ASR - VLSP 2021: Conformer with gradient mask and stochastic weight averaging for Vietnamese automatic speech recognition
Số trang: 7
Loại file: pdf
Dung lượng: 408.96 KB
Lượt xem: 18
Lượt tải: 0
Xem trước 1 trang đầu tiên của tài liệu này:
Thông tin tài liệu:
Recent years have witnessed the strong growth of Automatic Speech Recognition (ASR) studies due to its wide range of applications. However, there are few efforts put into the Vietnamese language. This paper introduces an end-to-end approach using Conformer, a combination of Transfomer and Convolution Neural Network, and pseudo labeling for Vietnamese ASR systems.
Nội dung trích xuất từ tài liệu:
ASR - VLSP 2021: Conformer with gradient mask and stochastic weight averaging for Vietnamese automatic speech recognition
Nội dung trích xuất từ tài liệu:
ASR - VLSP 2021: Conformer with gradient mask and stochastic weight averaging for Vietnamese automatic speech recognition
Tìm kiếm theo từ khóa liên quan:
Automatic speech recognition Gradient mask Convolution neural network Vietnamese ASR systems Modern E2E techniques Attention-basedEncoder-DecoderGợi ý tài liệu liên quan:
-
8 trang 29 0 0
-
7 trang 17 0 0
-
Design of an AI-based smart wearable device for visually impaired people
7 trang 16 0 0 -
Ebook Speech and Language Processing: An introduction to natural language processing - Part 1
509 trang 12 0 0 -
336 trang 11 0 0
-
Learning spatial features using CNN in network intrusion detection system
11 trang 6 0 0 -
Predictive neural stem cell differentiation using single-cell images based on deep learning
7 trang 5 0 0 -
Development of high performance and large scale Vietnamese automatic speech recognition systems
14 trang 4 0 0