DEEP MODULAR NEURAL NETWORKS WITH DOUBLE SPATIO-TEMPORAL ASSOCIATION STRUCTURE FOR PERSIAN CONTINUOUS 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.

ANSARI ZOHREH; SEYYED SALEHI SEYYED ALI

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

Journal Paper

Paper Information

Journal: SIGNAL AND DATA PROCESSING Year:2016 | Volume:- | Issue:1 (SERIAL 27) Page(s): 39-59

Download Full-Text

Persian Verion

View:

898

Download:

Cites:

Information Journal Paper

Title

DEEP MODULAR NEURAL NETWORKS WITH DOUBLE SPATIO-TEMPORAL ASSOCIATION STRUCTURE FOR PERSIAN CONTINUOUS SPEECH RECOGNITION

Author(s)

ANSARI ZOHREH | SEYYED SALEHI SEYYED ALI | Issue Writer Certificate

Keywords

DEEP NEURAL NETWORKSQ1

MODULAR NEURAL NETWORKSQ2

PRE-TRAININGQ2

SEMI-SUPERVISED LEARNINGQ2

CONTINUOUS SPEECH RECOGNITIONQ2

Abstract

In this article, growable deep MODULAR NEURAL NETWORKS for CONTINUOUS SPEECH RECOGNITION are introduced. These networks can be grown to implement the spatio-temporal information of the frame sequences at their input layer as well as their labels at the output layer at the same time. The trained neural network with such double spatio-temporal association structure can learn the phonetic sequence subspace. Therefore, it can filter out invalid phonetic sequences in its own structure and output valid sequences. To evaluate the performance of these growable neural networks, we used FARSDAT and BIG FARSDAT datasets. Experimental results on FARSDAT show that deep MODULAR NEURAL NETWORKS outperform the phone accuracy rate of GMM-HMM models with an absolute improvement of 2.7%. Moreover, developing deep MODULAR NEURAL NETWORKS to a double spatio-temporal association structure improves their result by 5.1%. As there is no phonetic labeling for BIG FARSDAT, a SEMI-SUPERVISED LEARNING algorithm is proposed to fine-tune the neural network with double spatio-temporal structure on this dataset, which achieves a comparable result with HMMs.

Cites

No record.

References

No record.

Cite

APA: Copy

ANSARI, ZOHREH, & SEYYED SALEHI, SEYYED ALI. (2016). DEEP MODULAR NEURAL NETWORKS WITH DOUBLE SPATIO-TEMPORAL ASSOCIATION STRUCTURE FOR PERSIAN CONTINUOUS SPEECH RECOGNITION. SIGNAL AND DATA PROCESSING, -(1 (SERIAL 27)), 39-59. SID. https://sid.ir/paper/160727/en

Vancouver: Copy

ANSARI ZOHREH, SEYYED SALEHI SEYYED ALI. DEEP MODULAR NEURAL NETWORKS WITH DOUBLE SPATIO-TEMPORAL ASSOCIATION STRUCTURE FOR PERSIAN CONTINUOUS SPEECH RECOGNITION. SIGNAL AND DATA PROCESSING[Internet]. 2016;-(1 (SERIAL 27)):39-59. Available from: https://sid.ir/paper/160727/en

IEEE: Copy

ZOHREH ANSARI, and SEYYED ALI SEYYED SALEHI, “DEEP MODULAR NEURAL NETWORKS WITH DOUBLE SPATIO-TEMPORAL ASSOCIATION STRUCTURE FOR PERSIAN CONTINUOUS SPEECH RECOGNITION,” SIGNAL AND DATA PROCESSING, vol. -, no. 1 (SERIAL 27), pp. 39–59, 2016, [Online]. Available: https://sid.ir/paper/160727/en

Related Journal Papers