Search Results for author:
Found 28 papers, 10 papers with code
Travel Time Prediction using Tree-Based Ensembles
The computational results show that the addition of this routing data can be beneficial to the model performance.
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
TDT models for Speech Recognition achieve better accuracy and up to 2. 82X faster inference than conventional Transducers.
Intent Classification
Intent Classification and Slot Filling
+3
SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation
We present a novel Speech Augmented Language Model (SALM) with {\em multitask} and {\em in-context} learning capabilities.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing
Extensive experiments have been conducted to compare the sensing capacity of each or several modalities in terms of multiple tasks.
Generative Dual Adversarial Network for Generalized Zero-shot Learning
Most previous models try to learn a fixed one-directional mapping between visual and semantic space, while some recently proposed generative methods try to generate image features for unseen classes so that the zero-shot learning problem becomes a traditional fully-supervised classification problem.
SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events
In this paper, we create a novel dataset, SUTD-TrafficQA (Traffic Question Answering), which takes the form of video QA based on the collected 10, 080 in-the-wild videos and annotated 62, 535 QA pairs, for benchmarking the cognitive capability of causal inference and event understanding models in complex traffic scenarios.
Ranked #2 on
Video Question Answering
on SUTD-TrafficQA
FedVision: An Online Visual Object Detection Platform Powered by Federated Learning
Federated learning (FL) is a promising approach to resolve this challenge.
Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score
Motivated by the fact that detecting these rare relations can be critical in real-world applications, this paper introduces a novel integrated framework of classification and ranking to resolve the class imbalance problem in scene graph parsing.
Auction-Based Combinatorial Multi-Armed Bandit Mechanisms with Strategic Arms
The multi-armed bandit (MAB) model has been deeply studied to solve many online learning problems, such as rate allocation in communication networks, Ad recommendation in social networks, etc.
dpMood: Exploiting Local and Periodic Typing Dynamics for Personalized Mood Prediction
Mood disorders are common and associated with significant morbidity and mortality.
Human-Computer Interaction Computers and Society
An Introduction to Image Synthesis with Generative Adversarial Nets
There has been a drastic growth of research in Generative Adversarial Nets (GANs) in the past few years.
NavigationNet: A Large-scale Interactive Indoor Navigation Dataset
Indoor navigation aims at performing navigation within buildings.
Learning under uncertainty: a comparison between R-W and Bayesian approach
The Bayesian approach indicates that the belief of environmental stationarity positively correlates with choice optimality, but not lose-shift rate (inverted U shape).
Context-sensitive active sensing in humans
Humans and animals readily utilize active sensing, or the use of self-motion, to focus sensory and cognitive resources on the behaviorally most relevant stimuli and events in the environment.
On-Demand Video Dispatch Networks: A Scalable End-to-End Learning Approach
We design a dispatch system to improve the peak service quality of video on demand (VOD).
Instance Scale Normalization for image understanding
Scale variation remains a challenging problem for object detection.
Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge
On the other hand, there is a large semantic gap between seen and unseen classes in the existing multi-label classification datasets.
Cooperative Communications for Internet of Everything in B5G/6G Hybrid and Ubiquitous Networks: Foundation, Further Optimization and Solutions
Cooperative Communications (CC) has been one of most critical communication technologies which plays a founding role on Internet of Everything in B5G/6G networks.
The Multi-Modal Video Reasoning and Analyzing Competition
In this paper, we introduce the Multi-Modal Video Reasoning and Analyzing Competition (MMVRAC) workshop in conjunction with ICCV 2021.
ME-Net: Multi-Encoder Net Framework for Brain Tumor Segmentation
Moreover, the serious voxel imbalance between the brain tumor and the background as well as the different sizes and locations of the brain tumor makes the segmentation of 3D images a challenging problem.
MetaFi: Device-Free Pose Estimation via Commodity WiFi for Metaverse Avatar Simulation
Avatar refers to a representative of a physical user in the virtual world that can engage in different activities and interact with other objects in metaverse.
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition
Conformer-based models have become the dominant end-to-end architecture for speech processing tasks.
Ranked #1 on
Speech Recognition
on LibriSpeech test-other
Leveraging Pretrained ASR Encoders for Effective and Efficient End-to-End Speech Intent Classification and Slot Filling
We study speech intent classification and slot filling (SICSF) by proposing to use an encoder pretrained on speech recognition (ASR) to initialize an end-to-end (E2E) Conformer-Transformer model, which achieves the new state-of-the-art results on the SLURP dataset, with 90. 14% intent accuracy and 82. 27% SLURP-F1.
Practical Parallel Algorithms for Non-Monotone Submodular Maximization
Submodular maximization has found extensive applications in various domains within the field of artificial intelligence, including but not limited to machine learning, computer vision, and natural language processing.
AdaPose: Towards Cross-Site Device-Free Human Pose Estimation with Commodity WiFi
The results demonstrate the effectiveness and robustness of AdaPose in eliminating domain shift, thereby facilitating the widespread application of WiFi-based pose estimation in smart cities.
The CHiME-7 Challenge: System Description and Performance of NeMo Team's DASR System
We present the NVIDIA NeMo team's multi-channel speech recognition system for the 7th CHiME Challenge Distant Automatic Speech Recognition (DASR) Task, focusing on the development of a multi-channel, multi-speaker speech recognition system tailored to transcribe speech from distributed microphones and microphone arrays.
Property-Aware Multi-Speaker Data Simulation: A Probabilistic Modelling Technique for Synthetic Data Generation
This capability offers a tailored training environment for developing neural models suited for speaker diarization and voice activity detection.
You Can Trade Your Experience in Distributed Multi-Agent Multi-Armed Bandits
In this paper, we propose a transaction-based multi-agent MAB framework, where agents can trade their bandit experience with each other to improve their total individual rewards.
