Two-stage noise aware training using asymmetric deep denoising autoencoder

Ever since the deep neural network (DNN)-based acoustic model appeared, the recognition performance of automatic speech recognition has been greatly improved. Due to this achievement, various researches on DNN-based technique for noise robustness are also in progress. Among these approaches, the noi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 5765 - 5769
Hlavní autoři: Lee, Kang Hyun, Kang, Shin Jae, Kang, Woo Hyun, Kim, Nam Soo
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: IEEE 01.03.2016
Témata:
Acoustics
Deep neural networks (DNNs)
denoising autoencoder
Electronics
Estimates
Feature extraction
Hidden Markov models
Neural networks
Noise
noise aware training (NAT)
Noise measurement
Noise reduction
robust speech recognition
Robustness
Speech
Speech recognition
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:Ever since the deep neural network (DNN)-based acoustic model appeared, the recognition performance of automatic speech recognition has been greatly improved. Due to this achievement, various researches on DNN-based technique for noise robustness are also in progress. Among these approaches, the noise-aware training (NAT) technique which aims to improve the inherent robustness of DNN using noise estimates has shown remarkable performance. However, despite the great performance, we cannot be certain whether NAT is an optimal method for sufficiently utilizing the inherent robustness of DNN. In this paper, we propose a novel technique which helps the DNN to address the complex connection between the input and target vectors of NAT smoothly. The proposed method outperformed the conventional NAT in Aurora-5 task.
Bibliografie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
ISSN:2379-190X
DOI:10.1109/ICASSP.2016.7472782