Robust sub-band speech feature extraction using multiresolution convolutional neural networks

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.

Naderi Navid; NASERSHARIF 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): 1393-1404

Download Full-Text

Persian Verion

View:

321

Download:

Cites:

Information Journal Paper

Title

Robust sub-band speech feature extraction using multiresolution convolutional neural networks

Author(s)

Naderi Navid | NASERSHARIF BABAK | Issue Writer Certificate

Keywords

Convolutional neural networkQ1

Robust speech recognitionQ2

Single resolutionQ1

Multi-resolutionQ1

Mel filter bankQ1

Abstract

Convolutional neural networks (CNNs), as a kind of deep neural networks, have been recently used for acoustic modeling and feature extraction along with acoustic modeling in speech recognition systems. In this paper, we propose to use CNN for robust feature extraction from the noisy speech spectrum. In the proposed manner, CNN inputs are noisy speech spectrum and its targets are denoised logarithm of Mel filter bank energies (LMFBs). Consequently, CNN extracts robust features from speech spectrum. The drawback of CNN in the proposed method is its fixed frequency resolution. Thus, we propose to use multiple CNNs with different convolution filter sizes to provide different frequency resolutions for feature extraction from the speech spectrum. We named this method as Multiresolution CNN (MRCNN). Recognition accuracy on Aurora 2 database, shows that CNNs outperform deep belief networks such that, CNN recognition accuracy has 20% relative improvement on average over DBN. However, results show that MRCNN recognition accuracy has 1% relative improvement on average over CNN.

Cites

No record.

References

No record.

Cite

APA: Copy

Naderi, Navid, & NASERSHARIF, BABAK. (2019). Robust sub-band speech feature extraction using multiresolution convolutional neural networks. TABRIZ JOURNAL OF ELECTRICAL ENGINEERING, 49(3 (89) ), 1393-1404. SID. https://sid.ir/paper/256522/en

Vancouver: Copy

Naderi Navid, NASERSHARIF BABAK. Robust sub-band speech feature extraction using multiresolution convolutional neural networks. TABRIZ JOURNAL OF ELECTRICAL ENGINEERING[Internet]. 2019;49(3 (89) ):1393-1404. Available from: https://sid.ir/paper/256522/en

IEEE: Copy

Navid Naderi, and BABAK NASERSHARIF, “Robust sub-band speech feature extraction using multiresolution convolutional neural networks,” TABRIZ JOURNAL OF ELECTRICAL ENGINEERING, vol. 49, no. 3 (89) , pp. 1393–1404, 2019, [Online]. Available: https://sid.ir/paper/256522/en

Related Journal Papers