This paper introduces SpeeChain, an open-source Pytorch-based toolkit
de...
We present NusaCrowd, a collaborative initiative to collect and unite
ex...
The success of deep learning on video Action Recognition (AR) has motiva...
Research about brain activities involving spoken word production is
cons...
Consistency regularization has recently been applied to semi-supervised
...
This paper presents a newly developed, simultaneous neural speech-to-spe...
Even though over seven hundred ethnic languages are spoken in Indonesia,...
Attention-based sequence-to-sequence automatic speech recognition (ASR)
...
Inspired by a human speech chain mechanism, a machine speech chain frame...
Previous research has proposed a machine speech chain to enable automati...
We present the Zero Resource Speech Challenge 2020, which aims at learni...
We aim to improve the performance of Multiple Object Tracking and
Segmen...
We aim to improve the performance of Multiple Object Tracking and
Segmen...
In this paper, we report our submitted system for the ZeroSpeech 2020
ch...
This work proposes a new human-related video processing task named 3D
pa...
In this paper, we explore a method for training speech-to-speech transla...
Although skeleton-based action recognition has achieved great success in...
The most common way for humans to communicate is by speech. But perhaps ...
We describe our submitted system for the ZeroSpeech Challenge 2019. The
...
We present the Zero Resource Speech Challenge 2019, which proposes to bu...
The speech chain mechanism integrates automatic speech recognition (ASR)...
A sequence-to-sequence model is a neural network module for mapping two
...
In previous work, we developed a closed-loop speech chain model based on...
In the machine learning fields, Recurrent Neural Network (RNN) has becom...
We propose an interactive image-manipulation system with natural languag...
Sequence-to-sequence attentional-based neural network architectures have...
Despite the success of sequence-to-sequence approaches in automatic spee...
Conventional automatic speech recognition (ASR) typically performs
multi...
Despite the close relationship between speech perception and production,...
Recurrent Neural Networks (RNNs), which are a powerful scheme for modeli...
Recently, encoder-decoder neural networks have shown impressive performa...