156 accepted papers
Selective State Space Models (SSMs) such as Mamba have emerged as efficient alternatives to Transformers, achieving linear complexity through input-dependent parameterization. However, this selectivity transforms the system from linear time-invariant (LTI) to linear parameter-varying (LPV), where in…
UV unwrapping is an essential task in computer graphics, enabling various visual editing operations in rendering pipelines. However, existing UV unwrapping methods struggle with time-consuming, fragmentation, lack of semanticity, and irregular UV islands, limiting their practical use. An artist-styl…
Vision-based tactile sensors (VBTS) face an inherent trade-off in tactile skin design. Opaque ink markers enable accurate force and tangential displacement estimation but occlude geometric features essential for object and texture classification. Conversely, markerless skins preserve surface details…
Recent advances in dense 3D reconstruction have led to significant progress, yet achieving accurate unified geometric prediction remains a major challenge. Most existing methods are limited to predicting a single geometry quantity from input images. However, geometric quantities such as depth, surfa…
Autoregressive diffusion models (ARDMs) have recently been applied to speech generation, achieving state-of-the-art (SOTA) performance in zero-shot text-to-speech. By autoregressively generating continuous speech tokens with next-token diffusion, these models offer a promising alternative to next-to…
Contact-based grasp generation plays a crucial role in various applications. Recent methods typically focus on the geometric structure of objects, producing grasps with diverse hand poses and plausible contact points. However, these approaches often overlook the physical attributes of the grasp, spe
The recent advancement of Artificial Intelligence Generated Content (AIGC) has led to significant strides in modeling human interaction, particularly in the context of multi-modal dialogue. While current methods impressively generates realistic dialogue in speech and vision modalities, challenges r…
Evaluating long-context language models on natural language conflates architectural capacity to capture dependencies with semantic knowledge and vocabulary statistics. When models fail at long contexts, we cannot determine whether failures stem from fundamental architectural limitations or insuffici…
The high cost and data scarcity in scientific exploration have motivated the use of large language models (LLMs) as knowledge-driven components in Bayesian optimization (BO). However, existing approaches typically embed LLMs directly into the sampling or surrogate modeling pipeline, without fully le…
Physically-based rendering (PBR) materials are fundamental to photorealistic graphics, yet their creation remains labor-intensive and requires specialized expertise. While generative models have advanced material synthesis, existing methods lack a unified representation bridging natural image appear
Reinforcement learning (RL) has demonstrated remarkable success in text and image generation, yet its potential in 3D generation remains largely unexplored. Existing attempts typically rely on offline direct preference optimization (DPO) method, which suffers from low training efficiency and limited
Recent advances in language and vision have demonstrated that scaling up model capacity consistently improves performance across diverse tasks.In 3D visual geometry reconstruction, large-scale training has likewise proven effective for learning versatile representations.However, further scaling of 3
Multi-modal imbalanced cross-source entity alignment aims to identify equivalent entity pairs across multi-modal knowledge graphs (MMKGs) that encompass diverse data sources with imbalanced modality, which poses significant challenges due to the non-uniform distribution of information across differe
Accurate camera–LiDAR fusion relies on precise extrinsic calibration, which fundamentally depends on establishing reliable cross-modal correspondences under potentially large misalignments. Existing learning-based methods typically project LiDAR points into depth maps for feature fusion, which disto
Face relighting aims to synthesize realistic portraits under novel illumination while preserving identity and geometry. However, progress remains constrained by the limited availability of large-scale, physically consistent illumination data. To address this, we introduce POLAR, a large-scale and ph
We introduce Part-X-MLLM, a native 3D multimodal large language model that unifies diverse 3D tasks by formulating them as programs in a structured, executable grammar. Given an RGB point cloud and a natural language prompt, our model autoregressively generates a single, coherent token sequence enco…
Synthesizing physics-grounded 3D assets is a critical bottleneck for interactive virtual worlds and embodied AI. Existing methods predominantly focus on static geometry, overlooking the functional properties essential for interaction. We propose that interactive asset generation must be rooted in fu…
The generation of quadrilateral-dominant meshes is a cornerstone of professional 3D content creation. However, existing generative models generate quad meshes by first generating triangle meshes and then merging triangles into quadrilaterals with some specific rules, which typically produces quad m…
LLM-based search agents are increasingly trained on entity-centric synthetic data to solve complex, knowledge-intensive tasks. However, prevailing training methods like Group Relative Policy Optimization (GRPO) discard this rich entity information, relying instead on sparse, outcome-based rewards. T…
Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models consistently underperform in agentic tasks, particularly in open-sourc…
Vision-Language-Action (VLA) models have emerged as a promising paradigm where pretrained Vision-Language Models (VLMs) serve as System 2 for high-level reasoning, connected to action experts as System 1 for low-level motor control.However, current works fail to genuinely leverage VLM capabilities:
Aligning large generative models with human feedback is a critical challenge. In speech synthesis, this is particularly pronounced due to the lack of a large-scale human preference dataset, which hinders the development of models that truly align with human perception. To address this, we introduce…
Training-free image editing with large diffusion models has become practical, yet faithfully performing complex non-rigid edits (e.g., pose or shape changes) remains highly challenging. We identify a key underlying cause: attention collapse in existing attention sharing mechanisms, where either posi
Real-world knowledge graphs (KGs) contain not only standard triple-based facts, but also more complex, heterogeneous types of facts, such as hyper-relational facts with auxiliary key-value pairs, temporal facts with additional timestamps, and nested facts that imply relationships between facts. Thes
Scientific discovery is increasingly constrained by costly experiments and limited budgets, making efficient optimization essential for AI for science. Bayesian Optimization (BO), while widely adopted for balancing exploration and exploitation, suffers from slow cold-start performance and poor scala…
Robotic pushing is a fundamental manipulation task that requires tactile feedback to capture subtle contact forces and dynamics between the end-effector and the object. However, real tactile sensors often face hardware limitations and deployment challenges, while vision-only policies struggle with s…
Peg-in-hole (PiH) assembly is a fundamental yet challenging robotic manipulation task. While reinforcement learning (RL) has shown promise in tackling such tasks, it requires extensive exploration. In this paper, we propose a novel visual-tactile skill learning framework for the PiH task that levera
Generating 3D shapes at part level is pivotal for downstream applications such as mesh retopology, UV mapping, and 3D printing. However, existing part-based generation methods often lack sufficient controllability and suffer from poor semantically meaningful decomposition. To this end, we introduce
Recently, multi-modal embedding methods have flourished in entity alignment. As state-of-the-art approaches evolve rapidly, visual modality (i.e., images) missing emerges as a critical challenge. While visual modality typically offers the most informative signals in multi-modal entity alignment (MME
The challenge of multimodal semantic segmentation lies in establishing semantically consistent and segmentable multimodal fusion features under conditions of significant visual feature discrepancies. Existing methods commonly construct cross-modal self-attention fusion frameworks or introduce additi…
Modern zero-shot text-to-speech (TTS) systems, despite using extensive pre-training, often struggle in challenging scenarios such as tongue twisters, repeated words, code-switching, and cross-lingual synthesis, leading to intelligibility issues. To address these limitations, this paper leverages pre…
Neural radiance fields have recently revolutionized novel-view synthesis and achieved high-fidelity renderings. However, these methods sacrifice the geometry for the rendering quality, limiting their further applications including relighting and deformation. How to synthesize photo-realistic rende…
We introduce Auto-Connect, a novel approach for automatic rigging that explicitly preserves skeletal connectivity through a connectivity-preserving tokenization scheme. Unlike previous methods that predict bone positions represented as two joints or first predict points before determining connectivi…
Microassembly plays an important role in fabricating complex structures with small basic components in industrial and biomedical fields. Inverted optical microscope could provide high-quality image feedback for microassembly with its continuously improving resolution. However, a compact stage capabl
The physics-informed neural networks (PINNs) are widely applied in solving differential equations. However, few studies have discussed their consistency. In this paper, we consider the consistency of PINNs when applied to second-order elliptic equations with Dirichlet boundary conditions. We first p…
Chemical reactions constitute a cornerstone of fundamental scientific inquiry, yet traditional methodologies and platforms are encumbered by excessive reagent and consumable demands. Emerging alternatives, such as microfluidic systems, while innovative, suffer from intricate fabrication processes an
Molecular Relational Learning (MRL) aims to understand interactions between molecular pairs, playing a critical role in advancing biochemical research. Recently, Large Language Models (LLMs), with their extensive knowledge bases and advanced reasoning capabilities, have emerged as powerful tools for
Driven by the "scale-is-everything" paradigm, modern machine learning increasingly demands ever-larger datasets and models, yielding prohibitive computational and storage requirements. Dataset distillation mitigates this by compressing an original dataset into a small set of synthetic samples, while…
Despite the advancements made in Vision Large Language Models (VLLMs), like text Large Language Models (LLMs), they have limitations in addressing questions that require real-time information or are knowledge-intensive. Indiscriminately adopting Retrieval Augmented Generation (RAG) techniques is an
Several recent studies have attempted to autoregressively generate continuous speech representations without discrete speech tokens by combining diffusion and autoregressive models, yet they often face challenges with excessive computational loads or suboptimal outcomes. In this work, we propose Dif…
The language model (LM) approach based on acoustic and linguistic prompts, such as VALL-E, has achieved remarkable progress in the field of zero-shot audio generation. However, existing methods still have some limitations: 1) repetitions, transpositions, and omissions in the output synthesized speec…
Micro-nano robots must break the symmetry of the flow field to generate net displacement in the low Reynolds number environment. The spherical micro-robots utilize the frictional forces generated through interaction with the surface. We designed a magnetic microroller robot powered by the rotating A
Speech-driven 3D facial animation aims to create lifelike facial expressions that synchronize accurately with speech. Despite significant progress, many existing methods may focus on generating facial animation with a fixed emotional state, neglecting the diverse transformations of facial emotions u
The next-coordinate prediction paradigm has emerged as the de facto standard in current auto-regressive mesh generation methods. Despite their effectiveness, there is no efficient measurement for the various tokenizers that serialize meshes into sequences. In this paper, we introduce a new metric P…
Disentanglement of visual features of primitives (i.e., attributes and objects) has shown exceptional results in Compositional Zero-shot Learning (CZSL). However, due to the feature divergence of an attribute (resp. object) when combined with different objects (resp. attributes), it is challenging t…
Large language models (LLMs) have demonstrated exceptional performance in text generation within current NLP research. However, the lack of factual accuracy is still a dark cloud hanging over the LLM skyscraper. Structural knowledge prompting (SKP) is a prominent paradigm to integrate external knowl…
Vehicle re-identification aims to match vehicles across non-overlapping camera views. Many existing methods extract features from one specific image, and these methods lack view-invariance when comparing vehicles of different orientations. As a result, discriminative parts obscured by viewpoint chan…
Cameras and LiDAR are essential sensors for autonomous vehicles. The fusion of camera and LiDAR data addresses the limitations of individual sensors but relies on precise extrinsic calibration. Recently, numerous end-to-end calibration methods have been proposed; however, most predict extrinsic para
Recent advancements in large language models (LLMs) have significantly improved various natural language processing (NLP) tasks. Typically, LLMs are trained to predict the next token, aligning well with many NLP tasks. However, in knowledge graph (KG) scenarios, entities are the fundamental units an…
Large Language Models (LLMs) often struggle with dynamically changing knowledge and handling unknown static information. Retrieval-Augmented Generation (RAG) is employed to tackle these challenges and has a significant impact on improving LLM performance. In fact, we find that not all questions need
We present a universal theoretical framework for understanding *long-context language modeling* based on a *bipartite* mutual information scaling law that we rigorously verify in natural language. We demonstrate that bipartite mutual information captures multi-token interactions distinct from and sc…
Dialogue serves as the most natural manner of human-computer interaction (HCI). Recent advancements in speech language models (SLM), have significantly enhanced speech-based conversational AI. However, these models are limited to turn-based conversation, lacking the ability to interact with humans i…
We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously curated audio-question-answer triplets, collected from real-world internet videos and refined through ite…
Existing pretrained models for 3D mesh generation often suffer from data biases and produce low-quality results, while global reinforcement learning (RL) methods rely on object-level rewards that struggle to capture local structure details. To address these challenges, we present $\textbf{Mesh-RFT}$…
Molecular Relational Learning (MRL) aims to understand interactions between molecular pairs, playing a critical role in advancing biochemical research. With the recent development of large language models (LLMs), a growing number of studies have explored the integration of MRL with LLMs and achieved…
Generating sewing patterns in garment design is receiving increasing attention due to its CG-friendly and flexible-editing nature. Previous sewing pattern generation methods have been able to produce exquisite clothing, but struggle to design complex garments with detailed control. To address these…
Learning high-quality multi-modal entity representations is an important goal of multi-modal knowledge graph (MMKG) representation learning, which can en- hance reasoning tasks within the MMKGs, such as MMKG completion (MMKGC). The main challenge is to collaboratively model the structural informatio…
The rise of Multi-modal Pre-training highlights the necessity for a unified Multi-Modal Knowledge Graph (MMKG) representation learning framework. Such a framework is essential for embedding structured knowledge into multi-modal Large Language Models effectively, alleviating issues like knowledge mis…
Traditional single-cell mechanical characterization techniques (e.g., atomic force microscopy) often face limitations in throughput, require invasive labeling, or fail to replicate physiological microenvironments, impeding their clinical utility for rapid cancer cell analysis. To address these limit
With the rise of generative models, there is a growing interest in unifying all tasks within a generative framework. Anomaly detection methods also fall into this scope and utilize diffusion models to generate or reconstruct normal samples when given arbitrary anomaly images. However, our study foun…
We propose a compressive yet effective mesh tokenization, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces. BPT compresses mesh sequences by employing block-wise indexing and patch aggregation, reducing their length by approximately 75% compared to…
RGB-T object detection in autonomous driving has been researched increasingly in recent years. Nevertheless, several problems limit the performance of RGB-T fusion perception. Initially, although illumination awareness is a mature technology to guide fusion process, the outputs of previous methods l
Generative models have shown significant achievements in audio generation tasks. However, existing models struggle with complex and detailed prompts, leading to potential performance degradation. We hypothesize that this problem stems from the simplicity and scarcity of the training data. This work…
Generating accurate sounds for complex audio-visual scenes is challenging, especially in the presence of multiple objects and sound sources. In this paper, we propose an interactive object-aware audio generation model that grounds sound generation in user-selected visual objects within images. Our m…
By locally encoding raw data into intermediate features, collaborative inference enables end users to leverage powerful deep learning models without exposure of sensitive raw data to cloud servers. However, recent studies have revealed that these intermediate features may not sufficiently preserve p…
Multi-modal knowledge graph completion (MMKGC) aims to discover unobserved knowledge from given multi-modal knowledge graphs (MMKG), collaboratively leveraging structural information from the triples and multi-modal information of the entities to overcome the inherent incompleteness. Existing MMKGC…
Recent advancements in large audio language models (LALMs) have demonstrated impressive results and promising prospects in universal understanding and reasoning across speech, music, and general sound. However, these models still lack the ability to recognize their knowledge boundaries and refuse to…
Vision-based tactile sensors (VBTSs) provide highresolution tactile images crucial for robot in-hand manipulation. However, force sensing in VBTSs is underutilized due to the costly and time-intensive process of acquiring paired tactile images and force labels. In this study, we introduce a transfer
Multi-modal knowledge graph completion (MMKGC) enhances the structural and semantic richness of knowledge graphs by integrating diverse information across modalities. However, existing methods often either overlook the diversity within a single modality or fail to ensure effective cross-modality ali…
Robotic pushing is a fundamental manipulation task that requires tactile feedback to capture subtle contact forces and dynamics between the end-effector and the object. However, real tactile sensors often face hardware limitations such as high costs and fragility, and deployment challenges involving
Conventional image compression methods are inadequate for intelligent analysis, as they overemphasize pixel-level precision while neglecting semantic significance and the interaction among multiple tasks. This paper introduces a Taskonomy-Aware Multi-Task Compression framework comprising (1) inter-…
3D facial editing a longstanding task in computer vision with broad applications is expected to fast and intuitively manipulate any face from arbitrary viewpoints following the user's will. Existing works have limitations in terms of intuitiveness generalization and efficiency. To overcome these cha…
"Recent advancements in end-to-end image compression demonstrate the potential to surpass traditional codecs regarding rate-distortion performance. However, current methods either prioritize human perceptual quality or solely optimize for one or a few predetermined downstream tasks, neglecting a mor…
Micromanipulation techniques that can achieve controlled fine operations at the micro scale play an important role in biomedical fields including embryo engineering, gene engineering, drug screening, and cell analysis. However, micromanipulation of biological micro-objects, such as cells and micro t…
Despite recent successes in natural language processing and computer vision, Transformer faces scalability issues when processing graphs, e.g., computing the full node-to-node attention on knowledge graphs (KGs) with million of entities is still infeasible. The existing methods mitigate this problem…
Optical tactile sensors provide robots with rich force information for robot grasping in unstructured environments. The fast and accurate calibration of three-dimensional contact forces holds significance for new sensors and existing tactile sensors which may have incurred damage or aging. However,
The generation of molecules with desired properties has become increasingly popular, revolutionizing the way scientists design molecular structures and providing valuable support for chemical and drug design. However, despite the potential of language models in molecule generation, they face challen…
3D-aware GANs successfully solve the problem of 3D-consistency generation and furthermore provide a 3D shape of the generated object. However, the application of the volume renderer disturbs the disentanglement of the latent space, which makes it difficult to manipulate 3D-aware GANs and lowers the…
Binocular 3D human pose estimation (HPE), reconstructing a 3D pose from 2D poses of two views, offers practical advantages by combining multiview geometry with the convenience of a monocular setup. However, compared to a multiview setup, the reduction in the number of cameras increases uncertainty i…
In the era of large language models, applying techniques such as Retrieval Augmented Generation can better address Open-Domain Question-Answering problems. Due to constraints including model sizes and computing resources, the length of context is often limited, and it becomes challenging to empower…
Deploying large language models (LLMs) to real scenarios for domain-specific question answering (QA) is a key thrust for LLM applications, which poses numerous challenges, especially in ensuring that responses are both accommodating to user requirements and appropriately leveraging domain-specific k…
Knowledge Graphs (KGs) are pivotal in various NLP applications but often grapple with incompleteness, especially due to the long-tail problem where infrequent, unpopular relationships drastically reduce the KG completion performance. In this paper, we focus on Few-shot Knowledge Graph Completion (FK…
Large language models (LLMs) have significantly advanced performance across a spectrum of natural language processing (NLP) tasks. Yet, their application to knowledge graphs (KGs), which describe facts in the form of triplets and allow minimal hallucinations, remains an underexplored frontier. In th…
Optical tactile sensors play a pivotal role in robot perception and manipulation tasks. The membrane of these sensors can be painted with markers or remain markerless, enabling them to function in either marker or markerless mode. However, this uni-modal selection means the sensor is only suitable f
Large Language Models (LLMs), with their remarkable task-handling capabilities and innovative outputs, have catalyzed significant advancements across a spectrum of fields. However, their proficiency within specialized domains such as biomolecular studies remains limited. To address this challenge, w…
Inverse rendering methods have achieved remarkable performance in reconstructing high-fidelity 3D objects with disentangled geometries, materials, and environmental light. However, they still face huge challenges in reflective surface reconstruction. Although recent methods model the light trace to…
Despite significant advancements in text generation and reasoning, Large Language Models (LLMs) still face challenges in accurately performing complex arithmetic operations. Language model systems often enable LLMs to generate code for arithmetic operations to achieve accurate calculations. However,…
We propose **Quan**tum-informed **T**ensor **A**daptation (**QuanTA**), a novel, easy-to-implement, fine-tuning method with no inference overhead for large-scale pre-trained language models. By leveraging quantum-inspired methods derived from quantum circuit structures, QuanTA enables efficient *hig…
MaxSAT is an optimization version of the famous NP-complete Satisfiability problem (SAT). Algorithms for MaxSAT mainly include complete solvers and local search incomplete solvers. In many complete solvers, once a better solution is found, a Soft conflict Pseudo Boolean (SPB) constraint will be gene…
Recent embedding-based methods have achieved great successes in exploiting entity alignment from knowledge graph (KG) embeddings of multiple modalities. In this paper, we study embedding-based entity alignment (EEA) from a perspective of generative models. We show that EEA shares similarities with t…
Multi-camera depth estimation has recently garnered significant attention due to its substantial practical implications in the realm of autonomous driving. In this paper, we delve into the task of self-supervised multi-camera depth estimation and propose an innovative framework, STViT, featuring sev…
Temporal Knowledge Graph Question Answering (TKGQA) aims to answer questions with temporal intent over Temporal Knowledge Graphs (TKGs). The core challenge of this task lies in understanding the complex semantic information regarding multiple types of time constraints (e.g., before, first) in questi…
Large-scale vision-language pre-training has achieved significant performance in multi-modal understanding and generation tasks. However, existing methods often perform poorly on image-text matching tasks that require structured representations, i.e., representations of objects, attributes, and rela…
Token-level serialized output training (t-SOT) was recently proposed to address the challenge of streaming multi-talker automatic speech recognition (ASR). T-SOT effectively handles overlapped speech by representing multi-talker transcriptions as a single token stream with ⟨cc⟩ symbols interspersed.…
Partial differential equations (PDEs) are instrumental for modeling dynamical systems in science and engineering. The advent of neural networks has initiated a significant shift in tackling these complexities though challenges in accuracy persist, especially for initial value problems. In this paper…
LiDAR semantic segmentation (LSS) is a critical task in autonomous driving and has achieved promising progress. However prior LSS methods are conventionally investigated and evaluated on datasets within the same domain in clear weather. The robustness of LSS models in unseen scenes and all weather c…
Multi-modal knowledge graph completion (MMKGC) aims to predict the missing triples in the multi-modal knowledge graphs by incorporating structural, visual, and textual information of entities into the discriminant models. The information from different modalities will work together to measure the tr…
Quantum many-body physics simulation has important impacts on understanding fundamental science and has applications to quantum materials design and quantum technology. However, due to the exponentially growing size of the Hilbert space with respect to the particle number, a direct simulation is int…
In recent years, deep learning-based approaches have shown great strength in multi-view stereo because of their outstanding ability to extract robust visual features. However, most learning-based methods need to build the cost volume and increase the receptive field enormously to get a satisfactory…
In recent years, self-supervised learning (SSL) has achieved tremendous success in various speech tasks due to its power to extract representations from massive unlabeled data. However, compared with tasks such as speech recognition (ASR), the improvements from SSL representation in speech separatio…
We introduce a self-supervised learning (SSL) framework BEATs for general audio representation pre-training, where we optimize an acoustic tokenizer and an audio SSL model by iterations. Unlike the previous audio SSL models that employ reconstruction loss for pre-training, our audio SSL model is tra…
Self-supervised learning has been successfully applied to various speech recognition and understanding tasks. However, for generative tasks such as speech enhancement and speech separation, most self-supervised speech representations did not show substantial improvements. To deal with this problem,…
Zero-shot learning (ZSL) aims to predict unseen classes whose samples have never appeared during training. One of the most effective and widely used semantic information for zero-shot image classification are attributes which are annotations for class-level visual characteristics. However, the curre…
Although existing stereo matching models have achieved continuous improvement, they often face issues related to trustworthiness due to the absence of uncertainty estimation. Additionally, effectively leveraging multi-scale and multi-view knowledge of stereo pairs remains unexplored. In this paper,…
The rapid development of Internet of Things (IoT) applications requires efficient computing and communication resource allocation strategies to streamline the existing network operations. These strategies could be formulated as mixed-integer nonlinear programming (MINLP) problems, where the optimal…
Reasoning system dynamics is one of the most important analytical approaches for many scientific studies. With the initial state of a system as input, the recent graph neural networks (GNNs)-based methods are capable of predicting the future state distant in time with high accuracy. Although these m…
In the last decade, researchers have been trying to develop many microrobots that mimic the extraordinary abilities of bionts in complex environments. How to fabricate the biomimetic microrobot with satisfying deformability and complex shapes to realize desired precise motion is the key issue. In th…
Meetings are an essential form of communication for all types of organizations, and remote collaboration systems have been much more widely used since the COVID-19 pandemic. One major issue with remote meetings is that it is challenging for remote participants to interrupt and speak. We have recentl…
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-talke…
Multi-talker automatic speech recognition (ASR) has been studied to generate transcriptions of natural conversation including over-lapping speech of multiple speakers. Due to the difficulty in acquiring real conversation data with high-quality human transcriptions, a naïve simulation of multi-talker…
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 tim…
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…
Automatic target sound extraction (TSE) is a machine learning approach to mimic the human auditory perception capability of attending to a sound source of interest from a mixture of sources. It often uses a model conditioned on a fixed form of target sound clues, such as a sound class label, which l…
In the age of neural natural language processing, there are plenty of works trying to derive interpretations of neural models. Intuitively, when gold rationales exist during training, one can additionally train the model to match its interpretation with the rationales. However, this intuitive idea…
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-agno…
Continuous speech separation (CSS) aims to separate overlapping voices from a continuous influx of conversational audio containing an unknown number of utterances spoken by an unknown number of speakers. A common application scenario is transcribing a meeting conversation recorded by a microphone ar…
In this paper, we propose a Collaboration of Experts (CoE) framework to assemble the expertise of multiple networks towards a common goal. Each expert is an individual network with expertise on a unique portion of the dataset, contributing to the collective capacity. Given a sample, delegator select…
While permutation invariant training (PIT) based continuous speech separation (CSS) significantly improves the conversation transcription accuracy, it often suffers from speech leakages and failures in separation at "hot spot" regions because it has a fixed number of output channels. In this paper,…
Streaming recognition of multi-talker conversations has so far been evaluated only for 2-speaker single-turn sessions. In this paper, we investigate it for multi-turn meetings containing multiple speakers using the Streaming Unmixing and Recognition Transducer (SURT) model, and show that naively ext…
Molecular representation learning contributes to multiple downstream tasks such as molecular property prediction and drug design. To properly represent molecules, graph contrastive learning is a promising paradigm as it utilizes self-supervision signals and has no requirements for human annotations.…
Zebrafish embryo injection is often required in biomedical research using zebrafish. In the injecting operation, trapping and rotating the zebrafish embryo to achieve a proper posture is essential for the high success rate. We proposed an on-chip platform capable of efficient and automatic trapping
With the recent surge of video conferencing tools usage, providing high-quality speech signals and accurate captions have become essential to conduct day-to-day business or connect with friends and families. Single-channel personalized speech enhancement (PSE) methods show promising results compared…
Personalized speech enhancement (PSE) models utilize additional cues, such as speaker embeddings like d-vectors, to remove background noise and interfering speech in real-time and thus improve the speech quality of online video conferencing systems for various acoustic scenarios. In this work, we pr…
"We propose Structural Triangulation, a closed-form solution for optimal 3D human pose considering multi-view 2D pose estimations, calibrated camera parameters, and bone lengths. To start with, we focus on embedding structural constraints of human body in the process of 2D-to-3D inference using tria…
This paper presents Transcribe-to-Diarize, a new approach for neural speaker diarization that uses an end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR). The E2E SA-ASR is a joint model that was recently proposed for speaker counting, multi-talker speech recognition, and speak…
Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years have witnessed great successes in applying self-supervised learning in speech recognition, while limited exploration was attemp…
Continuous speech separation using a microphone array was shown to be promising in dealing with the speech overlap problem in natural conversation transcription. This paper proposes VarArray, an array-geometry-agnostic speech separation neural network model. The proposed model is applicable to any n…
Continuous speech separation was recently proposed to deal with the overlapped speech in natural conversations. While it was shown to significantly improve the speech recognition performance for multichannel conversation transcription, its effectiveness has yet to be proven for a single-channel reco…
With its strong modeling capacity that comes from a multi-head and multi-layer structure, Transformer is a very powerful model for learning a sequential representation and has been successfully applied to speech separation recently. However, multi-channel speech separation sometimes does not necessa…
The continuous speech separation (CSS) is a task to separate the speech sources from a long, partially overlapped recording, which involves a varying number of speakers. A straightforward extension of conventional utterance-level speech separation to the CSS task is to segment the long recording wit…
Zero-shot learning (ZSL) which aims at predicting classes that have never appeared during the training using external knowledge (a.k.a. side information) has been widely investigated. In this paper we present a literature review towards ZSL in the perspective of external knowledge, where we categori…
This paper describes the Microsoft speaker diarization system for monaural multi-talker recordings in the wild, evaluated at the diarization track of the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020. We will first explain our system design to address issues in handling real multi-talker reco…
Recently, an end-to-end speaker-attributed automatic speech recognition (E2E SA-ASR) model was proposed as a joint model of speaker counting, speech recognition and speaker identification for monaural overlapped speech. In the previous study, the model parameters were trained based on the speaker-at…
Modules in all existing speech separation networks can be categorized into single-input-multi-output (SIMO) modules and single-input-single-output (SISO) modules. SIMO modules generate more outputs than input, and SISO modules keep the numbers of input and output the same. While the majority of sepa…
The cooperative relay network is a type of multi-terminal communication system. We present in this paper a Neural Network (NN)-based autoencoder (AE) approach to optimize its design. This approach implements a classical three-node cooperative system as one AE model, and uses a two-stage scheme to tr…
Multi-view stereo is a crucial task in computer vision, that requires accurate and robust photo-consistency among input images for depth estimation. Recent studies have shown that learning-based feature matching and confidence regularization can play a vital role in this task. Nevertheless, how to d…
This paper describes a dataset and protocols for evaluating continuous speech separation algorithms. Most prior speech separation studies use pre-segmented audio signals, which are typically generated by mixing speech utterances on computers so that they fully overlap. Also, the separation algorithm…
Recent studies in deep learning-based speech separation have proven the superiority of time-domain approaches to conventional time-frequency-based methods. Unlike the time-frequency domain approaches, the time-domain separation systems often receive input sequences consisting of a huge number of tim…
An important problem in ad-hoc microphone speech separation is how to guarantee the robustness of a system with respect to the locations and numbers of microphones. The former requires the system to be invariant to different indexing of the microphones with the same locations, while the latter requi…
Deep CNN networks have shown great success in various tasks for text-independent speaker recognition. In this paper, we explore two approaches for modeling long temporal contexts to improve the performance of the ResNet networks. The first approach is simply integrating the utterance-level mean and…
Multi-view stereo (MVS) aims to reconstruct 3D geometry of the target scene by using only information from 2D images. Although much progress has been made, it still suffers from textureless regions. To overcome this difficulty, we propose a mesh-guided MVS method with pyramid architecture, which mak…
Portrait animation, which aims to animate a still portrait to life using poses extracted from target frames, is an important technique for many real-world entertainment applications. Although recent works have achieved highly realistic results on synthesizing or controlling human head images, the pu…
Mobile-edge computing (MEC) is a promising technology to support computation-intensive and delay-sensitive applications at smart devices by offloading their local tasks to the network edge. In this paper, we propose a novel index based real-time task offloading policy for an asynchronous large-scale…
In this paper, we propose an autonomous gait analysis system consisting of a mobile robot and custom-engineered instrumented insoles. The robot is equipped with an on-board RGB-D sensor, the insoles feature inertial sensors and force sensitive resistors. This system is motivated by the need for a ro…
Speaker independent continuous speech separation (SI-CSS) is a task of converting a continuous audio stream, which may contain overlapping voices of unknown speakers, into a fixed number of continuous signals each of which contains no overlapping speech segment. A separated, or cleaned, version of e…
Neural network-based speech separation has received a surge of interest in recent years. Previously proposed methods either are speaker independent or extract a target speaker's voice by using his or her voice snippet. In applications such as home devices or office meeting transcriptions, a possible…
In this study, we develop the keyword spotting (KWS) and acoustic model (AM) components in a far-field speaker system. Specifically, we use teacher-student (T/S) learning to adapt a close-talk well-trained production AM to far-field by using parallel close-talk and simulated far-field data. We also…
Speech separation research has significantly progressed in recent years thanks to the rapid advances in deep learning technology. However the performance of recently proposed single-channel neural network-based speech separation methods is still limited especially in reverberant environments. To pus…
For many computer vision problems, deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, digital images are subject to a wide range of distortions in real application scenarios, while the practical issues regarding i…
Humans and mobile robots will be increasingly cohabiting in the same environments, which has lead to an increase in studies on human robot interaction (HRI). One important topic in these studies is the development of robot navigation algorithms that are socially compliant to humans navigating in the…
Spectrum sensing in heterogeneous networks is very challenging as it usually requires a large number of static secondary users (SUs) to capture the global spectrum states. In this paper, we tackle the spectrum sensing in heterogeneous networks from a new perspective. We exploit the mobility of multi…
This paper describes a neural network approach to far-field speech separation using multiple microphones. Our proposed approach is speaker-independent and can learn to implicitly figure out the number of speakers constituting an input speech mixture. This is realized by utilizing the permutation inv…
We propose a novel adversarial multi-task learning scheme, aiming at actively curtailing the inter-talker feature variability while maximizing its senone discriminability so as to enhance the performance of a deep neural network (DNN) based ASR system. We call the scheme speaker-invariant training (…
Despite the overwhelming success of deep learning in various speech processing tasks, the problem of separating simultaneous speakers in a mixture remains challenging. Two major difficulties in such systems are the arbitrary source permutation and unknown number of sources in the mixture. We propose…
Deep clustering is the first method to handle general audio separation scenarios with multiple sources of the same type and an arbitrary number of sources, performing impressively in speaker-independent speech separation tasks. However, little is known about its effectiveness in other challenging si…
We address the problem of "cocktail-party" source separation in a deep learning framework called deep clustering. Previous deep network approaches to separation have shown promising performance in scenarios with a fixed number of sources, each belonging to a distinct signal class, such as speech and…