QCRI's live speech translation system

Fahim Imaduddin Dalvi; Yifan Zhang; Sameer Khurana; Nadir Khan Durrani; Hassan Sajjad; Ahmed Abdelali; Hamdy Mubarak; Ahmed Ali; Stephan Vogel

QCRI's live speech translation system

Fahim Imaduddin Dalvi
, Yifan Zhang
, Sameer Khurana
, Nadir Khan Durrani
, Hassan Sajjad
, Ahmed Abdelali
, Hamdy Mubarak
, Ahmed Ali
, Stephan Vogel

Qatar Computing Research Institute

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper presents QCRI’s Arabic-to-English live speech translation system. It features modern web technologies to capture live audio, and broadcasts Arabic transcriptions and English translations simultaneously. Our Kaldi-based ASR system uses the Time Delay Neural Network (TDNN) architecture, while our Machine Translation (MT) system uses both phrase-based and neural frameworks. Although our neural MT system is slower than the phrase-based system, it produces significantly better translations and is memory efficient.

Original language	English
Title of host publication	Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics
Publication status	Published - 2017

Access to Document

https://scholar.google.com/citations?view_op=view_citation&hl=en&user=uQGCv10AAAAJ&pagesize=100&citation_for_view=uQGCv10AAAAJ:YsMSGLbcyi4C

Cite this

Dalvi, F. I., Zhang, Y., Khurana, S., Durrani, N. K., Sajjad, H., Abdelali, A., Mubarak, H., Ali, A., & Vogel, S. (2017). QCRI's live speech translation system. In Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics https://scholar.google.com/citations?view_op=view_citation&hl=en&user=uQGCv10AAAAJ&pagesize=100&citation_for_view=uQGCv10AAAAJ:YsMSGLbcyi4C

@inproceedings{6e7d014b90b24b2284f7d26ce943e26a,

title = "QCRI's live speech translation system",

abstract = "This paper presents QCRI{\textquoteright}s Arabic-to-English live speech translation system. It features modern web technologies to capture live audio, and broadcasts Arabic transcriptions and English translations simultaneously. Our Kaldi-based ASR system uses the Time Delay Neural Network (TDNN) architecture, while our Machine Translation (MT) system uses both phrase-based and neural frameworks. Although our neural MT system is slower than the phrase-based system, it produces significantly better translations and is memory efficient. ",

author = "Dalvi, \{Fahim Imaduddin\} and Yifan Zhang and Sameer Khurana and Durrani, \{Nadir Khan\} and Hassan Sajjad and Ahmed Abdelali and Hamdy Mubarak and Ahmed Ali and Stephan Vogel",

year = "2017",

language = "English",

booktitle = "Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics",

}

Dalvi, FI , Zhang, Y, Khurana, S, Durrani, NK, Sajjad, H, Abdelali, A, Mubarak, H, Ali, A & Vogel, S 2017, QCRI's live speech translation system. in Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics. <https://scholar.google.com/citations?view_op=view_citation&hl=en&user=uQGCv10AAAAJ&pagesize=100&citation_for_view=uQGCv10AAAAJ:YsMSGLbcyi4C>

TY - GEN

T1 - QCRI's live speech translation system

AU - Dalvi, Fahim Imaduddin

AU - Zhang, Yifan

AU - Khurana, Sameer

AU - Durrani, Nadir Khan

AU - Sajjad, Hassan

AU - Abdelali, Ahmed

AU - Mubarak, Hamdy

AU - Ali, Ahmed

AU - Vogel, Stephan

PY - 2017

Y1 - 2017

N2 - This paper presents QCRI’s Arabic-to-English live speech translation system. It features modern web technologies to capture live audio, and broadcasts Arabic transcriptions and English translations simultaneously. Our Kaldi-based ASR system uses the Time Delay Neural Network (TDNN) architecture, while our Machine Translation (MT) system uses both phrase-based and neural frameworks. Although our neural MT system is slower than the phrase-based system, it produces significantly better translations and is memory efficient.

AB - This paper presents QCRI’s Arabic-to-English live speech translation system. It features modern web technologies to capture live audio, and broadcasts Arabic transcriptions and English translations simultaneously. Our Kaldi-based ASR system uses the Time Delay Neural Network (TDNN) architecture, while our Machine Translation (MT) system uses both phrase-based and neural frameworks. Although our neural MT system is slower than the phrase-based system, it produces significantly better translations and is memory efficient.

M3 - Conference contribution

BT - Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics

ER -

QCRI's live speech translation system

Abstract

Access to Document

Fingerprint

Cite this