125 accepted papers
Model merging aims to combine multiple task-specific experts into a single model, but inter-task interference often causes severe degradation, especially when the experts are trained on heterogeneous objectives. Existing data-free methods are practical, yet largely rely on parameter-space heuristics
Unsupervised skill discovery (USD) aims to learn diverse behaviors without reward functions, but often results in task-irrelevant or hazardous behaviors due to uniform exploration. Guided skill discovery (GSD) addresses this issue by incorporating human intent to focus exploration on meaningful regi…
In the realm of multi-agent systems, the challenge of partial observability is a critical barrier to effective coordination and decision-making. Existing approaches, such as belief state estimation and inter-agent communication, often fall short. Belief-based methods are limited by their focus on pa…
The state-transition (decay) matrix governs how fixed-size memory is updated and used, making it a core design in linear attention models. Prior work exploits rank-1 approximations to reduce the cost of constructing decay matrices, but this low-rank constraint also limits the expressive capacity. We…
Linear attention mechanisms have emerged as efficient alternatives to Softmax attention, exhibiting steady improvements in language modeling capabilities driven by increasingly sophisticated designs for decay matrices—though their structural complexity has typically been limited to the Diagonal-Plus…
Neural Architecture Search (NAS) automates the design of Vision Transformer (ViT) architectures. However, the high computational cost of training-based methods has made training-free, zero-cost proxies a key research direction. While existing proxies can estimate model potential, they fail to captur
In multi-view clustering (MVC), complementary and consistent information from multiple views is integrated to improve clustering performance. However, inter-view sample correspondences may be partially missing in practice, making it difficult to learn cross-view consistency, which leads to the parti
With the rising demand for trustworthy AI in clinical practice, strong interpretability is now a critical requirement as well as accuracy. However, the modality gap for medical visual question answering is quite severe when continuous visual signals are forcibly projected into discrete text space fo
Meme is an expressive medium that often conveys rich emotions and intentions. Recent studies have confirmed the critical role of metaphors in meme understanding. However, existing metaphor research heavily relies on manual annotations, and mainstream vision-language models (VLMs) still struggle with
Deformable image registration (DIR) remains a fundamental yet challenging problem in medical image analysis, largely due to the prohibitively high-dimensional deformation space of dense displacement fields and the scarcity of voxel-level supervision. Existing reinforcement learning frameworks often
Model-based reinforcement learning (MBRL) is a crucial approach to enhance the generalization capabilities and improve the sample efficiency of RL algorithms. However, current MBRL methods focus primarily on building world models for single tasks and rarely address generalization across different s
Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences can be expensive and time-consuming, which forms a strong bar…
Spiking Neural Networks (SNNs) offer an energy--efficient route to 3D spatio--temporal perception, yet they lag behind Artificial Neural Networks (ANNs) due to weak pretraining and heavy inference stacks, limiting generalization and multimodal reasoning (e.g., zero--shot 3D classification and open--…
Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of segmentation foundation models for medical imaging. However, most federated LoRA methods adopt a uniform aggregation rule, which breaks under the encoder–decoder asymmetry in medical segmentation: the encoder is dominated by appea…
Automatic speech recognition (ASR) systems have achieved remarkable performance in common conditions but often struggle to leverage long-context information in contextualized scenarios that require domain-specific knowledge, such as conference presentations. This challenge arises primarily due to co
While Vision Language Models (VLMs) have demonstrated remarkable capabilities in general visual understanding, their application in the chemical domain has been limited, with previous works predominantly focusing on text and thus overlooking critical visual information, such as molecular structures.
In organic reaction prediction, many recent approaches ranging from traditional task-specific models to Large Language Models (LLMs), have demonstrated notable success. However, these methods are inherently data-driven, exhibit constrained interpretability, and have hit fundamental performance bottl…
Recent developments in Multimodal Large Language Models (MLLMs) have significantly improved Vision–Language (VL) reasoning in 2D domains. However, extending these capabilities to 3D scene understanding remains a major challenge. Existing 3D Multimodal Large Language Models (3D-MLLMs) often depend on…
Novel view synthesis from monocular videos of dynamic scenes with unknown camera poses remains a fundamental challenge in computer vision and graphics. While recent advances in 3D representations such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown promising results for…
Text-to-SQL is a technology that converts natural language questions into executable SQL queries, allowing users to query and manage relational databases more easily. In recent years, large language models have significantly advanced the development of text-to-SQL. However, existing methods often ov…
Preference-based reinforcement learning (PbRL) bypasses explicit reward engineering by inferring reward functions from human preference comparisons, enabling better alignment with human intentions. However, humans often struggle to label a clear preference between similar segments, reducing label ef…
Recent advancements in Large Language Models (LLMs) have driven growing interest in LLM-based agents for complex planning tasks. To avoid costly agent training, many studies adopted memory mechanism that enhances LLM with offline experiences or online trajectory analysis. However, existing works foc
Conditional semantic textual similarity (C-STS) assesses the similarity between pairs of sentence representations under different conditions. The current method encounters the over-estimation issue of positive and negative samples. Specifically, the similarity within positive samples is excessively…
Multi-modal representation is faithful and highly effective in describing real-world data samples' characteristics by describing their complementary information. However, the collected data often exhibits incomplete and misaligned characteristics due to factors such as inconsistent sensor frequencie
Comprehending natural language and following human instructions are critical capabilities for intelligent agents. However, the flexibility of linguistic instructions induces substantial ambiguity across language-conditioned tasks, severely degrading algorithmic performance. To address these limitat…
Text-to-SQL is the task of translating natural language questions into SQL queries based on relational databases. Different databases implement their own SQL dialects, leading to variations in syntax. As a result, SQL queries designed for one database may not execute properly in another, creating a
Recently, multi-view data has gradually attracted attention. However, real-world applications often face Partial View-aligned Problem (PVP) and Partially Sample-missing Problem (PSP) due to data loss or corruption. Existing methods addressing PVP typically focus only on learning from the information
With the development of wearable cardiac ultrasound devices, it is no longer sufficient to solely rely on doctors for diagnosing long-term echocardiogram videos. Automated diagnosis of echocardiogram videos has now become a research hotspot. Existing studies only analyze echocardiogram video through
Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-temporal features. Point clouds are sparse 3D spatial data, which suggests that SNNs should be well-suited for processing them. However, when applying SNNs to point clouds, they often exhibit limited performance and…
Multimodal named entity recognition (MNER) extends traditional named entity recognition (NER) by integrating visual and textual information. However, current methods still face significant challenges due to the text-image mismatch problem. Recent advancements in text-to-image synthesis provide promi…
Exploration in sparse reward environments remains a significant challenge in reinforcement learning, particularly in Contextual Markov Decision Processes (CMDPs), where environments differ across episodes. Existing episodic intrinsic motivation methods for CMDPs primarily rely on count-based approac…
Research in offline reinforcement learning (RL) marks a paradigm shift in RL. However, a critical yet under-investigated aspect of offline RL is determining the subset of the offline dataset, which is used to improve algorithm performance while accelerating algorithm training. Moreover, the size of…
With the prevalence of Large Language Models (LLMs), recent studies have shifted paradigms and leveraged LLMs to tackle the challenging task of Text-to-SQL. Because of the complexity of real world databases, previous works adopt the retrieve-then-generate framework to retrieve relevant database sche…
Large language models (LLMs) demonstrate impressive performance on downstream tasks through in-context learning(ICL). However, there is a significant gap between their performance in Named Entity Recognition (NER) and in fine-tuning methods. We believe this discrepancy is due to inconsistencies in l…
System-incremental log analysis, involves the ongoing training of a model using logs from diverse systems to enable effective resolution of log analysis tasks across an expanding array of systems. Existing continual learning methods, which are based on prompt tuning, have shown challenges in insuffi…
Multimodal hate detection aims to identify hate content across multiple modalities for promoting a harmonious online environment. Despite promising progress, three critical challenges, the absence of implicit hateful cues, the cross-modal-induced hate, and the diversity of hate target groups, inhere…
Due to its effectiveness and efficiency, graph-based multi-view clustering has recently attracted much attention. However, the multi-view data are often incomplete and unpaired in real-world applications as a consequence of data loss or corruption. Although efforts have been made through a series of…
Large Language Models (LLMs) have become essential for offensive language detection, yet their ability to handle annotation disagreement remains underexplored. Disagreement samples, which arise from subjective interpretations, pose a unique challenge due to their ambiguous nature. Understanding how…
Capturing the temporal evolution of Gaussian properties such as position, rotation, and scale is a challenging task due to the vast number of time-varying parameters and the limited photometric data available, which generally results in convergence issues, making it difficult to find an optimal solu…
Prompt compression is increasingly studied for its potential to reduce computational costs and alleviate the burden on language models when processing lengthy prompts. Prior research has assessed token retention and removal by calculating information entropy. However, prompt compression encounters t…
Automated log analysis plays a vital role in software operations, with deep learning methods demonstrating effectiveness for analyzing logs from individual systems. However, existing methods face limitations in efficiency, adaptability, and knowledge preservation in system-incremental log analysis.…
Vanilla spiking neurons are simplified from complex biological neurons with dendrites, soma, and synapses, into single somatic compartments. Due to limitations in performance and training efficiency, vanilla spiking neurons face significant challenges in modeling long sequences. In terms of performa…
Despite recent advances in Multimodal Relation Extraction (MRE), existing datasets and approaches primarily focus on single-image scenarios, overlooking the prevalent real-world cases where relationships are expressed through multiple images alongside text. To address this limitation, we present MRE…
Entropy regularization is widely used to improve policy optimization and encourage exploration in reinforcement learning. By maximizing both the expected return and entropy, the agent aims to succeed at the task while acting as randomly as possible. However, current methods based on policy entropy e
Few-Shot Document-Level Relation Extraction (FSDLRE) aims to develop models capable of generalizing to new categories with minimal support examples. Although Large Language Models (LLMs) demonstrate exceptional In-Context Learning (ICL) capabilities on many few-shot tasks, their performance on FSDLR…
Preference-based reinforcement learning (PbRL) stands out by utilizing human preferences as a direct reward signal, eliminating the need for intricate reward engineering. However, despite its potential, traditional PbRL methods are often constrained by the indistinguishability of segments, which imp
Preference-based reinforcement learning (PbRL) bypasses complex reward engineering by learning rewards directly from human preferences, enabling better alignment with human intentions. However, its effectiveness in multi-stage tasks, where agents sequentially perform sub-tasks (e.g., navigation, gra…
Preference-based reinforcement learning (PbRL) bypasses complex reward engineering by learning from human feedback. However, due to the high cost of obtaining feedback, PbRL typically relies on a limited set of preference-labeled samples. This data scarcity introduces two key inefficiencies: (1) the…
Function calling enables large language models (LLMs) to interact with external systems by leveraging tools and APIs. When faced with multi-step tool usage, LLMs still struggle with tool selection, parameter generation, and tool-chain planning. Existing methods typically rely on manually designing t
Advanced large language models (LLMs) frequently reflect in reasoning chain-of-thoughts (CoTs), where they self-verify the correctness of current solutions and explore alternatives. However, given recent findings that LLMs detect limited errors in CoTs, how reflection contributes to empirical improv…
The task of translating natural language questions into query languages has long been a central focus in semantic parsing. Recent advancements in Large Language Models (LLMs) have significantly accelerated progress in this field. However, existing studies typically focus on a single query language,
Spiking Neural Networks (SNNs) have a low-power advantage but perform poorly in image segmentation tasks. The reason is that directly converting neural networks with complex architectural designs for segmentation tasks into spiking versions leads to performance degradation and non-convergence. To ad…
Detecting fake news in short videos is crucial for combating misinformation. Existing methods utilize topic modeling and co-attention mechanism, overlooking the modality heterogeneity and resulting in suboptimal performance. To address this issue, we introduce Text-Guided Fine-grained Counterfactual…
Multimodal fake news detection has become one of the most crucial issues on social media platforms. Although existing methods have achieved advanced performance, two main challenges persist: (1) Under-performed multimodal news information fusion due to model architecture solidification, and (2) weak…
The rapid development of large language models has greatly advanced human-computer dialogue research. However, applying these models to specialized fields like maternity and infant care often leads to subpar performance due to a lack of domain-specific datasets. To address this problem, we have crea
Offline multi-agent reinforcement learning (MARL) with pre-training paradigm, which uses a large quantity of trajectories for offline pre-training and online deployment, has become fashionable lately. While performing well on various tasks, conventional pre-trained decision-making models based on im…
Sentence representation learning is a fundamental task in NLP. Existing methods use contrastive learning (CL) to learn effective sentence representations, which benefit from high-quality contrastive data but require extensive human annotation. Large language models (LLMs) like ChatGPT and GPT4 can a…
Emotion recognition in conversation (ERC) is essential for dialogue systems to identify the emotions expressed by speakers. Although previous studies have made significant progress, accurate recognition and interpretation of similar fine-grained emotion properly accounting for individual variability…
In recent years, with the vast and rapidly increasing amounts of spoken and textual data, Named Entity Recognition (NER) tasks have evolved into three distinct categories, i.e., text-based NER (TNER), Speech NER (SNER) and Multimodal NER (MNER). However, existing approaches typically require designi…
Much progress has been made in dynamic scene reconstruction by neural rendering techniques. Even if existing methods based on Neural Radiance Field (NeRF) achieve marvelous fidelity, they suffer from either complex camera settings, dense training timestamps, or limited ability to inter- and extrapol…
In current synthetic aperture radar (SAR) object classification, one of the major challenges is the severe overfitting issue due to the limited dataset (few-shot) and noisy data. Considering the advantages of knowledge distillation as a learned label smoothing regularization, this paper proposes a n…
Reinforcement learning (RL) algorithms are typically based on optimizing a Markov Decision Process (MDP) using the optimal Bellman equation. Recent studies have revealed that focusing the optimization of Bellman equations solely on in-sample actions tends to result in more stable optimization, espec…
"In recent years, 2D human pose estimation has made significant progress on public benchmarks. However, many of these approaches face challenges of less applicability in the industrial community due to the large number of parametric quantities and computational overhead. Efficient human pose estimat…
Multi-timestep simulation of brain-inspired Spiking Neural Networks (SNNs) boost memory requirements during training and increase inference energy cost. Current training methods cannot simultaneously solve both training and inference dilemmas. This work proposes a novel Temporal Reversible architect…
Meta-learning has emerged as a prominent technology for few-shot text classification and has achieved promising performance. However, existing methods often encounter difficulties in drawing accurate class prototypes from support set samples, primarily due to probable large intra-class differences a…
"Brain-inspired Spiking Neural Networks (SNNs) have bio-plausibility and low-power advantages over Artificial Neural Networks (ANNs). Applications of SNNs are currently limited to simple classification tasks because of their poor performance. In this work, we focus on bridging the performance gap be…
Vision transformers (ViTs) have been outstanding in multiple dense prediction tasks, including image matting. However, the high computational and training costs of ViTs lead to a bottleneck for applications on low computing power devices. In this paper, we propose a novel transformer-specific knowle…
Recently, multimodal named entity recognition (MNER) has emerged as a vital research area within named entity recognition. However, current MNER datasets and methods are predominantly based on text and a single accompanying image, leaving a significant research gap in MNER scenarios involving multip…
In the domain of multi-agent reinforcement learning (MARL), the limited information availability, complex agent interactions, and individual capabilities among agents often pose a bottleneck for effective decision-making. Previous studies frequently fall short due to insufficient consideration of th…
Various linear complexity models, such as Linear Transformer (LinFormer), State Space Model (SSM), and Linear RNN (LinRNN), have been proposed to replace the conventional softmax attention in Transformer structures. However, the optimal design of these linear models is still an open question. In thi…
Disclaimer: Samples in this paper may be harmful and cause discomfort! Patronizing and condescending language (PCL) is a form of speech directed at vulnerable groups. As an essential branch of toxic language, this type of language exacerbates conflicts and confrontations among Internet communities a…
Performance of trimap-free image matting methods is limited when trying to decouple the deterministic and undetermined regions, especially in the scenes where foregrounds are semantically ambiguous, chromaless, or high transmittance. In this paper, we propose a novel framework named Privileged Prior…
Temporal knowledge graph completion is a critical task within the knowledge graph domain. Existing approaches encompass deep neural network-based methods for temporal knowledge graph embedding and rule-based logical symbolic reasoning. However, the former may not adequately account for structural de…
Neuromorphic computing, which exploits Spiking Neural Networks (SNNs) on neuromorphic chips, is a promising energy-efficient alternative to traditional AI. CNN-based SNNs are the current mainstream of neuromorphic computing. By contrast, no neuromorphic chips are designed especially for Transformer-…
Brain-inspired Spiking Neural Network (SNN) has demonstrated its effectiveness and efficiency in vision, natural language, and speech understanding tasks, indicating their capacity to “see”, “listen”, and “read”. In this paper, we design SpikeVoice, which performs high-quality Text-To-Speech (TTS) v…
Researchers have attempted to mitigate lexical bias in toxic language detection (TLD). However, existing methods fail to disentangle the “useful” and “misleading” impact of lexical bias on model decisions. Therefore, they do not effectively exploit the positive effects of the bias and lead to a degr…
Reasoning over the Temporal Knowledge Graph (TKG) that predicts facts in the future has received much attention. Most previous works attempt to model temporal dynamics with knowledge graphs and graph convolution networks. However, these methods lack the consideration of high-order interactions betwe…
Harmful memes have proliferated on the Chinese Internet, while research on detecting Chinese harmful memes significantly lags behind due to the absence of reliable datasets and effective detectors. To this end, we present the comprehensive detection of Chinese harmful memes. We introduce ToxiCN MM,…
In unsupervised reinforcement learning, agents traverse a reward-free environment, aiming for rapid generalisation to subsequent tasks. This strategy offers a compelling resolution to the challenges of sample efficiency. Nevertheless, environments are frequently saturated with excessive information.…
Short video fake news detection is crucial for combating the spread of misinformation. Current detection methods tend to aggregate features from individual modalities into multimodal features, overlooking the implicit opinions and the evolving nature of opinions across modalities. In this paper, we…
Enhancing automatic speech recognition (ASR) performance by leveraging additional multimodal information has shown promising results in previous studies. However, most of these works have primarily focused on utilizing visual cues derived from human lip motions. In fact, context-dependent visual and…
Video question answering involves understanding video content to generate accurate answers to questions. Recent studies have successfully modeled video features and achieved diverse multimodal interaction, yielding impressive outcomes. However, they have overlooked the fact that the video contains r…
We propose a novel visual-inertial odometry (VIO) initialization method, which decouples rotation and translation estimation, and achieves higher efficiency and better robustness. Existing loosely-coupled VIO-initialization methods suffer from poor stability of visual structure-from-motion (SfM), wh…
The spiking neural network (SNN) using leaky-integrated-and-fire (LIF) neurons has been commonly used in automatic speech recognition (ASR) tasks. However, the LIF neuron is still relatively simple compared to that in the biological brain. Further research on more types of neurons with different sca…
The widespread dissemination of toxic online posts is increasingly damaging to society. However, research on detecting toxic language in Chinese has lagged significantly due to limited datasets. Existing datasets suffer from a lack of fine-grained annotations, such as the toxic type and expressions…
Acquiring dynamics is critical for robot learning and is fundamental to planning and control. This paper concerns two fundamental questions: How can we learn a model that covers massive, diverse robot dynamics? Can we construct a model that lifts the data-collection pain and domain expertise require…
Spiking Neural Networks (SNNs) are well known as a promising energy-efficient alternative to conventional artificial neural networks. Subject to the preconceived impression that SNNs are sparse firing, the analysis and optimization of inherent redundancy in SNNs have been largely overlooked, thus th…
Sarcasm, as a form of irony conveying mockery and contempt, has been widespread in social media such as Twitter and Weibo, where the sarcastic text is commonly characterized as an incongruity between the surface positive and negative situation. Naturally, it has an urgent demand to automatically ide…
Medical Slot Filling (MSF) task aims to convert medical queries into structured information, playing an essential role in diagnosis dialogue systems. However, the lack of sufficient term semantics learning makes existing approaches hard to capture semantically identical but colloquial expressions of…
Neural ordinary differential equations (ODEs) are widely recognized as the standard for modeling physical mechanisms, which help to perform approximate inference in unknown physical or biological environments. In partially observable (PO) environments, how to infer unseen information from raw observ…
Multi-task deep reinforcement learning (DRL) ambitiously aims to train a general agent that masters multiple tasks simultaneously. However, varying learning speeds of different tasks compounding with negative gradients interference makes policy learning inefficient. In this work, we propose PiCor, a…
Experience replay, which stores transitions in a replay memory for repeated use, plays an important role of improving sample efficiency in reinforcement learning. Existing techniques such as reweighted sampling, episodic learning and reverse sweep update further process the information in the replay…
Spiking Neural Networks (SNNs) provide an energy-efficient deep learning option due to their unique spike-based event-driven (i.e., spike-driven) paradigm. In this paper, we incorporate the spike-driven paradigm into Transformer by the proposed Spike-driven Transformer with four unique properties: (…
Most existing portrait matting models either require expensive auxiliary information or try to decompose the task into sub-tasks that are usually resource-hungry. These challenges limit its application on low-power computing devices. In this paper, we propose an ultra-light-weighted portrait matting…
Building a human-machine conversational agent is a core problem in Artificial Intelligence, where knowledge has to be integrated into the model effectively. In this paper, we propose a Multi Domain Knowledge Enhanced Matching Network (MDKEMN) to build retrievalbased dialogue systems that could lever…
Recently, multimodal information extraction from social media posts has gained increasing attention in the natural language processing community. Despite their success, current approaches overestimate the significance of images. In this paper, we argue that different social media posts should consid…
Intense spatiotemporal coupling states frequently appear in robotic tasks, and this coupling enriches the information encapsulated in each state. Taking advantage of historical observations can provide more information about the robot, especially for partially observable Markov decision processes. H
Visual Dialog is a challenging vision-language task since the visual dialog agent needs to answer a series of questions after reasoning over both the image content and dialog history. Though existing methods try to deal with the cross-modal understanding in visual dialog, they are still not enough i…
Nowadays, most methods for end-to-end contextual speech recognition bias the recognition process towards contextual knowledge. Since all-neural contextual biasing methods rely on phrase-level contextual modeling and attention-based relevance modeling, they may suffer from the confusion between simil…
Kinematics and instantaneous kinematics are fundamental in many robotic tasks, such as positioning and collision avoidance. Existing learning methods mainly concern a single robot, and small-scale networks are sufficient for considerable approximation accuracy. A question is: Can we learn a kinemati…
Leveraging line features to improve the accuracy of the SLAM system has been studied in many works. However, making full use of the characteristics of different line features (parallel, non-parallel) to improve the SLAM system is rarely mentioned. In this paper, we designed a VIO system based on poi
Network architectures and learning principles are key in forming complex functions in artificial neural networks (ANNs) and spiking neural networks (SNNs). SNNs are considered the new-generation artificial networks by incorporating more biological features than ANNs, including dynamic spiking neuron…
With the help of deep neural networks (DNNs), deep reinforcement learning (DRL) has achieved great success on many complex tasks, from games to robotic control. Compared to DNNs with partial brain-inspired structures and functions, spiking neural networks (SNNs) consider more biological features, in…
Intelligent medical services have attracted great research interests for providing automated medical consultation. However, the lack of corpora becomes a main obstacle to related research, particularly data from real scenarios. In this paper, we construct RealMedDial, a Chinese medical dialogue data…
Most existing CNN-based salient object detection methods can identify fine-grained segmentation details like hair and animal fur, but often mispredict the salient object due to lack of global contextual information caused by locality convolution layers. The limited training data of the current SOD t…
End-to-end (E2E) models have achieved promising results on multiple speech recognition benchmarks, and shown the potential to become the mainstream. However, the unified structure and the E2E training hamper injecting context information into them for contextual biasing. Though contextual LAS (CLAS)…
Speech-to-text translation (ST), which directly translates the source language speech to the target language text, has attracted intensive attention recently. However, the combination of speech recognition and machine translation in a single model poses a heavy burden on the direct cross-modal cross…
Providing a reliable explanation for clinical diagnosis based on the Electronic Medical Record (EMR) is fundamental to the application of Artificial Intelligence in the medical field. Current methods mostly treat the EMR as a text sequence and provide explanations based on a precise medical knowledg…
An end-to-end speech-to-text translation (ST) takes audio in a source language and outputs the text in a target language. Existing methods are limited by the amount of parallel corpus. Can we build a system to fully utilize signals in a parallel ST corpus? We are inspired by human understanding syst…
Although researches on word embeddings have made great progress in recent years, many tasks in natural language processing are on the sentence level. Thus, it is essential to learn sentence embeddings. Recently, Sentence BERT (SBERT) is proposed to learn embeddings on the sentence level, and it uses…
In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features (e.g., mel-spectrograms or MFCC) as the input, and recognizing b…
Most speech separation methods, trying to separate all channel sources simultaneously, are still far from having enough generalization capabilities for real scenarios where the number of input sounds is usually uncertain and even dynamic. In this work, we employ ideas from auditory attention with tw…
Most existing human matting algorithms tried to separate pure human-only foreground from the background. In this paper, we propose a Virtual Multi-modality Foreground Matting (VMFM) method to learn human-object interactive foreground (human and objects interacted with him or her) from a raw RGB imag…
In the speaker extraction problem, it is found that additional information from the target speaker contributes to the tracking and extraction of the target speaker, which includes voiceprint, lip movement, facial expression, and spatial information. However, no one cares for the cue of sound onset,…
In this paper, we propose a novel soft and monotonic alignment mechanism used for sequence transduction. It is inspired by the integrate-and-fire model in spiking neural networks and employed in the encoder-decoder framework consists of continuous functions, thus being named as: Continuous Integrate…
Vision is often used as a complementary modality for audio speech recognition (ASR), especially in the noisy environment where performance of solo audio modality significantly deteriorates. After combining visual modality, ASR is upgraded to the multi-modality speech recognition (MSR). In this paper…
Emotion recognition in textual conversations (ERTC) plays an important role in a wide range of applications, such as opinion mining, recommender systems, and so on. ERTC, however, is a challenging task. For one thing, speakers often rely on the context and commonsense knowledge to express emotions;…
Spiking Neural Network (SNN) is considered more biologically plausible and energy-efficient on emerging neuromorphic hardware. Recently backpropagation algorithm has been utilized for training SNN, which allows SNN to go deeper and achieve higher performance. However, most existing SNN models for ob…
Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on one-to-many sequence transduction problems, such as extracting multiple sequential sources from a mixture sequence.…
Self-attention network, an attention-based feedforward neural network, has recently shown the potential to replace recurrent neural networks (RNNs) in a variety of NLP tasks. However, it is not clear if the self-attention network could be a good alternative of RNNs in automatic speech recognition (A…
This paper presents a general framework for model-based 3D face reconstruction from a single image, which can incorporate mature face alignment methods and utilize their properties. In the proposed framework, the final model parameters, i.e., mostly including pose, identity and expression, are achie…
In this paper, we propose a speaker-independent multi-speaker monaural speech separation system (CBLDNN-GAT) based on convolutional, bidirectional long short-term memory, deep feedforward neural network (CBLDNN) with generative adversarial training (GAT). Our system aims at obtaining better speech q…
Recurrent sequence-to-sequence models using encoder-decoder architecture have made great progress in speech recognition task. However, they suffer from the drawback of slow training speed because the internal recurrence limits the training parallelization. In this paper, we present the Speech-Transf…
In this paper, we target improving the accuracy of acoustic modelling for statistical parametric speech synthesis (SPSS) and introduce the convolutional neural network (CNN) due to its powerful capacity in locality modelling. A novel model architecture combining unidirectional long short-term memory…
Though recurrent neural networks (RNNs) using long short-term memory (LSTM) units can address the issue of long-span dependencies across the linguistic inputs and have achieved the state-of-the-art performance for statistical parametric speech synthesis (SPSS), another limitation of the intrinsic un…