WEIGHTED TRAINING OF CONTEXT DEPENDENT MODELS FOR 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.

SEYED AHADI S.M.; SHAMS SH.

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

Journal Paper

Paper Information

Journal: AMIRKABIR Year:2003 | Volume:14 | Issue:53 Page(s): 80-92

Download Full-Text

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

Persian Verion

View:

1,214

Download:

Cites:

Information Journal Paper

Title

WEIGHTED TRAINING OF CONTEXT DEPENDENT MODELS FOR CONTINUOUS SPEECH RECOGNITION

Author(s)

SEYED AHADI S.M. | SHAMS SH. | Issue Writer Certificate

Keywords

CONTINUOUS DENSITY HIDDEN MARKOV MODELSQ4

CONTINUOUS PERSIAN SPEECH RECOGNITIONQ4

CONTEXTQ4

DEPENDENT MODELINGQ4

BAUM-WELCH TRININGQ4

STATE TYINGQ4

MAP ESTIMATINQ4

Abstract

Context dependent modelling is a well-known technique used to improve recognition rate in continuous speech recognition. However, it can also dramatically increase the overall system parameter count which usually leads to a grave problem known as sparse training data condition. Different techniques such as model parameter tying and MAP estimation are used to overcome this problem. In this paper, a new approach, namely weighted training, has been introduced which benefits from both MAP estimation and parameter tying strengths and also outperforms the widely used parameter tying approach. The trip hone models are used in this implementation.

Cites

SPEAKER ADAPTATION IN CONTINUOUS SPEECH RECOGNITION USING MLLR-BASED MAP ESTIMATION

References

No record.

Cite

APA: Copy

SEYED AHADI, S.M., & SHAMS, SH.. (2003). WEIGHTED TRAINING OF CONTEXT DEPENDENT MODELS FOR CONTINUOUS SPEECH RECOGNITION. AMIRKABIR, 14(53), 80-92. SID. https://sid.ir/paper/663/en

Vancouver: Copy

SEYED AHADI S.M., SHAMS SH.. WEIGHTED TRAINING OF CONTEXT DEPENDENT MODELS FOR CONTINUOUS SPEECH RECOGNITION. AMIRKABIR[Internet]. 2003;14(53):80-92. Available from: https://sid.ir/paper/663/en

IEEE: Copy

S.M. SEYED AHADI, and SH. SHAMS, “WEIGHTED TRAINING OF CONTEXT DEPENDENT MODELS FOR CONTINUOUS SPEECH RECOGNITION,” AMIRKABIR, vol. 14, no. 53, pp. 80–92, 2003, [Online]. Available: https://sid.ir/paper/663/en

Related Journal Papers