Multi-Task Autoencoder for Noise-Robust Speech Recognition

For speech recognition in noisy environments, we propose a multi-task autoencoder which estimates not only clean speech features but also noise features from noisy speech. We introduce the deSpeeching autoencoder, which excludes speech signals from noisy speech, and combine it with the conventional...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) s. 5599 - 5603
Hlavní autoři: Zhang, Haoyi, Liu, Conggui, Inoue, Nakamasa, Shinoda, Koichi
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.04.2018
Témata:
Denoising autoencoder
deSpeeching au-toencoder
Ion radiation effects
Magnetosphere
Noise measurement
Noise reduction
robust speech recognition
Speech recognition
Task analysis
Training
ISSN:2379-190X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:For speech recognition in noisy environments, we propose a multi-task autoencoder which estimates not only clean speech features but also noise features from noisy speech. We introduce the deSpeeching autoencoder, which excludes speech signals from noisy speech, and combine it with the conventional denoising autoencoder to form a unified multi-task au-toencoder (MTAE). We evaluate it using the Aurora 2 dataset and CHIME 3 dataset. It reduced WER by 15.7% from the conventional denoising autoencoder in the Aurora 2 test set A.
ISSN:2379-190X
DOI:10.1109/ICASSP.2018.8461446