A STATE-OF-THE-ART AND EFFICIENT FRAMEWORK FOR PERSIANSPEECH 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.

BABAALI BAGHER

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:13 | Issue:3 (SERIAL 29) Page(s): 51-62

Download Full-Text

Persian Verion

View:

704

Download:

Cites:

Information Journal Paper

Title

A STATE-OF-THE-ART AND EFFICIENT FRAMEWORK FOR PERSIANSPEECH RECOGNITION

Author(s)

BABAALI BAGHER | Issue Writer Certificate

Keywords

PERSIAN CONTINUOUS SPEECH RECOGNITIONQ2

FARSDAT DATABASEQ3

KALDI TOOLKITQ2

Abstract

Although researches in the field of Persian speech recognition claim a thirty-year-old history in Iranwhich bas achieved considerable progresses, due to the lack of well-dermed experimental framework, outcomes from many of these researches are not comparable to each other and their accurate assessmentwon't be possible. The experimental framework includes ASR toolkit and speech database which consists oftraining, development and test datasets. In recent years, as a state-of-the-art open-source ASR toolkit; Kaldi bas been very well-received and welcomed in the community of the world-ranked speech researchersaround the world. considering all aspectsJ Kaldi is the best option among all of the other ASR toolkits to establish a framework to do research in all languages, including Persian. In this paper, we chose Fardat as the speech database which is the counterpart of TIMIT for Persian language because not only it has got a standard form but Ws also accessible for all researchers around the world. Similar to the recipe on TIMIT database, we defined these three sets on the Farsdat: Training, Development and Test sets. After a survey on Kaldi's components and featuresJ we applied most of state-of the-art ASR techniques in the Kaldi on the Farsdat based on three sets defmition. The best phone error rate on development and test set have been 20. 3o/e and 19. 8o/e. All of the codes and the recipe that was written by author have been submitted to Kaldi repository and they are accessible for free, so aU the reported results will be easily repUcable if you have access to FARSDAT DATABASE.

Cites

No record.

References

No record.

Cite

APA: Copy

BABAALI, BAGHER. (2016). A STATE-OF-THE-ART AND EFFICIENT FRAMEWORK FOR PERSIANSPEECH RECOGNITION. SIGNAL AND DATA PROCESSING, 13(3 (SERIAL 29) ), 51-62. SID. https://sid.ir/paper/160895/en

Vancouver: Copy

BABAALI BAGHER. A STATE-OF-THE-ART AND EFFICIENT FRAMEWORK FOR PERSIANSPEECH RECOGNITION. SIGNAL AND DATA PROCESSING[Internet]. 2016;13(3 (SERIAL 29) ):51-62. Available from: https://sid.ir/paper/160895/en

IEEE: Copy

BAGHER BABAALI, “A STATE-OF-THE-ART AND EFFICIENT FRAMEWORK FOR PERSIANSPEECH RECOGNITION,” SIGNAL AND DATA PROCESSING, vol. 13, no. 3 (SERIAL 29) , pp. 51–62, 2016, [Online]. Available: https://sid.ir/paper/160895/en

Related Journal Papers