Feature Adaptation Using Linear Spectro-Temporal Transform for Robust Speech Recognition
Spectral information represents short-term speech information within a frame of a few tens of milliseconds, while temporal information captures the evolution of speech statistics over consecutive frames. Motivated by the findings that human speech comprehension relies on the integrity of both the sp...
Saved in:
Main Authors: | Nguyen, Duc Hoang Ha, Xiao, Xiong, Chng, Eng Siong, Li, Haizhou |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2016
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/84664 http://hdl.handle.net/10220/41916 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Speech dereverberation for enhancement and recognition using dynamic features constrained deep neural networks and feature adaptation
by: Xiao, Xiong, et al.
Published: (2016) -
Joint spectral and temporal normalization of features for robust recognition of noisy and reverberated speech
by: Xiao, Xiong, et al.
Published: (2013) -
Multistage spatio-temporal networks for robust sketch recognition
by: Li, Hanhui, et al.
Published: (2022) -
Integrating articulatory based features with auditory based features for robust stressed speech recognition
by: Tin, L.N., et al.
Published: (2013) -
Temporally Varying Weight Regression for Speech Recognition
by: LIU SHILIN
Published: (2014)