Spatial position constraint for unsupervised learning of speech representations
The success of supervised learning techniques for automatic speech processing does not always extend to problems with limited annotated speech. Unsupervised representation learning aims at utilizing unlabelled data to learn a transformation that makes speech easily distinguishable for classification...
Main Authors: | Mohammad Ali Humayun, Hayati Yassin, Pg Emeroylariffion Abas |
---|---|
Format: | Article |
Language: | English |
Published: |
PeerJ Inc.
2021-07-01
|
Series: | PeerJ Computer Science |
Subjects: | |
Online Access: | https://peerj.com/articles/cs-650.pdf |
Similar Items
-
Improving Low-Resource Speech Recognition Based on Improved NN-HMM Structures
by: Xiusong Sun, et al.
Published: (2020-01-01) -
Unsupervised Representation Learning with Task-Agnostic Feature Masking for Robust End-to-End Speech Recognition
by: June-Woo Kim, et al.
Published: (2023-01-01) -
JSUM: A Multitask Learning Speech Recognition Model for Jointly Supervised and Unsupervised Learning
by: Nurmemet Yolwas, et al.
Published: (2023-04-01) -
Separate Syntax and Semantics: Part-of-Speech-Guided Transformer for Image Captioning
by: Dong Wang, et al.
Published: (2022-11-01) -
Speech Emotion and Naturalness Recognitions With Multitask and Single-Task Learnings
by: Bagus Tris Atmaja, et al.
Published: (2022-01-01)