Sorry, you need to enable JavaScript to visit this website.

Machine Translation of Speech (SLP-SSMT)

ANALYSIS OF MULTILINGUAL BLSTM ACOUSTIC MODEL ON AND HIGH RESOURCE LANGUAGES


The paper provides an analysis of automatic speech recognition
systems (ASR) based on multilingual BLSTM, where we used multi-task
training with separate classification layer for each language. The
focus is on low resource languages, where only a limited
amount of transcribed speech is available. In such
scenario, we found it
essential to train the ASR systems in a multilingual fashion and we
report superior results
obtained with pre-trained multilingual BLSTM on this task.
The high resource languages are also

poster.pdf

PDF icon poster.pdf (50 downloads)

Paper Details

Authors:
Submitted On:
12 April 2018 - 11:22am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

poster.pdf

(50 downloads)

Subscribe

[1] , " ANALYSIS OF MULTILINGUAL BLSTM ACOUSTIC MODEL ON AND HIGH RESOURCE LANGUAGES", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2390. Accessed: Aug. 21, 2018.
@article{2390-18,
url = {http://sigport.org/2390},
author = { },
publisher = {IEEE SigPort},
title = { ANALYSIS OF MULTILINGUAL BLSTM ACOUSTIC MODEL ON AND HIGH RESOURCE LANGUAGES},
year = {2018} }
TY - EJOUR
T1 - ANALYSIS OF MULTILINGUAL BLSTM ACOUSTIC MODEL ON AND HIGH RESOURCE LANGUAGES
AU -
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2390
ER -
. (2018). ANALYSIS OF MULTILINGUAL BLSTM ACOUSTIC MODEL ON AND HIGH RESOURCE LANGUAGES. IEEE SigPort. http://sigport.org/2390
, 2018. ANALYSIS OF MULTILINGUAL BLSTM ACOUSTIC MODEL ON AND HIGH RESOURCE LANGUAGES. Available at: http://sigport.org/2390.
. (2018). " ANALYSIS OF MULTILINGUAL BLSTM ACOUSTIC MODEL ON AND HIGH RESOURCE LANGUAGES." Web.
1. . ANALYSIS OF MULTILINGUAL BLSTM ACOUSTIC MODEL ON AND HIGH RESOURCE LANGUAGES [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2390

Prosodic Annotation Enriched Statistical Machine Translation


More and more linguistic information has been employed to improve the performance of machine translation, such as part of speech, syntactic structures, discourse contexts, and so on. However, conventional approaches typically ignore the key information beyond the text such as prosody. In this paper, we exploit and employ three prosodic features: pronunciation (phonetic alphabet and tone), prosodic boundaries and emphasis.

Paper Details

Authors:
Peidong Guo, Heyan Huang, Ping Jian, Yuhang Guo
Submitted On:
15 October 2016 - 12:10pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Prosodic Annotation Enriched Statistical Machine Translation(161014).pdf

(217 downloads)

Subscribe

[1] Peidong Guo, Heyan Huang, Ping Jian, Yuhang Guo, "Prosodic Annotation Enriched Statistical Machine Translation", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1250. Accessed: Aug. 21, 2018.
@article{1250-16,
url = {http://sigport.org/1250},
author = {Peidong Guo; Heyan Huang; Ping Jian; Yuhang Guo },
publisher = {IEEE SigPort},
title = {Prosodic Annotation Enriched Statistical Machine Translation},
year = {2016} }
TY - EJOUR
T1 - Prosodic Annotation Enriched Statistical Machine Translation
AU - Peidong Guo; Heyan Huang; Ping Jian; Yuhang Guo
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1250
ER -
Peidong Guo, Heyan Huang, Ping Jian, Yuhang Guo. (2016). Prosodic Annotation Enriched Statistical Machine Translation. IEEE SigPort. http://sigport.org/1250
Peidong Guo, Heyan Huang, Ping Jian, Yuhang Guo, 2016. Prosodic Annotation Enriched Statistical Machine Translation. Available at: http://sigport.org/1250.
Peidong Guo, Heyan Huang, Ping Jian, Yuhang Guo. (2016). "Prosodic Annotation Enriched Statistical Machine Translation." Web.
1. Peidong Guo, Heyan Huang, Ping Jian, Yuhang Guo. Prosodic Annotation Enriched Statistical Machine Translation [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1250