Deep learning based speech enhancement for noise adverse environment

Deep learning based speech enhancement for noise adverse environment

Speech is the primary way humans communicate. Speech enhancement algorithms estimate speech from received signals. Although conventional approaches can achieve accurate estimates under low noise conditions, their performance degrades with reducing signal-to-noise ratio (SNR). This thesis introduces...

Full description

Bibliographic Details
Main Author: Tan, Zhi Wei
Other Authors: Andy Khong W H
Format: Thesis-Doctor of Philosophy
Language:English
Published: Nanyang Technological University 2024
Subjects:
Computer and Information Science
Engineering
Speech enhancement
Neural beamforming
Deep learning
Direction-of-arrival
Low signal-to-noise ratio
Transfer learning
Scarse training data
Array signal processing
Online Access:https://hdl.handle.net/10356/178275

Internet

https://hdl.handle.net/10356/178275

Similar Items