FEATURE MAPPING USING DEEP BELIEF NETWORKS FOR ROBUST SPEECH RECOGNITION

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.

GHOLAMI POOR MOJTABA; NASER SHARIF BABAK

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

Journal Paper

Paper Information

Journal: The Modares Journal of Electrical Engineering Year:2014 | Volume:14 | Issue:3 Page(s): 24-30

Download Full-Text

View:

254

Download:

Cites:

Information Journal Paper

Title

FEATURE MAPPING USING DEEP BELIEF NETWORKS FOR ROBUST SPEECH RECOGNITION

Author(s)

GHOLAMI POOR MOJTABA | NASER SHARIF BABAK | Issue Writer Certificate

Keywords

MFCC

TANDEM FEATURE

DBN

ROBUSTNESS

SPEECH RECOGNITION

Abstract

Performance of automatic SPEECH RECOGNITION (ASR) systems degrades in noisy conditions due to mismatch between training and test environments. Many methods have been proposed for reducing this mismatch in ASR systems. In recent years, deep neural networks (DNNs) have been widely used in ASR systems and also robust SPEECH RECOGNITION and feature extraction. In this paper, we propose to use deep belief network (DBN) as a post-processing method for de-noising Mel frequency cepstral coefficients (MFCCs). In addition, we use deep belief network for extracting TANDEM FEATUREs (posterior probability of phones occurrence) from de-noised MFCCs (obtained from previous stage) to obtain more robust and discriminative features. The final robust feature vector consists of de-noised MFCCs concatenated to mentioned TANDEM FEATUREs. Evaluation results on Aurora2 database show that the proposed feature vector performs better than similar and conventional techniques, where it increases recognition accuracy in average by 28% in comparison to MFCCs.

Cites

No record.

References

No record.

Cite

APA: Copy

GHOLAMI POOR, MOJTABA, & NASER SHARIF, BABAK. (2014). FEATURE MAPPING USING DEEP BELIEF NETWORKS FOR ROBUST SPEECH RECOGNITION. MODARES JOURNAL OF ELECTRICAL ENGINEERING, 14(3), 24-30. SID. https://sid.ir/paper/688706/en

Vancouver: Copy

GHOLAMI POOR MOJTABA, NASER SHARIF BABAK. FEATURE MAPPING USING DEEP BELIEF NETWORKS FOR ROBUST SPEECH RECOGNITION. MODARES JOURNAL OF ELECTRICAL ENGINEERING[Internet]. 2014;14(3):24-30. Available from: https://sid.ir/paper/688706/en

IEEE: Copy

MOJTABA GHOLAMI POOR, and BABAK NASER SHARIF, “FEATURE MAPPING USING DEEP BELIEF NETWORKS FOR ROBUST SPEECH RECOGNITION,” MODARES JOURNAL OF ELECTRICAL ENGINEERING, vol. 14, no. 3, pp. 24–30, 2014, [Online]. Available: https://sid.ir/paper/688706/en

Related Journal Papers

No record.

Related Seminar Papers

No record.

Related Plans

No record.

Recommended Workshops