arXiv subjects

Jian Wu

Publications and source records attributed to Jian Wu.

At least 271 records · Page 15Linked to original sources

arXiv2023

NMSSM neutralino dark matter for CDF II $W$-boson mass and muon $g-2$ and the promising prospect of direct detection

Two experiments from the Fermilab, E989 and CDF II, have reported two anomalies for muon $g-2$ and $W$-boson mass that may indicate the new physics at the low energy scale. Here we examine the possibility of a common origin of these two anomalies in the Next-to-Minimal Supersymmetric Standard Model. Considering various experimental and astrophysical constraints such as the Higgs mass, collider data, flavor physics, dark matter relic density, and direct detection experiments, we find that lighter electroweakinos and sleptons can generate sufficient contributions to muon $g-2$ and $m_W$. Moreover, the corresponding bino-like neutralino dark matter mass is in the $\sim 180-280$ GeV range. Interestingly, the favored DM mass region can soon be entirely probed by ongoing direct detection experiments like PandaX-4T, XENONnT, LUX-ZEPLIN, and DARWIN.

hep-ph↗

arXiv2023

Speaker Change Detection for Transformer Transducer ASR

Speaker change detection (SCD) is an important feature that improves the readability of the recognized words from an automatic speech recognition (ASR) system by breaking the word sequence into paragraphs at speaker change points. Existing SCD solutions either require additional ensemble for the time based decisions and recognized word sequences, or implement a tight integration between ASR and SCD, limiting the potential optimum performance for both tasks. To address these issues, we propose a novel framework for the SCD task, where an additional SCD module is built on top of an existing Transformer Transducer ASR (TT-ASR) network. Two variants of the SCD network are explored in this framework that naturally estimate speaker change probability for each word, while allowing the ASR and SCD to have independent optimization scheme for the best performance. Experiments show that our methods can significantly improve the F1 score on LibriCSS and Microsoft call center data sets without ASR degradation, compared with a joint SCD and ASR baseline.

eess.AS↗

arXiv2023

ACL-Fig: A Dataset for Scientific Figure Classification

Most existing large-scale academic search engines are built to retrieve text-based information. However, there are no large-scale retrieval services for scientific figures and tables. One challenge for such services is understanding scientific figures' semantics, such as their types and purposes. A key obstacle is the need for datasets containing annotated scientific figures and tables, which can then be used for classification, question-answering, and auto-captioning. Here, we develop a pipeline that extracts figures and tables from the scientific literature and a deep-learning-based framework that classifies scientific figures using visual features. Using this pipeline, we built the first large-scale automatically annotated corpus, ACL-Fig, consisting of 112,052 scientific figures extracted from ~56K research papers in the ACL Anthology. The ACL-Fig-Pilot dataset contains 1,671 manually labeled scientific figures belonging to 19 categories. The dataset is accessible at https://huggingface.co/datasets/citeseerx/ACL-fig under a CC BY-NC license.

cs.AI↗

arXiv2023

RL-GA: A Reinforcement Learning-Based Genetic Algorithm for Electromagnetic Detection Satellite Scheduling Problem

The study of electromagnetic detection satellite scheduling problem (EDSSP) has attracted attention due to the detection requirements for a large number of targets. This paper proposes a mixed-integer programming model for the EDSSP problem and a genetic algorithm based on reinforcement learning (RL-GA). Numerous factors that affect electromagnetic detection are considered in the model, such as detection mode, bandwidth, and other factors. The RL-GA embeds a Q-learning method into an improved genetic algorithm, and the evolution of each individual depends on the decision of the agent. Q-learning is used to guide the population search process by choosing evolution operators. In this way, the search information can be effectively used by the reinforcement learning method. In the algorithm, we design a reward function to update the Q value. According to the problem characteristics, a new combination of is proposed. The RL-GA also uses an elite individual retention strategy to improve search performance. After that, a task time window selection algorithm (TTWSA) is proposed to evaluate the performance of population evolution. Several experiments are used to examine the scheduling effect of the proposed algorithm. Through the experimental verification of multiple instances, it can be seen that the RL-GA can solve the EDSSP problem effectively. Compared with the state-of-the-art algorithms, the RL-GA performs better in several aspects.

cs.NE↗

arXiv2022

Subcycle resolved strong-field tunneling ionization: Identification of magnetic dipole and electric quadrupole effects

Interaction of a strong laser pulse with matter transfers not only energy but also linear momentum of the photons. Recent experimental advances have made it possible to detect the small amount of linear momentum delivered to the photoelectrons in strong-field ionization of atoms. Linear momentum transfer is a unique signature of the laser-atom interaction beyond its dipolar limit. Here, we present a decomposition of the subcycle time-resolved linear momentum transfer in term of its multipolar components. We show that the magnetic dipole contribution dominates the linear momentum transfer during the dynamical tunneling process while the post-ionization longitudinal momentum transfer in the field-driven motion of the electron in the continuum is primarily governed by the electric quadrupole interaction. Alternatively, exploiting the radiation gauge, we identify nondipole momentum transfer effects that scale either linearly or quadratically with the coupling to the laser field. The present results provide detailed insights into the physical mechanisms underlying the subcycle linear momentum transfer induced by nondipole effects.

physics.atom-ph↗

arXiv2022

CTT-Net: A Multi-view Cross-token Transformer for Cataract Postoperative Visual Acuity Prediction

Surgery is the only viable treatment for cataract patients with visual acuity (VA) impairment. Clinically, to assess the necessity of cataract surgery, accurately predicting postoperative VA before surgery by analyzing multi-view optical coherence tomography (OCT) images is crucially needed. Unfortunately, due to complicated fundus conditions, determining postoperative VA remains difficult for medical experts. Deep learning methods for this problem were developed in recent years. Although effective, these methods still face several issues, such as not efficiently exploring potential relations between multi-view OCT images, neglecting the key role of clinical prior knowledge (e.g., preoperative VA value), and using only regression-based metrics which are lacking reference. In this paper, we propose a novel Cross-token Transformer Network (CTT-Net) for postoperative VA prediction by analyzing both the multi-view OCT images and preoperative VA. To effectively fuse multi-view features of OCT images, we develop cross-token attention that could restrict redundant/unnecessary attention flow. Further, we utilize the preoperative VA value to provide more information for postoperative VA prediction and facilitate fusion between views. Moreover, we design an auxiliary classification loss to improve model performance and assess VA recovery more sufficiently, avoiding the limitation by only using the regression metrics. To evaluate CTT-Net, we build a multi-view OCT image dataset collected from our collaborative hospital. A set of extensive experiments validate the effectiveness of our model compared to existing methods in various metrics. Code is available at: https://github.com/wjh892521292/Cataract OCT.

eess.IV↗

arXiv2022

Construction and Validation of a Geometry-based Mathematical Model for the Hard X-ray Imager

Quantitative and analytical analysis of modulation process of the collimator is a great challenge, and is also of great value to the design and development of Fourier transform imaging telescopes. The Hard X-ray Imager (HXI), as one of the three payloads onboard the Advanced Space-based Solar Observatory(ASO-S) mission, adopts modulating Fourier-Transformation imaging technique and will be used to explore mechanism of energy release and transmission in solar flare activities. As an important step to reconstruct the images of solar flares, accurate modulation functions of HXI are needed. In this paper, a mathematical model is developed to analyze the modulation function under a simplified condition first. Then its behavior under six degrees of freedom is calculated after adding the rotation matrix and translation change to the model. In addition, unparalleled light and extended sources also are considered so that our model can be used to analyze the X-ray beam experiment. Next, applied to the practical HXI conditions, the model has been confirmed not only by Geant4 simulations but also by some verification experiments. Furthermore, how this model helps to improve the image reconstruction process after the launch of ASO-S is also presented.

astro-ph.IM↗

arXiv2022

Speech separation with large-scale self-supervised learning

Self-supervised learning (SSL) methods such as WavLM have shown promising speech separation (SS) results in small-scale simulation-based experiments. In this work, we extend the exploration of the SSL-based SS by massively scaling up both the pre-training data (more than 300K hours) and fine-tuning data (10K hours). We also investigate various techniques to efficiently integrate the pre-trained model with the SS network under a limited computation budget, including a low frame rate SSL model training setup and a fine-tuning scheme using only the part of the pre-trained model. Compared with a supervised baseline and the WavLM-based SS model using feature embeddings obtained with the previously released 94K hours trained WavLM, our proposed model obtains 15.9% and 11.2% of relative word error rate (WER) reductions, respectively, for a simulated far-field speech mixture test set. For conversation transcription on real meeting recordings using continuous speech separation, the proposed model achieves 6.8% and 10.6% of relative WER reductions over the purely supervised baseline on AMI and ICSI evaluation sets, respectively, while reducing the computational cost by 38%.

eess.AS↗

arXiv2022

Simulating realistic speech overlaps improves multi-talker ASR

Multi-talker automatic speech recognition (ASR) has been studied to generate transcriptions of natural conversation including overlapping speech of multiple speakers. Due to the difficulty in acquiring real conversation data with high-quality human transcriptions, a naïve simulation of multi-talker speech by randomly mixing multiple utterances was conventionally used for model training. In this work, we propose an improved technique to simulate multi-talker overlapping speech with realistic speech overlaps, where an arbitrary pattern of speech overlaps is represented by a sequence of discrete tokens. With this representation, speech overlapping patterns can be learned from real conversations based on a statistical language model, such as N-gram, which can be then used to generate multi-talker speech for training. In our experiments, multi-talker ASR models trained with the proposed method show consistent improvement on the word error rates across multiple datasets.

eess.AS↗

arXiv2022

Self-supervised learning with bi-label masked speech prediction for streaming multi-talker speech recognition

Self-supervised learning (SSL), which utilizes the input data itself for representation learning, has achieved state-of-the-art results for various downstream speech tasks. However, most of the previous studies focused on offline single-talker applications, with limited investigations in multi-talker cases, especially for streaming scenarios. In this paper, we investigate SSL for streaming multi-talker speech recognition, which generates transcriptions of overlapping speakers in a streaming fashion. We first observe that conventional SSL techniques do not work well on this task due to the poor representation of overlapping speech. We then propose a novel SSL training objective, referred to as bi-label masked speech prediction, which explicitly preserves representations of all speakers in overlapping speech. We investigate various aspects of the proposed system including data configuration and quantizer selection. The proposed SSL setup achieves substantially better word error rates on the LibriSpeechMix dataset.

eess.AS↗

arXiv2022

VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition

This paper presents a novel streaming automatic speech recognition (ASR) framework for multi-talker overlapping speech captured by a distant microphone array with an arbitrary geometry. Our framework, named t-SOT-VA, capitalizes on independently developed two recent technologies; array-geometry-agnostic continuous speech separation, or VarArray, and streaming multi-talker ASR based on token-level serialized output training (t-SOT). To combine the best of both technologies, we newly design a t-SOT-based ASR model that generates a serialized multi-talker transcription based on two separated speech signals from VarArray. We also propose a pre-training scheme for such an ASR model where we simulate VarArray's output signals based on monaural single-talker ASR training data. Conversation transcription experiments using the AMI meeting corpus show that the system based on the proposed framework significantly outperforms conventional ones. Our system achieves the state-of-the-art word error rates of 13.7% and 15.5% for the AMI development and evaluation sets, respectively, in the multiple-distant-microphone setting while retaining the streaming inference capability.

eess.AS↗

arXiv2022

Orbits and action changes during star-clump encounters responsible for the origin of exponential discs in dwarf galaxies

Previous studies found that stellar scattering by massive clumps can lead to the formation of exponential profiles in galaxy discs, but details on how a star is moved around have not been fully explained. We use a GADGET-2 simulation where an exponential profile forms from an initially Gaussian disc in about 4 Gyr for a low-mass galaxy like a dwarf irregular. We find that nearly all large angular momentum changes of stars are caused by star-clump encounters with the closest approach less than 0.5 kpc. During star-clump encounters, stars may increase their random motions, resulting in an increase in the average radial and vertical actions of the whole stellar population. The angular momentum change and the radial action change of an individual star are influenced by the direction from which the star approaches a clump. A star initially at a higher galactic radius relative to the scattering clump usually gets pulled inwards and loses its angular momentum during the encounter, and one at a lower radius tends to shift outwards and gains angular momentum. The increase in the radial action is the largest if a star encounters a clump from the azimuthal direction, and is the smallest from a radial approach. The angular momentum change due to encounters has an inward bias when the clump profile has a steep radial decline, and a shallow decline can make the bias outwards. The stellar profile evolution towards an exponential seems to occur regardless of the direction of the bias.

astro-ph.GA↗

arXiv2022

Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarization

This paper describes a speaker diarization model based on target speaker voice activity detection (TS-VAD) using transformers. To overcome the original TS-VAD model's drawback of being unable to handle an arbitrary number of speakers, we investigate model architectures that use input tensors with variable-length time and speaker dimensions. Transformer layers are applied to the speaker axis to make the model output insensitive to the order of the speaker profiles provided to the TS-VAD model. Time-wise sequential layers are interspersed between these speaker-wise transformer layers to allow the temporal and cross-speaker correlations of the input speech signal to be captured. We also extend a diarization model based on end-to-end neural diarization with encoder-decoder based attractors (EEND-EDA) by replacing its dot-product-based speaker detection layer with the transformer-based TS-VAD. Experimental results on VoxConverse show that using the transformers for the cross-speaker modeling reduces the diarization error rate (DER) of TS-VAD by 11.3%, achieving a new state-of-the-art (SOTA) DER of 4.57%. Also, our extended EEND-EDA reduces DER by 6.9% on the CALLHOME dataset relative to the original EEND-EDA with a similar model size, achieving a new SOTA DER of 11.18% under a widely used training data setting.

eess.AS↗

arXiv2022

The Microsoft System for VoxCeleb Speaker Recognition Challenge 2022

In this report, we describe our submitted system for track 2 of the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22). We fuse a variety of good-performing models ranging from supervised models to self-supervised learning(SSL) pre-trained models. The supervised models, trained using VoxCeleb-2 dev data, consist of ECAPA-TDNN and Res2Net in a very deep structure. The SSL pre-trained models, wav2vec and wavLM, are trained using large scale unlabeled speech data up to million hours. These models are cascaded with ECAPA-TDNN and further fine-tuned in a supervised fashion to extract the speaker representations. All 13 models are applied with score normalization and calibration and then fused into the the submitted system. We also explore the audio quality measures in the calibration stage such as duration, SNR, T60, and MOS. The best submitted system achieves 0.073 in minDCF and 1.436% in EER on the VoxSRC-22 evaluation set.

cs.SD↗

arXiv2022

Study of the Global Alignment for the DAMPE Detector

The Dark Matter Particle Explorer (DAMPE) is designed as a high energy particle detector for probing cosmic-rays and $γ-$rays in a wide energy range. The trajectory of the incident particle is mainly measured by the Silicon-Tungsten tracKer-converter (STK) sub-detector, which heavily depends on the precise internal alignment correction as well as the accuracy of the global coordinate system. In this work, we carried out a global alignment method to validate the potential displacement of these sub-detectors, and particularly demonstrated that the track reconstruction of STK can well satisfy the required objectives by means of comparing flight data and simulations.

physics.ins-det↗

arXiv2022

DialMed: A Dataset for Dialogue-based Medication Recommendation

Medication recommendation is a crucial task for intelligent healthcare systems. Previous studies mainly recommend medications with electronic health records (EHRs). However, some details of interactions between doctors and patients may be ignored or omitted in EHRs, which are essential for automatic medication recommendation. Therefore, we make the first attempt to recommend medications with the conversations between doctors and patients. In this work, we construct DIALMED, the first high-quality dataset for medical dialogue-based medication recommendation task. It contains 11,996 medical dialogues related to 16 common diseases from 3 departments and 70 corresponding common medications. Furthermore, we propose a Dialogue structure and Disease knowledge aware Network (DDN), where a QA Dialogue Graph mechanism is designed to model the dialogue structure and the knowledge graph is used to introduce external disease knowledge. The extensive experimental results demonstrate that the proposed method is a promising solution to recommend medications with medical dialogues. The dataset and code are available at https://github.com/f-window/DialMed.

cs.CL↗

arXiv2022

Online Deep Learning from Doubly-Streaming Data

This paper investigates a new online learning problem with doubly-streaming data, where the data streams are described by feature spaces that constantly evolve, with new features emerging and old features fading away. The challenges of this problem are two folds: 1) Data samples ceaselessly flowing in may carry shifted patterns over time, requiring learners to update hence adapt on-the-fly. 2) Newly emerging features are described by very few samples, resulting in weak learners that tend to make error predictions. A plausible idea to overcome the challenges is to establish relationship between the pre-and-post evolving feature spaces, so that an online learner can leverage the knowledge learned from the old features to better the learning performance on the new features. Unfortunately, this idea does not scale up to high-dimensional media streams with complex feature interplay, which suffers an tradeoff between onlineness (biasing shallow learners) and expressiveness(requiring deep learners). Motivated by this, we propose a novel OLD^3S paradigm, where a shared latent subspace is discovered to summarize information from the old and new feature spaces, building intermediate feature mapping relationship. A key trait of OLD^3S is to treat the model capacity as a learnable semantics, yields optimal model depth and parameters jointly, in accordance with the complexity and non-linearity of the input data streams in an online fashion. Both theoretical analyses and empirical studies substantiate the viability and effectiveness of our proposal.

cs.LG↗

arXiv2022

Multilingual Transformer Language Model for Speech Recognition in Low-resource Languages

It is challenging to train and deploy Transformer LMs for hybrid speech recognition 2nd pass re-ranking in low-resource languages due to (1) data scarcity in low-resource languages, (2) expensive computing costs for training and refreshing 100+ monolingual models, and (3) hosting inefficiency considering sparse traffic. In this study, we present a new way to group multiple low-resource locales together and optimize the performance of Multilingual Transformer LMs in ASR. Our Locale-group Multilingual Transformer LMs outperform traditional multilingual LMs along with reducing maintenance costs and operating expenses. Further, for low-resource but high-traffic locales where deploying monolingual models is feasible, we show that fine-tuning our locale-group multilingual LMs produces better monolingual LM candidates than baseline monolingual LMs.

cs.CL↗