arXiv subjects

Ning Ma

Publications and source records attributed to Ning Ma.

At least 55 records · Page 3Linked to original sources

arXiv2022

Auditory-Based Data Augmentation for End-to-End Automatic Speech Recognition

End-to-end models have achieved significant improvement on automatic speech recognition. One common method to improve performance of these models is expanding the data-space through data augmentation. Meanwhile, human auditory inspired front-ends have also demonstrated improvement for automatic speech recognisers. In this work, a well-verified auditory-based model, which can simulate various hearing abilities, is investigated for the purpose of data augmentation for end-to-end speech recognition. By introducing the auditory model into the data augmentation process, end-to-end systems are encouraged to ignore variation from the signal that cannot be heard and thereby focus on robust features for speech recognition. Two mechanisms in the auditory model, spectral smearing and loudness recruitment, are studied on the LibriSpeech dataset with a transformer-based end-to-end model. The results show that the proposed augmentation methods can bring statistically significant improvement on the performance of the state-of-the-art SpecAugment.

eess.AS↗

arXiv2022

Generalizations of Alladi's formula for arithmetical semigroups

In this article, we prove that a general version of Alladi's formula with Dirichlet convolution holds for arithmetical semigroups satisfying Axiom $A$ or Axiom $A^{\#}$. As applications, we apply our main results to certain semigroups coming from algebraic number theory, arithmetical geometry and graph theory, particularly generalizing the results of Wang 2021, Kural et al. 2020 and Duan et al. 2020.

math.NT↗

arXiv2021

Nonsplitting of the Hilbert exact sequence and the principal Chebotarev density theorem

Let $K/k$ be a finite Galois extension of number fields, and let $H_K$ be the Hilbert class field of $K$. We find a way to verify the nonsplitting of the short exact sequence $$1\to Cl_K\to \text{Gal}(H_K/k)\to\text{Gal}(K/k)\to 1$$ by finite calculation. Our method is based on the study of the principal version of the Chebotarev density theorem, which represents the density of the prime ideals of $k$ that factor into the product of principal prime ideals in $K$. We also find explicit equations to express the principal density in terms of the invariants of $K/k$. In particular, we prove that the group structure of the ideal class group of $K$ can be determined by reading the principal densities.

math.NT↗

arXiv2021

Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation

Domain Adaptation has been widely used to deal with the distribution shift in vision, language, multimedia etc. Most domain adaptation methods learn domain-invariant features with data from both domains available. However, such a strategy might be infeasible in practice when source data are unavailable due to data-privacy concerns. To address this issue, we propose a novel adaptation method via hypothesis transfer without accessing source data at adaptation stage. In order to fully use the limited target data, a semi-supervised mutual enhancement method is proposed, in which entropy minimization and augmented label propagation are used iteratively to perform inter-domain and intra-domain alignments. Compared with state-of-the-art methods, the experimental results on three public datasets demonstrate that our method gets up to 19.9% improvements on semi-supervised adaptation tasks.

cs.CV↗

arXiv2021

Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data

Present domain adaptation methods usually perform explicit representation alignment by simultaneously accessing the source data and target data. However, the source data are not always available due to the privacy preserving consideration or bandwidth limitation. Source-free domain adaptation aims to solve the above problem by performing domain adaptation without accessing the source data. The adaptation paradigm is receiving more and more attention in recent years, and multiple works have been proposed for unsupervised source-free domain adaptation. However, without utilizing any supervised signal and source data at the adaptation stage, the optimization of the target model is unstable and fragile. To alleviate the problem, we focus on semi-supervised domain adaptation under source-free setting. More specifically, we propose uncertainty-guided Mixup to reduce the representation's intra-domain discrepancy and perform inter-domain alignment without directly accessing the source data. Finally, we conduct extensive semi-supervised domain adaptation experiments on various datasets. Our method outperforms the recent semi-supervised baselines and the unsupervised variant also achieves competitive performance. The experiment codes will be released in the future.

cs.CV↗

arXiv2021

Seebeck and Nernst effects in topological insulator: the case of strained HgTe

We theoretically study the thermoelectric transport properties of strained HgTe in the topological insulator phase. We developed a model for the system using a Dirac Hamiltonian including the effect of strain induced by the interface between HgTe and the CdTe substrate. The conductivity tensor was explored assuming the electrons are scattered by charge impurities, while the thermopower tensor was addressed using the Mott relation. Seebeck and Nernst responses exhibit remarkable enhancements in comparison with other two-dimensional Dirac materials, such as graphene, germanane, prosphorene and stanene. The intensity of these termoeletric responses, their dependencies with the external perpendicular magnetic field and temperature are also addressed.

cond-mat.mes-hall↗

arXiv2021

Optimising Hearing Aid Fittings for Speech in Noise with a Differentiable Hearing Loss Model

Current hearing aids normally provide amplification based on a general prescriptive fitting, and the benefits provided by the hearing aids vary among different listening environments despite the inclusion of noise suppression feature. Motivated by this fact, this paper proposes a data-driven machine learning technique to develop hearing aid fittings that are customised to speech in different noisy environments. A differentiable hearing loss model is proposed and used to optimise fittings with back-propagation. The customisation is reflected on the data of speech in different noise with also the consideration of noise suppression. The objective evaluation shows the advantages of optimised custom fittings over general prescriptive fittings.

cs.SD↗

arXiv2021

DHASP: Differentiable Hearing Aid Speech Processing

Hearing aids are expected to improve speech intelligibility for listeners with hearing impairment. An appropriate amplification fitting tuned for the listener's hearing disability is critical for good performance. The developments of most prescriptive fittings are based on data collected in subjective listening experiments, which are usually expensive and time-consuming. In this paper, we explore an alternative approach to finding the optimal fitting by introducing a hearing aid speech processing framework, in which the fitting is optimised in an automated way using an intelligibility objective function based on the HASPI physiological auditory model. The framework is fully differentiable, thus can employ the back-propagation algorithm for efficient, data-driven optimisation. Our initial objective experiments show promising results for noise-free speech amplification, where the automatically optimised processors outperform one of the well recognised hearing aid prescriptions.

cs.SD↗

arXiv2020

Accelerating Generalized Benders Decomposition for Wireless Resource Allocation

Generalized Benders decomposition (GBD) is a globally optimal algorithm for mixed integer nonlinear programming (MINLP) problems, which are NP-hard and can be widely found in the area of wireless resource allocation. The main idea of GBD is decomposing an MINLP problem into a primal problem and a master problem, which are iteratively solved until their solutions converge. However, a direct implementation of GBD is time- and memory-consuming. The main bottleneck is the high complexity of the master problem, which increases over the iterations. Therefore, we propose to leverage machine learning (ML) techniques to accelerate GBD aiming at decreasing the complexity of the master problem. Specifically, we utilize two different ML techniques, classification and regression, to deal with this acceleration task. In this way, a cut classifier and a cut regressor are learned, respectively, to distinguish between useful and useless cuts. Only useful cuts are added to the master problem and thus the complexity of the master problem is reduced. By using a resource allocation problem in device-to-device communication networks as an example, we validate that the proposed method can reduce the computational complexity of GBD without loss of optimality and has strong generalization ability. The proposed method is applicable for solving various MINLP problems in wireless networks since the designs are invariant for different problems.

cs.IT↗

arXiv2020

Adaptive-Step Graph Meta-Learner for Few-Shot Graph Classification

Graph classification aims to extract accurate information from graph-structured data for classification and is becoming more and more important in graph learning community. Although Graph Neural Networks (GNNs) have been successfully applied to graph classification tasks, most of them overlook the scarcity of labeled graph data in many applications. For example, in bioinformatics, obtaining protein graph labels usually needs laborious experiments. Recently, few-shot learning has been explored to alleviate this problem with only given a few labeled graph samples of test classes. The shared sub-structures between training classes and test classes are essential in few-shot graph classification. Exiting methods assume that the test classes belong to the same set of super-classes clustered from training classes. However, according to our observations, the label spaces of training classes and test classes usually do not overlap in real-world scenario. As a result, the existing methods don't well capture the local structures of unseen test classes. To overcome the limitation, in this paper, we propose a direct method to capture the sub-structures with well initialized meta-learner within a few adaptation steps. More specifically, (1) we propose a novel framework consisting of a graph meta-learner, which uses GNNs based modules for fast adaptation on graph data, and a step controller for the robustness and generalization of meta-learner; (2) we provide quantitative analysis for the framework and give a graph-dependent upper bound of the generalization error based on our framework; (3) the extensive experiments on real-world datasets demonstrate that our framework gets state-of-the-art results on several few-shot graph classification tasks compared to baselines.

cs.LG↗

arXiv2019

An End-to-End Solution for Effectively Demoting Watermarked Images in Image Search

We propose an end-to-end solution, from watermark feature generation to metric design, for effectively demoting watermarked images surfed by a real world image search engine. We use a few fundamental techniques to obtain effective watermark features of images in the image search index, and utilize the signals in a commercial search engine to improve the image search quality. We collect a diverse and large set (about 1M) of images with human labels indicating whether the image contains visible watermark. We train a few deep convolutional neural networks to extract watermark information from the raw images. The deep CNN classifiers we trained can achieve high accuracy on the watermark test data set. We also analyze the images based on their domains to get watermark information from a domain-based watermark classifier. We design a new novel hybrid metric which includes the relevance, image attractiveness and watermark information all together. We demonstrate that using these watermark signals together with the new metric in image search ranker can significantly demote the watermarked images during the online image ranking.

cs.CV↗

arXiv2019

Deep Learning Features for Robust Detection of Acoustic Events in Sleep-Disordered Breathing

Sleep-disordered breathing (SDB) is a serious and prevalent condition, and acoustic analysis via consumer devices (e.g. smartphones) offers a low-cost solution to screening for it. We present a novel approach for the acoustic identification of SDB sounds, such as snoring, using bottleneck features learned from a corpus of whole-night sound recordings. Two types of bottleneck features are described, obtained by applying a deep autoencoder to the output of an auditory model or a short-term autocorrelation analysis. We investigate two architectures for snore sound detection: a tandem system and a hybrid system. In both cases, a `language model' (LM) was incorporated to exploit information about the sequence of different SDB events. Our results show that the proposed bottleneck features give better performance than conventional mel-frequency cepstral coefficients, and that the tandem system outperforms the hybrid system given the limited amount of labelled training data available. The LM made a small improvement to the performance of both classifiers.

eess.AS↗

arXiv2019

Exploiting Deep Neural Networks and Head Movements for Robust Binaural Localisation of Multiple Sources in Reverberant Environments

This paper presents a novel machine-hearing system that exploits deep neural networks (DNNs) and head movements for robust binaural localisation of multiple sources in reverberant environments. DNNs are used to learn the relationship between the source azimuth and binaural cues, consisting of the complete cross-correlation function (CCF) and interaural level differences (ILDs). In contrast to many previous binaural hearing systems, the proposed approach is not restricted to localisation of sound sources in the frontal hemifield. Due to the similarity of binaural cues in the frontal and rear hemifields, front-back confusions often occur. To address this, a head movement strategy is incorporated in the localisation model to help reduce the front-back errors. The proposed DNN system is compared to a Gaussian mixture model (GMM) based system that employs interaural time differences (ITDs) and ILDs as localisation features. Our experiments show that the DNN is able to exploit information in the CCF that is not available in the ITD cue, which together with head movements substantially improves localisation accuracies under challenging acoustic scenarios in which multiple talkers and room reverberation are present.

eess.AS↗

arXiv2019

Robust Binaural Localization of a Target Sound Source by Combining Spectral Source Models and Deep Neural Networks

Despite there being clear evidence for top-down (e.g., attentional) effects in biological spatial hearing, relatively few machine hearing systems exploit top-down model-based knowledge in sound localisation. This paper addresses this issue by proposing a novel framework for binaural sound localisation that combines model-based information about the spectral characteristics of sound sources and deep neural networks (DNNs). A target source model and a background source model are first estimated during a training phase using spectral features extracted from sound signals in isolation. When the identity of the background source is not available, a universal background model can be used. During testing, the source models are used jointly to explain the mixed observations and improve the localisation process by selectively weighting source azimuth posteriors output by a DNN-based localisation system. To address the possible mismatch between training and testing, a model adaptation process is further employed on-the-fly during testing, which adapts the background model parameters directly from the noisy observations in an iterative manner. The proposed system therefore combines model-based and data-driven information flow within a single computational framework. The evaluation task involved localisation of a target speech source in the presence of an interfering source and room reverberation. Our experiments show that by exploiting model-based information in this way, sound localisation performance can be improved substantially under various noisy and reverberant conditions.

eess.AS↗

arXiv2019

End-to-end Binaural Sound Localisation from the Raw Waveform

A novel end-to-end binaural sound localisation approach is proposed which estimates the azimuth of a sound source directly from the waveform. Instead of employing hand-crafted features commonly employed for binaural sound localisation, such as the interaural time and level difference, our end-to-end system approach uses a convolutional neural network (CNN) to extract specific features from the waveform that are suitable for localisation. Two systems are proposed which differ in the initial frequency analysis stage. The first system is auditory-inspired and makes use of a gammatone filtering layer, while the second system is fully data-driven and exploits a trainable convolutional layer to perform frequency analysis. In both systems, a set of dedicated convolutional kernels are then employed to search for specific localisation cues, which are coupled with a localisation stage using fully connected layers. Localisation experiments using binaural simulation in both anechoic and reverberant environments show that the proposed systems outperform a state-of-the-art deep neural network system. Furthermore, our investigation of the frequency analysis stage in the second system suggests that the CNN is able to exploit different frequency bands for localisation according to the characteristics of the reverberant environment.

cs.SD↗

arXiv2019

An Universal Image Attractiveness Ranking Framework

We propose a new framework to rank image attractiveness using a novel pairwise deep network trained with a large set of side-by-side multi-labeled image pairs from a web image index. The judges only provide relative ranking between two images without the need to directly assign an absolute score, or rate any predefined image attribute, thus making the rating more intuitive and accurate. We investigate a deep attractiveness rank net (DARN), a combination of deep convolutional neural network and rank net, to directly learn an attractiveness score mean and variance for each image and the underlying criteria the judges use to label each pair. The extension of this model (DARN-V2) is able to adapt to individual judge's personal preference. We also show the attractiveness of search results are significantly improved by using this attractiveness information in a real commercial search engine. We evaluate our model against other state-of-the-art models on our side-by-side web test data and another public aesthetic data set. With much less judgments (1M vs 50M), our model outperforms on side-by-side labeled data, and is comparable on data labeled by absolute score.

cs.CV↗

arXiv2018

Rapido: A Layer2 Payment System for Decentralized Currencies

Bitcoin blockchain faces the bitcoin scalability problem, for which bitcoin's blocks contain the transactions on the bitcoin network. The on-chain transaction processing capacity of the bitcoin network is limited by the average block creation time of 10 minutes and the block size limit. These jointly constrain the network's throughput. The transaction processing capacity maximum is estimated between 3.3 and 7 transactions per second (TPS). A Layer2 Network, named Lightning Network, is proposed and activated solutions to address this problem. LN operates on top of the bitcoin network as a cache to allow payments to be affected that are not immediately put on the blockchain. However, it also brings some drawbacks. In this paper, we observe a specific payment issue among current LN, which requires additional claims to blockchain and is time-consuming. We call the issue as shares issue. Therefore, we propose Rapido to explicitly address the shares issue. Furthermore, a new smart contract, D-HTLC, is equipped with Rapido as the payment protocol. We finally provide a proof of concept implementation and simulation for both Rapido and LN, in which Rapdio not only mitigates the shares issue but also mitigates the skewness issue thus is proved to be more applicable for various transactions than LN.

cs.DC↗

arXiv2016

Collective fermion excitation in a warm massless Dirac system

Basing on a self-consistent method, we predict theoretically that there occurs not only a normal (quasi) fermion mode, but also a collective fermion mode, plasmino, in a warm 2D massless Dirac system, especially in a warm intrinsic graphene system. Results of Landau damping show that both fermion and plasmino are well defined modes. We find that there are sharp differences between the discussed system and the QCD/QED system. Firstly, the thermal mass is proportional to $α_g^{3/4}T$ but not $α_g T$. Secondly, at $0 q_c$. Thirdly, the fermion behaves as a "relativity particles" with none zero mass and the plasmino exhibits an anormal dispersion at moderate momentum.

cond-mat.quant-gas↗