Publication: A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition
A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition
Date
Date
Date
Citations
Braun, S., Neil, D., & Liu, S.-C. (2017). A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition. 0–0. https://doi.org/10.23919/EUSIPCO.2017.8081267
Abstract
Abstract
Abstract
The performance of automatic speech recognition systems under noisy environments still leaves room for improvement. Speech enhancement or feature enhancement techniques for increasing noise robustness of these systems usually add components to the recognition system that need careful optimization. In this work, we propose the use of a relatively simple curriculum training strategy called accordion annealing (ACCAN). It uses a multi-stage training schedule where samples at signal-to-noise ratio (SNR) values as low as 0dB are first adde
Metrics
Views
Additional indexing
Creators (Authors)
- Braun, Stefan
- Neil, Daniel
- Liu, Shih-Chii
Event Title
Event Title
Event Title
Event Location
Event Location
Event Location
Event Country
Event Country
Event Country
Event Start Date
Event Start Date
Event Start Date
Event End Date
Event End Date
Event End Date
Publisher
Publisher
Publisher
Page range/Item number
Page range/Item number
Page range/Item number
Page end
Page end
Page end
Item Type
Item Type
Item Type
In collections
Language
Language
Language
Date available
Date available
Date available
Series Name
Series Name
Series Name
OA Status
OA Status
OA Status
Publisher DOI
Metrics
Views
Citations
Braun, S., Neil, D., & Liu, S.-C. (2017). A Curriculum Learning Method for Improved Noise Robustness in Automatic Speech Recognition. 0–0. https://doi.org/10.23919/EUSIPCO.2017.8081267
