Seq2Seq

User-realistic path synthesis via multi-task generative adversarial networks for continuous path keyboard input
An example method includes at an electronic device with one or more processors and memory: obtaining first data representing a …
Jerome R. Bellegarda, Jui-Yang Hsu, Partha Lal, Akash Mehra
Source Document
DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation
In previous works, only parameter weights of ASR models are optimized under fixed-topology architecture. However, the design of …
Yi-Chen Chen, Jui-Yang Hsu, Cheng-Kuang Lee, Hung-Yi Lee
PDF Cite
DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation
Meta Learning for End-to-End Low-Resource Speech Recognition
In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for …
Jui-Yang Hsu, Yuan-Jui Chen, Hung-Yi Lee
PDF Cite Code Video DOI
Meta Learning for End-to-End Low-Resource Speech Recognition