Search Results for author:
Found 20 papers, 8 papers with code
FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder
The goal of this paper is to generate realistic audio with a lightweight and fast diffusion-based vocoder, named FreGrad.
Let There Be Sound: Reconstructing High Quality Speech from Silent Videos
In this paper, we propose a novel lip-to-speech system that significantly improves the generation quality by alleviating the one-to-many mapping problem from multiple perspectives.
CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech Synthesis
In this paper, we propose CrossSpeech which improves the quality of cross-lingual speech by effectively disentangling speaker and language information in the level of acoustic feature space.
Relation-Aware Language-Graph Transformer for Question Answering
To address these issues, we propose Question Answering Transformer (QAT), which is designed to jointly reason over language and graphs with respect to entity relations in a unified manner.
Accelerating Large-Scale Graph-based Nearest Neighbor Search on a Computational Storage Platform
In this paper, we propose a computational storage platform that can accelerate a large-scale graph-based nearest neighbor search algorithm based on SmartSSD CSD.
Two-Step Question Retrieval for Open-Domain QA
These models have shown a significant increase in inference speed, but at the cost of lower QA performance compared to the retriever-reader models.
Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?
To take such non-linear characteristics into account, we introduce Label-Gradient Alignment (LGA), a novel NTK-based metric whose inherent formulation allows it to capture the large amount of non-linear advantage present in modern neural architectures.
VoiceMixer: Adversarial Voice Style Mixup
This insufficiency leads to the converted speech containing source speech style or losing source speech content.
SUMNAS: Supernet with Unbiased Meta-Features for Neural Architecture Search
We propose Supernet with Unbiased Meta-Features for Neural Architecture Search (SUMNAS), a supernet learning strategy based on meta-learning to tackle the knowledge forgetting issue.
GC-TTS: Few-shot Speaker Adaptation with Geometric Constraints
While numerous attempts have been made to the few-shot speaker adaptation system, there is still a gap in terms of speaker similarity to the target speaker depending on the amount of data.
Weakly Supervised Pre-Training for Multi-Hop Retriever
In multi-hop QA, answering complex questions entails iterative document retrieval for finding the missing entity of the question.
Fre-GAN: Adversarial Frequency-consistent Audio Synthesis
Although recent works on neural vocoder have improved the quality of synthesized audio, there still exists a gap between generated and ground-truth audio in frequency space.
Faster and Smarter AutoAugment: Augmentation Policy Search Based on Dynamic Data-Clustering
Data augmentation tuned to datasets and tasks has had great success in various AI applications, such as computer vision, natural language processing, autonomous driving, and bioinformatics.
Scale down Transformer by Grouping Features for a Lightweight Character-level Language Model
This paper introduces a method that efficiently reduces the computational cost and parameter size of Transformer.
Context-Aware Answer Extraction in Question Answering
With experiments on reading comprehension, we show that BLANC outperforms the state-of-the-art QA models, and the performance gap increases as the number of answer text occurrences increases.
HyperTendril: Visual Analytics for User-Driven Hyperparameter Optimization of Deep Neural Networks
HyperTendril takes a novel approach to effectively steering hyperparameter optimization through an iterative, interactive tuning procedure that allows users to refine the search spaces and the configuration of the AutoML method based on their own insights from given results.
VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning
We show that our method can be applied to classification tasks on multiple different datasets -- including one that is a real-world dataset with heavy data imbalance -- significantly outperforming the state of the art.
ACE: Artificial Checkerboard Enhancer to Induce and Evade Adversarial Attacks
The checkerboard phenomenon is one of the well-known visual artifacts in the computer vision field.
CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms
Many hyperparameter optimization (HyperOpt) methods assume restricted computing resources and mainly focus on enhancing performance.
The Impact of Automatic Pre-annotation in Clinical Note Data Element Extraction - the CLEAN Tool
Our study introduces CLEAN (CLinical note rEview and ANnotation), a pre-annotation-based cNLP annotation system to improve clinical note annotation of data elements, and comprehensively compares CLEAN with the widely-used annotation system Brat Rapid Annotation Tool (BRAT).
