issue, we first propose an Debiased Region Mining (DRM) approach that combines class-agnostic Region Proposal Network (RPN) and class-aware RPN in a complementary manner. Additionally, we suggest to improve the representation network through semi-supervised contrastive learning by leveraging unlabeled data. Finally, we adopt a simple and efficient mini-batch K-means clustering method for novel class discovery. We conduct extensive experiments on the NCDL benchmark, and the results demonstrate that the proposed DRM approach significantly outperforms previous methods, establishing a new state-of-the-art.

cs.CV↗

arXiv2024

EMALG: An Enhanced Mandarin Lombard Grid Corpus with Meaningful Sentences

This study investigates the Lombard effect, where individuals adapt their speech in noisy environments. We introduce an enhanced Mandarin Lombard grid (EMALG) corpus with meaningful sentences , enhancing the Mandarin Lombard grid (MALG) corpus. EMALG features 34 speakers and improves recording setups, addressing challenges faced by MALG with nonsense sentences. Our findings reveal that in Mandarin, meaningful sentences are more effective in enhancing the Lombard effect. Additionally, we uncover that female exhibit a more pronounced Lombard effect than male when uttering meaningful sentences. Moreover, our results reaffirm the consistency in the Lombard effect comparison between English and Mandarin found in previous research.

cs.SD↗

arXiv2023

Mandarin Lombard Flavor Classification

The Lombard effect refers to individuals' unconscious modulation of vocal effort in response to variations in the ambient noise levels, intending to enhance speech intelligibility. The impact of different decibel levels and types of background noise on Lombard effects remains unclear. Building upon the characteristic of Lombard speech that individuals adjust their speech to improve intelligibility dynamically based on the self-feedback speech, we propose a flavor classification approach for the Lombard effect. We first collected Mandarin Lombard speech under different noise conditions, then simulated self-feedback speech, and ultimately conducted the statistical test on the word correct rate. We found that both SSN and babble noise types result in four distinct categories of Mandarin Lombard speech in the range of 30 to 80 dBA with different transition points.

cs.SD↗

arXiv2023

Pruning Deep Neural Networks from a Sparsity Perspective

In recent years, deep network pruning has attracted significant attention in order to enable the rapid deployment of AI into small devices with computation and memory constraints. Pruning is often achieved by dropping redundant weights, neurons, or layers of a deep network while attempting to retain a comparable test performance. Many deep pruning algorithms have been proposed with impressive empirical success. However, existing approaches lack a quantifiable measure to estimate the compressibility of a sub-network during each pruning iteration and thus may under-prune or over-prune the model. In this work, we propose PQ Index (PQI) to measure the potential compressibility of deep neural networks and use this to develop a Sparsity-informed Adaptive Pruning (SAP) algorithm. Our extensive experiments corroborate the hypothesis that for a generic pruning procedure, PQI decreases first when a large model is being effectively regularized and then increases when its compressibility reaches a limit that appears to correspond to the beginning of underfitting. Subsequently, PQI decreases again when the model collapse and significant deterioration in the performance of the model start to occur. Additionally, our experiments demonstrate that the proposed adaptive pruning algorithm with proper choice of hyper-parameters is superior to the iterative pruning algorithms such as the lottery ticket-based pruning methods, in terms of both compression efficiency and robustness.

cs.LG↗

arXiv2023

PCNN: A Lightweight Parallel Conformer Neural Network for Efficient Monaural Speech Enhancement

Convolutional neural networks (CNN) and Transformer have wildly succeeded in multimedia applications. However, more effort needs to be made to harmonize these two architectures effectively to satisfy speech enhancement. This paper aims to unify these two architectures and presents a Parallel Conformer for speech enhancement. In particular, the CNN and the self-attention (SA) in the Transformer are fully exploited for local format patterns and global structure representations. Based on the small receptive field size of CNN and the high computational complexity of SA, we specially designed a multi-branch dilated convolution (MBDC) and a self-channel-time-frequency attention (Self-CTFA) module. MBDC contains three convolutional layers with different dilation rates for the feature from local to non-local processing. Experimental results show that our method performs better than state-of-the-art methods in most evaluation criteria while maintaining the lowest model parameters.

eess.AS↗

arXiv2023

Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation

Acoustic echo cancellation (AEC) aims to remove interference signals while leaving near-end speech least distorted. As the indistinguishable patterns between near-end speech and interference signals, near-end speech can't be separated completely, causing speech distortion and interference signals residual. We observe that besides target positive information, e.g., ground-truth speech and features, the target negative information, such as interference signals and features, helps make pattern of target speech and interference signals more discriminative. Therefore, we present a novel AEC model encoder-decoder architecture with the guidance of negative information termed as CMNet. A collaboration module (CM) is designed to establish the correlation between the target positive and negative information in a learnable manner via three blocks: target positive, target negative, and interactive block. Experimental results demonstrate our CMNet achieves superior performance than recent methods.

eess.AS↗

arXiv2023

CQNV: A combination of coarsely quantized bitstream and neural vocoder for low rate speech coding

Recently, speech codecs based on neural networks have proven to perform better than traditional methods. However, redundancy in traditional parameter quantization is visible within the codec architecture of combining the traditional codec with the neural vocoder. In this paper, we propose a novel framework named CQNV, which combines the coarsely quantized parameters of a traditional parametric codec to reduce the bitrate with a neural vocoder to improve the quality of the decoded speech. Furthermore, we introduce a parameters processing module into the neural vocoder to enhance the application of the bitstream of traditional speech coding parameters to the neural vocoder, further improving the reconstructed speech's quality. In the experiments, both subjective and objective evaluations demonstrate the effectiveness of the proposed CQNV framework. Specifically, our proposed method can achieve higher quality reconstructed speech at 1.1 kbps than Lyra and Encodec at 3 kbps.

cs.SD↗

arXiv2023

A Snoring Sound Dataset for Body Position Recognition: Collection, Annotation, and Analysis

Obstructive Sleep Apnea-Hypopnea Syndrome (OSAHS) is a chronic breathing disorder caused by a blockage in the upper airways. Snoring is a prominent symptom of OSAHS, and previous studies have attempted to identify the obstruction site of the upper airways by snoring sounds. Despite some progress, the classification of the obstruction site remains challenging in real-world clinical settings due to the influence of sleep body position on upper airways. To address this challenge, this paper proposes a snore-based sleep body position recognition dataset (SSBPR) consisting of 7570 snoring recordings, which comprises six distinct labels for sleep body position: supine, supine but left lateral head, supine but right lateral head, left-side lying, right-side lying and prone. Experimental results show that snoring sounds exhibit certain acoustic features that enable their effective utilization for identifying body posture during sleep in real-world scenarios.

cs.SD↗

arXiv2023

Minimax rates of convergence for nonparametric location-scale models

This paper studies minimax rates of convergence for nonparametric location-scale models, which include mean, quantile and expectile regression settings. Under Hellinger differentiability on the error distribution and other mild conditions, we show that the minimax rate of convergence for estimating the regression function under the squared $L_2$ loss is determined by the metric entropy of the nonparametric function class. Different error distributions, including asymmetric Laplace distribution, asymmetric connected double truncated gamma distribution, connected normal-Laplace distribution, Cauchy distribution and asymmetric normal distribution are studied as examples. Applications on low order interaction models and multiple index models are also given.

math.ST↗

arXiv2023

All Information is Necessary: Integrating Speech Positive and Negative Information by Contrastive Learning for Speech Enhancement

Monaural speech enhancement (SE) is an ill-posed problem due to the irreversible degradation process. Recent methods to achieve SE tasks rely solely on positive information, e.g., ground-truth speech and speech-relevant features. Different from the above, we observe that the negative information, such as original speech mixture and speech-irrelevant features, are valuable to guide the SE model training procedure. In this study, we propose a SE model that integrates both speech positive and negative information for improving SE performance by adopting contrastive learning, in which two innovations have consisted. (1) We design a collaboration module (CM), which contains two parts, contrastive attention for separating relevant and irrelevant features via contrastive learning and interactive attention for establishing the correlation between both speech features in a learnable and self-adaptive manner. (2) We propose a contrastive regularization (CR) built upon contrastive learning to ensure that the estimated speech is pulled closer to the clean speech and pushed far away from the noisy speech in the representation space by integrating self-supervised models. We term the proposed SE network with CM and CR as CMCR-Net. Experimental results demonstrate that our CMCR-Net achieves comparable and superior performance to recent approaches.

eess.AS↗

arXiv2023

Implementing Active Learning in Cybersecurity: Detecting Anomalies in Redacted Emails

Research on email anomaly detection has typically relied on specially prepared datasets that may not adequately reflect the type of data that occurs in industry settings. In our research, at a major financial services company, privacy concerns prevented inspection of the bodies of emails and attachment details (although subject headings and attachment filenames were available). This made labeling possible anomalies in the resulting redacted emails more difficult. Another source of difficulty is the high volume of emails combined with the scarcity of resources making machine learning (ML) a necessity, but also creating a need for more efficient human training of ML models. Active learning (AL) has been proposed as a way to make human training of ML models more efficient. However, the implementation of Active Learning methods is a human-centered AI challenge due to potential human analyst uncertainty, and the labeling task can be further complicated in domains such as the cybersecurity domain (or healthcare, aviation, etc.) where mistakes in labeling can have highly adverse consequences. In this paper we present research results concerning the application of Active Learning to anomaly detection in redacted emails, comparing the utility of different methods for implementing active learning in this context. We evaluate different AL strategies and their impact on resulting model performance. We also examine how ratings of confidence that experts have in their labels can inform AL. The results obtained are discussed in terms of their implications for AL methodology and for the role of experts in model-assisted email anomaly screening.

cs.HC↗

arXiv2023

Selector-Enhancer: Learning Dynamic Selection of Local and Non-local Attention Operation for Speech Enhancement

Attention mechanisms, such as local and non-local attention, play a fundamental role in recent deep learning based speech enhancement (SE) systems. However, natural speech contains many fast-changing and relatively brief acoustic events, therefore, capturing the most informative speech features by indiscriminately using local and non-local attention is challenged. We observe that the noise type and speech feature vary within a sequence of speech and the local and non-local operations can respectively extract different features from corrupted speech. To leverage this, we propose Selector-Enhancer, a dual-attention based convolution neural network (CNN) with a feature-filter that can dynamically select regions from low-resolution speech features and feed them to local or non-local attention operations. In particular, the proposed feature-filter is trained by using reinforcement learning (RL) with a developed difficulty-regulated reward that is related to network performance, model complexity, and "the difficulty of the SE task". The results show that our method achieves comparable or superior performance to existing approaches. In particular, Selector-Enhancer is potentially effective for real-world denoising, where the number and types of noise are varies on a single noisy mixture.

eess.AS↗

arXiv2022

Multifold Cross-Validation Model Averaging for Generalized Additive Partial Linear Models

Generalized additive partial linear models (GAPLMs) are appealing for model interpretation and prediction. However, for GAPLMs, the covariates and the degree of smoothing in the nonparametric parts are often difficult to determine in practice. To address this model selection uncertainty issue, we develop a computationally feasible model averaging (MA) procedure. The model weights are data-driven and selected based on multifold cross-validation (CV) (instead of leave-one-out) for computational saving. When all the candidate models are misspecified, we show that the proposed MA estimator for GAPLMs is asymptotically optimal in the sense of achieving the lowest possible Kullback-Leibler loss. In the other scenario where the candidate model set contains at least one correct model, the weights chosen by the multifold CV are asymptotically concentrated on the correct models. As a by-product, we propose a variable importance measure to quantify the importances of the predictors in GAPLMs based on the MA weights. It is shown to be able to asymptotically identify the variables in the true model. Moreover, when the number of candidate models is very large, a model screening method is provided. Numerical experiments show the superiority of the proposed MA method over some existing model averaging and selection methods.

stat.ME↗