AI in Speech: What is next for Arabic Speech Recognition? – ArabicSpeech 2019

Date: 29-30 April, 2019

Location: HBKU Research Complex, Multipurpose Room

Introduction: The first annual meeting for the Arabic Speech community will be hosted by Qatar Center for Artificial Intelligence (QCAI) of Qatar Computing Research Institute (QCRI).

The purpose of this workshop is to bring together researchers, practitioners, students and industry experts in the fields of speech recognition and language processing with special attention to Arabic (standard and dialectal) to present recent advances, to discuss open research questions, and to bridge the gap between research and industry needs on certain concrete problems.

We will address these topics of interest through both invited and contributed talks from leading AI companies in speech processing, such as Google, Amazon and Facebook AI Research (FAIR). Additionally, the workshop will feature talks from prestigious speech research teams from Johns Hopkins, Edinburgh and Aalto  universities.

The Arabic Speech workshop will serve as a platform for the exchange of ideas and the identification of important and challenging applications. Arabic Speech ( an organization that runs for the benefit of Arabic speech science and technology community. Arabic speech will help to build innovation and technology capacities for the Arabic language. It will focus on tackling large-scale computing challenges that address real priorities that will impact people’s life. We address the state of the art as well as the state of the market. You can learn more about it here:

We invite colleagues from both academic and industrial fields to attend, contribute and discuss these topics with leading experts and practitioners from around the world.

To register to the event, please click here.

Please contact Dr Ahmed Ali for questions about the event.



Monday, 29 April 2019
8:30 – 9:00 Registration
9:00 – 9:30 Opening remark and Introduction to Arabic Speech
9:30 – 10:15 “Emotion recognition and sentiment analysis based on speech for call center applications”

by Najim Dehak | Johns Hopkins University

10:15 – 10:30 “WaveFont – Visualization of information from the voice in captions”

by Tim Schlippe | Silicon Surfer

10:30 – 10:45 AM Break
10:45 – 11:15 “Aalto submission to the MGB-3 challenge”

by Peter Smit| Aalto University &

11:15 – 11:45 “DNN statistical interpretation and normalization for ASR ”

by Erfan Loweimi | University of Edinburgh

11:45 – 12:15 “Speech recognition in the news room”

By Wassime Achkar| Aljazeera

12:15 – 13:30 LUNCH
13:30 – 14:15 “Transformers with convolutional context for ASR”

by Abdelrahman Mohamed | Facebook AI Research (FAIR)

14:15 – 14:45 “OCR and handwriting using kaldi”

by Jan Trmal | Johns Hopkins University

14:45 – 15:15 PM Break
15:15 – 15:35 “Arabic linguistic resources at Birzeit University”

by Mustafa Jarrar | Birzeit University

15:35 – 15:55 “Building large scale speech resources for Arabic – ELRA”

by Khalid Choukri | ELDA

15:55 – 16:15 “Algerian hierarchical classification  for spoken dialect identification
by Hadda Cherroun | Université Amar Telidji Laghouat
16:15 – 17:00 “Speech and Language Technologies for Arabic
by Levent Arslan | Bogazici University and SESTEK Inc.

Leave a Reply

Your email address will not be published. Required fields are marked *