Search Results for author:
Found 18 papers, 14 papers with code
Wav2Gloss: Generating Interlinear Glossed Text from Speech
Thousands of the world's languages are in danger of extinction--a tremendous threat to cultural identities and human language diversity.
OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer
In this work, we aim to improve the performance and efficiency of OWSM without extra training data.
Understanding Probe Behaviors through Variational Bounds of Mutual Information
With the success of self-supervised representations, researchers seek a better understanding of the information encapsulated within a representation.
Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study
Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling.
Speech Intelligibility Assessment of Dysarthric Speech by using Goodness of Pronunciation with Uncertainty Quantification
This paper proposes an improved Goodness of Pronunciation (GoP) that utilizes Uncertainty Quantification (UQ) for automatic speech intelligibility assessment for dysarthric speech.
Unsupervised Speech Representation Pooling Using Vector Quantization
However, the pooling problem remains; the length of speech representations is inherently variable.
OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset
Inspired by humans comprehending speech in a multi-modal manner, various audio-visual datasets have been constructed.
Correcting Faulty Road Maps by Image Inpainting
As maintaining road networks is labor-intensive, many automatic road extraction approaches have been introduced to solve this real-world problem, fueled by the abundance of large-scale high-resolution satellite imagery and advances in computer vision.
Opening the Black Box of wav2vec Feature Encoder
Self-supervised models, namely, wav2vec and its variants, have shown promising results in various downstream tasks in the speech domain.
Automatic Severity Classification of Dysarthric speech by using Self-supervised Model with Multi-task Learning
To tackle the problem, we propose a novel automatic severity assessment method for dysarthric speech, using the self-supervised model in conjunction with multi-task learning.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
TiDAL: Learning Training Dynamics for Active Learning
Active learning (AL) aims to select the most useful data samples from an unlabeled data pool and annotate them to expand the labeled dataset under a limited budget.
Reliable Decision from Multiple Subtasks through Threshold Optimization: Content Moderation in the Wild
In this study, we formulate real-world scenarios of content moderation and introduce a simple yet effective threshold optimization method that searches the optimal thresholds of the multiple subtasks to make a reliable moderation decision in a cost-effective way.
Distilling a Pretrained Language Model to a Multilingual ASR Model
Hence, we are motivated to distill the rich knowledge embedded inside a well-trained teacher text model to the student speech model.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection
Recent studies on learning with noisy labels have shown remarkable performance by exploiting a small clean dataset.
Temporal Knowledge Distillation for On-device Audio Classification
Improving the performance of on-device audio classification models remains a challenge given the computational limits of the mobile environment.
Ranked #7 on
Audio Classification
on FSD50K
Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learning
Neural architecture search (NAS) has fostered various fields of machine learning.
Disentangling Label Distribution for Long-tailed Visual Recognition
Although this method surpasses state-of-the-art methods on benchmark datasets, it can be further improved by directly disentangling the source label distribution from the model prediction in the training phase.
Ranked #20 on
Long-tail Learning
on Places-LT
Combating the Instability of Mutual Information-based Losses via Regularization
Notable progress has been made in numerous fields of machine learning based on neural network-driven mutual information (MI) bounds.
