Robust Speech Recognition using Long Short Term Memory Networks and Bottleneck Features

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

Moaven Joula Amin; AKBARI AHMAD; NASER SHARIF BABAK

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: TABRIZ JOURNAL OF ELECTRICAL ENGINEERING Year:2019 | Volume:49 | Issue:3 (89) Page(s): 1333-1343

Download Full-Text

Persian Verion

View:

482

Download:

Cites:

Information Journal Paper

Title

Robust Speech Recognition using Long Short Term Memory Networks and Bottleneck Features

Author(s)

Moaven Joula Amin | AKBARI AHMAD | NASER SHARIF BABAK | Issue Writer Certificate

Keywords

Speech recognitionQ2

Noise robustnessQ1

Multicondition dataQ1

Autoencoder networkQ1

Long short term memory networkQ1

Abstract

Deep neural networks have been widely used in Speech recognition systems in recent years. However, the robustness of these models in the presence of environmental noise has been less discussed. In this paper, we propose two approaches for the robustness of deep neural networks models against environmental additive noise. In the first approach, we propose to increase the robustness of long short-term memory (LSTM) networks in the presence of noise based on their abilities in learning long-term noise behavior. For this purpose, we propose to use noisy speech for training models. In this way, LSTMs are trained in a noise-aware manner. The results on the noisy TIMIT dataset show that if the models are trained with noisy speech rather than clean speech, recognition accuracy will be improved up to 18%. In the second approach, we propose to reduce noise effects on the extracted features using a denoised Autoencoder network and to use the bottleneck features to compress the feature vector and represent the higher level of input features. This method increases the accuracy of the proposed recognition system in the first approach by 4% in the presence of noise.

Cites

No record.

References

No record.

Cite

APA: Copy

Moaven Joula, Amin, AKBARI, AHMAD, & NASER SHARIF, BABAK. (2019). Robust Speech Recognition using Long Short Term Memory Networks and Bottleneck Features. TABRIZ JOURNAL OF ELECTRICAL ENGINEERING, 49(3 (89) ), 1333-1343. SID. https://sid.ir/paper/256545/en

Vancouver: Copy

Moaven Joula Amin, AKBARI AHMAD, NASER SHARIF BABAK. Robust Speech Recognition using Long Short Term Memory Networks and Bottleneck Features. TABRIZ JOURNAL OF ELECTRICAL ENGINEERING[Internet]. 2019;49(3 (89) ):1333-1343. Available from: https://sid.ir/paper/256545/en

IEEE: Copy

Amin Moaven Joula, AHMAD AKBARI, and BABAK NASER SHARIF, “Robust Speech Recognition using Long Short Term Memory Networks and Bottleneck Features,” TABRIZ JOURNAL OF ELECTRICAL ENGINEERING, vol. 49, no. 3 (89) , pp. 1333–1343, 2019, [Online]. Available: https://sid.ir/paper/256545/en

Related Journal Papers