Search Results for author:
Found 26 papers, 11 papers with code
Neural Directed Speech Enhancement with Dual Microphone Array in High Noise Scenario
In multi-speaker scenarios, leveraging spatial features is essential for enhancing target speech.
NTC-KWS: Noise-aware CTC for Robust Keyword Spotting
In recent years, there has been a growing interest in designing small-footprint yet effective Connectionist Temporal Classification based keyword spotting (CTC-KWS) systems.
Streaming Keyword Spotting Boosted by Cross-layer Discrimination Consistency
Connectionist Temporal Classification (CTC), a non-autoregressive training criterion, is widely used in online keyword spotting (KWS).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Semantic Scene Completion Based 3D Traversability Estimation for Off-Road Terrains
Off-road environments present significant challenges for autonomous ground vehicles due to the absence of structured roads and the presence of complex obstacles, such as uneven terrain, vegetation, and occlusions.
Does Few-Shot Learning Help LLM Performance in Code Synthesis?
This work focuses on the few-shot examples present in most code generation prompts, offering a systematic study on whether few-shot examples improve LLM's coding capabilities, which few-shot examples have the largest impact, and how to select impactful examples.
MiniCPM-V: A GPT-4V Level MLLM on Your Phone
The recent surge of Multimodal Large Language Models (MLLMs) has fundamentally reshaped the landscape of AI research and industry, shedding light on a promising path toward the next AI milestone.
Ranked #7 on
Multiple-choice
on Neptune-Full
Text-aware Speech Separation for Multi-talker Keyword Spotting
TPDT-SS shows remarkable success in addressing permutation problems in mixed keyword speech, thereby greatly boosting the performance of the backend.
TDT-KWS: Fast And Accurate Keyword Spotting Using Token-and-duration Transducer
Designing an efficient keyword spotting (KWS) system that delivers exceptional performance on resource-constrained edge devices has long been a subject of significant attention.
NeuralDiffuser: Neuroscience-inspired Diffusion Guidance for fMRI Visual Reconstruction
Reconstructing visual stimuli from functional Magnetic Resonance Imaging fMRI enables fine-grained retrieval of brain activity.
Improving Efficiency of Iso-Surface Extraction on Implicit Neural Representations Using Uncertainty Propagation
In this paper, we present an improved technique for range analysis by revisiting the arithmetic rules and analyzing the probability distribution of the network output within a spatial region.
Accelerating Distributed Deep Learning using Lossless Homomorphic Compression
As deep neural networks (DNNs) grow in complexity and size, the resultant increase in communication overhead during distributed training has become a significant bottleneck, challenging the scalability of distributed training systems.
The Future of Cognitive Strategy-enhanced Persuasive Dialogue Agents: New Perspectives and Trends
To depict the research trends of CogAgent, in this paper, we first present several fundamental cognitive psychology theories and give the formalized definition of three typical cognitive strategies, including the persuasion strategy, the topic path planning strategy, and the argument structure prediction strategy.
Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation
Data attribution methods trace model behavior back to its training dataset, offering an effective approach to better understand ''black-box'' neural networks.
Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks
Metallic Glasses (MGs) are widely used materials that are stronger than steel while being shapeable as plastic.
Hybrid HMM Decoder For Convolutional Codes By Joint Trellis-Like Structure and Channel Prior
In this paper, we propose the use of a Hidden Markov Model (HMM) for the reconstruction of convolutional codes and decoding by the Viterbi algorithm.
IDLat: An Importance-Driven Latent Generation Method for Scientific Data
We qualitatively and quantitatively evaluate the effectiveness and efficiency of latent representations generated by our method with data from multiple scientific visualization applications.
VDL-Surrogate: A View-Dependent Latent-based Model for Parameter Space Exploration of Ensemble Simulations
In the model inference stage, we predict the latent representations at previously selected viewpoints and decode the latent representations to data space.
Joint Noise Reduction and Listening Enhancement for Full-End Speech Enhancement
Speech enhancement (SE) methods mainly focus on recovering clean speech from noisy input.
DDS: A new device-degraded speech dataset for speech enhancement
A large and growing amount of speech content in real-life scenarios is being recorded on consumer-grade devices in uncontrolled environments, resulting in degraded speech quality.
Local Latent Representation based on Geometric Convolution for Particle Data Feature Exploration
Feature related particle data analysis plays an important role in many scientific applications such as fluid simulations, cosmology simulations and molecular dynamics.
Multi-Metric Optimization using Generative Adversarial Networks for Near-End Speech Intelligibility Enhancement
The intelligibility of speech severely degrades in the presence of environmental noise and reverberation.
Noise Tokens: Learning Neural Noise Templates for Environment-Aware Speech Enhancement
In recent years, speech enhancement (SE) has achieved impressive progress with the success of deep neural networks (DNNs).
Audio and Speech Processing
iMetricGAN: Intelligibility Enhancement for Speech-in-Noise using Generative Adversarial Network-based Metric Learning
The intelligibility of natural speech is seriously degraded when exposed to adverse noisy environments.
Audio and Speech Processing Sound
NNVA: Neural Network Assisted Visual Analysis of Yeast Cell Polarization Simulation
We utilize the trained network to perform interactive parameter sensitivity analysis of the original simulation at multiple levels-of-detail as well as recommend optimal parameter configurations using the activation maximization framework of neural networks.
Faster super-resolution imaging with auto-correlation two-step deconvolution
Despite super-resolution fluorescence blinking microscopes break the diffraction limit, the intense phototoxic illumination and long-term image sequences thus far still pose to major challenges in visualizing live-organisms.
Optics
Volumetric Light-field Encryption at the Microscopic Scale
We report a light-field based method that allows the optical encryption of three-dimensional (3D) volumetric information at the microscopic scale in a single 2D light-field image.
